GitHub Trending

Prompt as Code | GPT-Image2 Industrial Prompt Engine & Template Library, 500+ Reverse-Engineered Cases, 20+ Industrial Templates English | 简体中文 | 日本語 🌐 Visual Website Use the live site at gpt-image2.canghe.ai to browse the gallery as a product experience: open large previews, copy full prompts, filter by style or scenario, test generation after Google sign-in, and jump back to the source case on GitHub. Community 交流群 Join the GPT-Image2 discussion group to exchange prompts, workflows, and creative ideas with other users. Visit the community page to join. Follow the WeChat official account 苍何 or scan the QR code below to receive project updates, new cases, and practical tutorials. ❤️ Sponsors Want to appear here? Support the project through GitHub Sponsors, or search 苍何 on WeChat and send your product name plus a short sponsorship note. | Sponsor | Description | | ------- | ----------- | | | Thanks to APIMart for sponsoring this project! APIMart is a low-cost API platform for AI image & video generation — GPT-Image-2 from $0.006/image, 160+ images per dollar. One async API covers both image and video: submit a task, get an ID, fetch results via polling or callback. Batch tens of thousands of images without timeouts, switch models without changing code. Pay-as-you-go with no monthly fee — sign up here to get started. | | | Thanks to hiapi for sponsoring this project! hiapi is an AI image & video generation API platform — GPT-Image-2 (text-to-image, image edit, 1K–4K) alongside video models like Seedance, Kling and Wan, all through one unified async API: submit a task, get a task_id, fetch results by polling or callback, batch without timeouts, switch models without code changes. Every result is stored on hiapi's own CDN with persistent storage, so your image/video URLs stay available long-term and can be fetched anytime — no rushing to download and back them up yourself. Native Remote MCP and Agent Skills plug straight into Claude Code & Cursor. Chinese UI & docs, WeChat Pay, pay-as-you-go with no monthly fee — new users get $1 free credit (~50 images). Sign up here. | | | Thanks to PackyCode for sponsoring this project! PackyCode is a stable, high-performance API relay provider for Claude Code, Codex, Gemini, and more. Automatic failover, smart routing, and unlimited concurrency help turn AI coding into a reliable productivity tool. Register here to get started. | | | Project sponsor. PPToken provides API relay and key distribution for ChatGPT, Claude, Gemini, and other mainstream AI models, with low-latency access, high availability, pay-as-you-go billing, and flexible subscription plans. | ⚡️ Project Vision After GPT-Image2 became widely available, AI image generation moved from "can it make an image?" to "can it make stable, controllable, reusable images?" This project turns scattered community examples into Prompt-as-Code assets that are easier for agents and automation workflows to reuse. The core goal is simple: compress prose-style prompts into structured protocols. When you need batch generation, template systems, or production workflows, this structure is more valuable than a pile of isolated examples. 🧱 Atomic schema: split subjects, lighting, materials, layout, and visual details into composable parts ⚙️ Workflow friendly: designed for agents, scripts, and automation systems 🧬 Structured control: improve controllability for layout, copy, and information hierarchy 📖 Quick Links Full case gallery Gallery Part 1: cases 1-165 Gallery Part 2: cases 166-544 Industrial prompt templates and pitfalls guide Agent skill: GPT-Image2 Style Library MIT License Full disclaimer 🗂️ Category Overview Start with the case album to find a visual direction, then open the prompt template categories to turn that direction into reusable structure. 🖼️ Case Album 🧩 UI & Interfaces73 cases Apps, websites, dashboards, social screenshots, and product interfaces. View Cases 📊 Charts & Infographics53 cases Infographics, knowledge maps, technical explainers, and structured diagrams. View Cases 📰 Posters & Typography90 cases Event posters, covers, type-driven visuals, and strong layout compositions. View Cases 🛍️ Products & E-commerce42 cases Product shots, detail pages, packaging, selling points, and ads. View Cases 🏷️ Brand & Logos27 cases Logos, identity systems, brand touchpoints, and campaign visuals. View Cases 🏛️ Architecture & Spaces12 cases Architecture renders, interiors, city maps, and spatial concepts. View Cases 📷 Photography & Realism78 cases Portraits, phone photography, film texture, and commercial photography. View Cases 🎨 Illustration & Art59 cases Illustration, art styles, material experiments, and decorative images. View Cases 🧍 Characters & People31 cases Character design, pose references, cards, and 3D toys. View Cases 🎬 Scenes & Storytelling21 cases Storyboards, narrative scenes, livestream frames, and worldbuilding. View Cases 🏮 History & Classical Chinese Themes16 cases Classical scrolls, historical figures, traditional themes, and poetry visuals. View Cases 📚 Documents & Publishing11 cases White papers, manuals, encyclopedic plates, and publishing layouts. View Cases 🧪 Other Use Cases28 cases Creative experiments, special tasks, mixed workflows, and practical cases. View Cases 🖼️ Full Gallery Browse all 544 cases by gallery part and category. Open Gallery ⭐ Latest Additions The newest community cases and workflows collected in the repo. View Latest 🧩 Prompt Template Categories The prompt body remains in the original template document for now. This homepage only adds an English navigation layer. Template Page 1 / 4: Design & Information | Category | Template Entry | Core Capability | |---|---|---| | 🧩 UI & Interfaces | View Prompts | Components, page hierarchy, screenshot texture | | 📊 Charts & Infographics | View Prompts | Modules, arrows, data structure, readability | | 📰 Posters & Typography | View Prompts | Layout, headline systems, people, visual impact | Template Page 2 / 4: Commerce & Space | Category | Template Entry | Core Capability | |---|---|---| | 🛍️ Products & E-commerce | View Prompts | Product selling points, packaging, detail-page structure | | 🏷️ Brand & Logos | View Prompts | Logos, identity, brand touchpoint systems | | 🏛️ Architecture & Spaces | View Prompts | Perspective, materials, indoor and outdoor lighting | Template Page 3 / 4: Imaging & Characters | Category | Template Entry | Core Capability | |---|---|---| | 📷 Photography & Realism | View Prompts | Lenses, lighting, realistic textures | | 🎨 Illustration & Art | View Prompts | Brushwork, materials, art styles | | 🧍 Characters & People | View Prompts | Character design, pose sheets, consistency | Template Page 4 / 4: Narrative & Extensions | Category | Template Entry | Core Capability | |---|---|---| | 🎬 Scenes & Storytelling | View Prompts | Storyboards, worldbuilding, emotional pacing | | 🏮 History & Classical Chinese Themes | View Prompts | Dynasties, clothing, scroll-style narrative | | 📚 Documents & Publishing | View Prompts | Page systems, tables of contents, layout rules | | 🧪 Other Use Cases | View Prompts | Mixed tasks, experimental workflows, special outputs | 🤖 Agent Skill This repository includes an agent skill for choosing GPT-Image2 styles, templates, categories, and scene tags from the same data used by the website. Package links: npm / GitHub Packages Example output from a city-life-system-map request using the style library skill. Quick Install for Agent Skills Recommended for Claude Code, Codex, Cursor, and other tools supported by skills: npx skills add freestylefly/awesome-gpt-image-2 --skill gpt-image-2-style-library --agent claude-code codex --global --yes --copy Install to every supported local agent: npx skills add freestylefly/awesome-gpt-image-2 --global --all --copy Claude Code Plugin Marketplace Run these commands inside Claude Code: /plugin marketplace add freestylefly/awesome-gpt-image-2 /plugin install gpt-image-2-style-library@awesome-gpt-image-2 npm CLI If you prefer npm, install the CLI and then sync the skill into local agent folders: npm install -g gpt-image-2-style-library gpt-image-2-style-library install all You can also run it without a global install: npx gpt-image-2-style-library install all Install from GitHub Packages: npm login --scope=@freestylefly --registry=https://npm.pkg.github.com npm install -g @freestylefly/gpt-image-2-style-library --registry=https://npm.pkg.github.com gpt-image-2-style-library install all install all writes the skill to the common local folders used by Codex and Claude Code, including /.codex/skills, /.claude/skills, and ~/.agents/skills. Restart the agent session after installing. Use it with a request like: Use gpt-image-2-style-library to create an infographic prompt about Codex. For local source development: npm run generate:style-skill npm run install:skill The skill source lives at agents/skills/gpt-image-2-style-library. Its generated reference comes from data/style-library.json, so the website and Agent workflow share one style library. 🔐 Website Auth & Generation The visual site includes login-gated case generation powered by Supabase Auth, Supabase Postgres, and a Vercel Function proxy for the GPT Image 2 API. Required Vercel environment variables: VITE_SUPABASE_URL= VITE_SUPABASE_ANON_KEY= SUPABASE_SERVICE_ROLE_KEY= SUPER_ADMIN_EMAILS=2689458656@qq.com,canghe0818@gmail.com CIYUAN_API_KEY= CIYUAN_BASE_URL=https://ciyuan.today APP_URL=https://gpt-image2.canghe.ai STRIPE_SECRET_KEY= STRIPE_WEBHOOK_SECRET= VITE_GA_MEASUREMENT_ID= GA4_PROPERTY_ID= GOOGLE_ANALYTICS_CLIENT_ID= GOOGLE_ANALYTICS_CLIENT_SECRET= GOOGLE_ANALYTICS_REFRESH_TOKEN= Setup checklist: Apply supabase/migrations/202605090001_user_credits.sql to the Supabase project. Apply supabase/migrations/20260509090000_membership_billing.sql to add membership plans, credit packs, Stripe order records, and credit adjustment RPCs. Apply supabase/migrations/20260721090000_alipay_webpay.sql before enabling Alipay website payments, then configure each credit pack's reviewed CNY price. See Alipay website payment setup. Apply supabase/migrations/20260722090000_paid_community.sql before enabling the paid community. Keep COMMUNITY_PAYMENT_ENABLED=false until the protected QR, Alipay onboarding, and production payment/refund checks are complete. See the paid community runbook. Apply supabase/migrations/20260512090000_google_account_center.sql to add account usage summaries and forced credit charging for super admins. Apply supabase/migrations/20260512143000_pricing_admin_metrics.sql to update the $5 / 300 credits catalog and add admin dashboard metrics. Apply supabase/migrations/20260515090000_case_favorites.sql to add per-user case favorites. Add https://gpt-image2.canghe.ai and local dev URLs such as http://127.0.0.1:5173 to Supabase Auth redirect URLs. Enable the Google Provider after adding Google OAuth credentials in the Supabase Dashboard. To force Google-only sign-in, disable the Email Provider in Supabase Auth settings. Keep SUPABASE_SERVICE_ROLE_KEY only in server-side environments such as Vercel Environment Variables. Configure Stripe Checkout with the webhook URL https://gpt-image2.canghe.ai/api/billing/webhook. Subscribe the Stripe webhook to checkout.session.completed, invoice.payment_succeeded, customer.subscription.updated, and customer.subscription.deleted. Keep STRIPE_SECRET_KEY and STRIPE_WEBHOOK_SECRET only in server-side Vercel Environment Variables. Create a GA4 property for gpt-image2.canghe.ai, add the measurement ID to VITE_GA_MEASUREMENT_ID, and copy the numeric property ID to GA4_PROPERTY_ID. Create a Google OAuth Web Client with http://localhost:8080/oauth2callback as an authorized redirect URI, then add GOOGLE_ANALYTICS_CLIENT_ID and GOOGLE_ANALYTICS_CLIENT_SECRET to local .env.local. Run npm run ga4:oauth, open the generated URL, approve the analytics.readonly permission, paste the callback URL into the terminal, then add the returned GOOGLE_ANALYTICS_REFRESH_TOKEN to Vercel as a Sensitive environment variable. 🖼️ Featured Cases Case 1: Infographic Visualization Urban Metabolism Atlas An engineering-whitepaper-style infographic case for studying modular structure, information hierarchy, and bilingual labels. View full case Case 2: Social Media Interface Screenshot Ailln AI A mixed "product interface + social content screenshot" case for controlling text blocks, UI frames, and content cards. View full case Case 6: Illustration Art Japanese fantasy illustration A Japanese fantasy illustration example for studying atmosphere, color, and large-scene composition. View full case Case 17: Interaction Design Diagram Interaction design diagram A classic "structured breakdown + explanatory layout" case for product diagrams and poster-like technical explainers. View full case Case 166: Twelve Gold Saints Card Set Twelve Gold Saints card set A multi-card, unified-style case for studying batch generation and series design. View full case Case 310: Snack Brand Technical Breakdown Snack brand technical breakdown A strong hybrid of brand narrative, structural breakdown, and commercial presentation. Useful as an "infographic + brand visual" reference. View full case Canghe Original Tests Case 330: Moonlit Livestream Scene A high-fidelity livestream screenshot reference for UI atmosphere, comments, and realistic people. View Case Case 334: RAG Technical Explainer A reference for technical concepts, process arrows, and Chinese explanation modules. View Case Case 338: Red Cliff Classical Scroll A complete example of scroll format, classical Chinese narrative, and full-text layout. View Case Case 331: Hand-Drawn Xi'an Watercolor Map A lightweight reference for city maps, hand-drawn routes, and landmark labels. View Case Case 332: Tea Pi Product Poster A beverage product image combining Chinese selling points and a clean commercial poster style. View Case Case 339: Apple-Style Nature Science Poster Minimal studio photography, a natural subject, and science-poster information layout. View Case Latest Community Additions Only the latest collection and import run is shown here. Older imports stay in the full gallery. Case 539: Raw Sketchy Portrait Poster A customizable rough-ink portrait poster prompt combining an oversized subject, close companion, minimal scenery, restrained palette, and intentionally imperfect print texture. View Case Case 540: Dreamlike Futuristic World Poster A vertical editorial art-poster prompt for surreal future cities with sculptural architecture, oversized plants, tiny people, vintage travel texture, and luxury pacing. View Case Case 541: 50/50 Mixed-Media Memory Card A reference-photo editing prompt that keeps the top photo intact and converts the lower half into a handmade paper memory card with wax-crayon sketching. View Case Case 542: Black-and-White Typographic Portrait Poster A high-contrast monochrome typographic portrait prompt that fuses side-profile silhouettes, rough ink texture, microtext, and a large readable text block. View Case Case 543: Travel Souvenir Enamel Pin Badge A product-design prompt that turns a travel photo into a glossy enamel pin badge with gold dividers, scene hierarchy, simplified figure rules, and fabric backdrop. View Case Case 544: Preschool Vocabulary Learning Card A preschool learning-card prompt for clean object-and-part vocabulary layouts with realistic produce, dotted arrows, simple illustration, and clear labels. View Case 🧩 Template Entry The full template library lives in docs/templates.md. Use the Prompt Template Categories above for quick category jumps, or open Industrial prompt templates and pitfalls guide for the complete template text. 🚀 How To Use This Repository Start from the featured cases and decide what output type you want to imitate. Open the full gallery and find nearby cases. Copy structure first, then style words. Return to the template page and fill your business variables into the general or JSON templates. 📄 Notes & Disclaimer Acknowledgements & Sources During collection and research, this project references public prompt-library content from YouMind and OpenNana for learning, summarization, and methodology research. Copyright belongs to the original authors or platforms. If any content is infringing or inappropriate, please contact us and we will correct or remove it promptly. Disclaimer This project only organizes publicly accessible community prompts and example images for learning and research. It does not claim ownership of any third-party original content. All prompt cases and generated images in this repository were initially inspired by public community sources, especially YouMind and OpenNana. The project aims to break down strong examples into reusable structured protocols for learning, summarization, and automated testing with large-model agents. We make every effort to preserve original sources, including author profiles, original post links, and source repository links. For third-party content, we follow source repository statements, licenses such as CC BY 4.0, and the relevant platform rules. If you are the original author or rights holder and believe an entry should not be displayed, please open an Issue with the entry link. We will review it and remove it quickly when appropriate. This repository does not guarantee that third-party content can be used commercially. Please obtain authorization from the original rights holder before commercial use. If this library helps you, please star the repository. Star History Star History Chart 📜 License This project is open source under the MIT License. You can use, modify, distribute, and build on it freely while preserving the license notice.

Community plugin marketplace for Claude Cowork and Claude Code. Read-only mirror — submit plugins at clau.de/plugin-directory-submission.

English · 简体中文 Archify product preview Archify Turn a codebase or system description into a polished, interactive system map — directly in chat. Archify is a Node.js rendering and validation system for Cursor, Claude Code, Codex CLI, and OpenCode. Agents produce typed JSON IR; Archify deterministically compiles it into HTML/SVG. Open it and present — five diagram types, four presets, dark/light themes, built-in brand marks, and finite motion Review architecture changes before merge — compare two validated snapshots as Before / Delta / After, with exact added, removed, changed, moved, and rerouted facts Every interaction stays grounded — search nodes, optionally open revision-verified source, trace upstream/downstream authored reach and exact routes, compare roles, and play guided stories without inventing topology One file, ready to trust and share — typed JSON IR and deterministic checks produce self-contained HTML plus PNG, SVG, WebM, and 1200×630 share cards License Agent Skill Stable Version Current stable version: v2.16.0. See Changelog. Project page · Scenario guide · Proof Lab npx skills add tt-a1i/archify -g Using Cursor? Open the agent-aware quick start for exact global and project commands. No repository is required: describe the system in any agent chat. ❤️ Sponsors APINEBULAAPINEBULA sponsors Archify with one API for Claude, GPT, Gemini, and more. Register through Archify and use Archify for 10% off. EverMind · RavenEverMind sponsors Archify and builds memory infrastructure for agents. Its Raven harness supports Archify as a Skill for verified, interactive system maps. Want to sponsor Archify? Contact us by email. See Archify in action These are generated Archify artifacts, not product mockups. Click a frame to open its live, shareable state. Three real generated artifacts. Signal Flow · Blueprint · Classic · open the interactive Proof Lab ↗ | Guided story | Route probe | Semantic lens | |---|---|---| | Agent workflow playing one authored chapter | Cache-miss sequence showing the Web App to Postgres route | Production architecture comparing backend and database roles | | Play one finite named chapter. | Inspect the shortest authored directed path. | Compare real traffic between semantic roles. | The Proof Lab contains all 11 checked-in scenarios, their JSON sources, named views, and validation receipts. A real repository, mapped from source MCO runtime architecture generated from the public mco-org/mco repository Archify traced mco-org/mco at 9f1a1cf and produced this checked map. Open it ↗ · trace reach ↗ · typed source Preview Same diagram, two themes, one click to switch: | Dark | Light | |---|---| | Dark theme | Light theme | The Export menu copies PNG to the clipboard and downloads static or motion formats: Export menu Use Copy Share Card when you want a canonical 1200×630 image for a README, release, or social post. After tracing a route, Export → Route Share Card downloads that authored path as a 1200×630 PNG with the full diagram retained for context. Route Share Card showing the exact Users to API Server path with the full architecture retained as context After tracing authored Upstream or Downstream reach, Export → Reach Share Card captures that exact reading without claiming runtime impact. MCO downstream Reach Share Card showing authored relationships from Command Router Open examples/web-app.html locally to try the complete viewer. Quick start 1. Install npx skills add tt-a1i/archify -g For an explicit, non-interactive Cursor install: npx -y skills add tt-a1i/archify --skill archify --agent cursor --global --copy --yes To try without installing: npx skills use tt-a1i/archify@archify --agent codex DSH community opt-in: dsh plugin --profile web add @tt-a1i/archify-dsh@0.1.0 The agent switcher covers cursor, codex, claude-code, and opencode. For Raven's manual ZIP install, extract archify.zip into /.raven/workspace/skills; it yields /.raven/workspace/skills/archify. Raven is not a switcher target. Archify may GET the fixed stable manifest solely to show an optional reminder; it never downloads or installs updates. Successful checks wait about 72 hours (±20%); active use retries failures after 6, then 24 hours. The server sees normal HTTP metadata (IP and time), but receives no version, Agent, project data, prompts, account/device ID, or ETag. You decide whether and when to update. Set ARCHIFY_UPDATE_CHECK_DISABLED=1 to disable networking and reminder-state writes. 2. Start from a description — no repository required Use Archify to draw: Browser -> API -> Redis cache -> PostgreSQL fallback. For source evidence, open a repository and ask: Analyze this repository, then use archify to create a high-level runtime architecture diagram. Show 8–12 core components, one primary path, external dependencies, and trust boundaries. Put supporting detail in cards instead of adding more edges. 3. Refine in chat Continue with focused requests such as add Redis, move auth to the left, or highlight the rollback path. Archify keeps the typed source available for targeted iteration. Choose the right diagram | Type | Best for | Include in your prompt | |---|---|---| | Architecture | Components, services, storage, boundaries | Scope, core components, primary path | | Workflow | CI/CD, approvals, tool calls, runbooks | Participants, order, branches, exceptions | | Sequence | API calls, cache fallback, auth, async traces | Callers, callees, returns, timing | | Data Flow | Pipelines, lineage, PII, consumers | Sources, transforms, stores, boundaries | | Lifecycle | States, retries, waits, terminal outcomes | States, events, retry and cancellation paths | Architecture's optional deployment-ownership profile fails closed when authored owners, region placement, private database scope, or named crossings are missing; it is never implicit and does not inspect live infrastructure. See the checked deployment proof. For design or PR review, Architecture Delta compares validated Before / Delta / After snapshots with a machine receipt. Select an authored change or play one finite, viewer-only Review; it infers no impact, risk, or merge safety. node archify/bin/archify.mjs compare architecture base.json head.json architecture-delta.html --json Architecture Delta showing added, removed, changed, and moved authored facts Not sure which one fits? Use the interactive scenario guide, or ask the zero-dependency CLI: node archify/bin/archify.mjs guide "Show an API request with Redis cache miss" node archify/bin/archify.mjs guide "Map Kafka topics, consumer groups, replay, and DLQ" --json Workflow keeps the happy path clear across lanes: Workflow example Sequence explains one interaction over time: Sequence example Data Flow makes movement and sensitivity boundaries explicit: Data Flow example Lifecycle separates progress, waits, retries, and terminal outcomes: Lifecycle example Architecture examples: web-app · Archify pipeline · grid placement · desktop agent Why Archify Layout judgment over generic auto-layout — the agent chooses hierarchy, spacing, routes, and emphasis; shared automatic endpoints spread deterministically instead of piling arrows on one midpoint. Typed JSON IR — every renderer-backed mode has a schema and reproducible source. Atomic validation before delivery — schema, layout, HTML/SVG, route, and label-to-route clearance checks must all pass before a showcase artifact replaces the last known good output. Failures come with a repair receipt — validate --json and deliver --json return stable rule codes, the exact subject, measured evidence, and only supported repair controls instead of a Node stack or an unstructured retry guess. Last-good live preview — an optional desktop loop watches one JSON file, refreshes only after the latest candidate passes every gate, and keeps the previous verified diagram visible when a save is incomplete or invalid. Truthful interaction — focus, upstream/downstream reach, exact routes, role comparison, and stories reuse authored nodes and relationships instead of inventing topology or claiming runtime impact. Source evidence, only when requested — Evidence-backed Architecture nodes mark themselves SRC n and open Git-verified files and line ranges pinned to one public commit; ordinary artifacts stay source-free. Portable by default — the result is one HTML file; exports remain full-diagram and free of temporary viewer state. Archify is not a general-purpose drawing editor or a Mermaid theme. It turns technical intent into a communication artifact. How it works | Step | What happens | |---|---| | Generate | The agent creates typed JSON IR from your description. | | Validate | Bundled validators and layout rules check the source; failures identify the exact local repair in machine-readable JSON. | | Preview (optional) | A loopback-only desktop session watches one source and reloads only verified revisions; failures keep the last-good artifact. | | Deliver | A same-directory candidate is rendered and checked; only a passing artifact atomically replaces the target, then optional --open launches that exact file. | | Iterate | The agent updates the source while unrelated structure stays stable. | Useful repository commands: cd archify node bin/archify.mjs doctor node bin/archify.mjs demo /tmp/archify-demo node bin/archify.mjs guide "Show CI/CD checks, approval, deploy, and rollback" node bin/archify.mjs validate workflow examples/agent-tool-call.workflow.json --quality showcase --json node bin/archify.mjs preview workflow examples/agent-tool-call.workflow.json /tmp/workflow.html --quality showcase node bin/archify.mjs deliver workflow examples/agent-tool-call.workflow.json /tmp/workflow.html --quality showcase --open --json preview is an explicit loopback-only desktop mode: it watches one JSON file on a random 127.0.0.1 port, keeps the last verified output through failures, stops with Ctrl-C, and adds no generated-HTML runtime. Use --no-open for tests or manual URL opening. deliver --open is an opt-in one-shot handoff after commit. Opener failure preserves success; JSON remains on stdout and the absolute fallback path goes to stderr. On failure, validate --json and deliver --json emit one JSON object. Apply only each diagnostics] subject's supportedFixes, within the Skill's two correction rounds; visual review remains separate. Settings: { "meta": { "locale": "en", "animation": "trace", "visual_preset": "signal-flow" } } meta.locale=en|zh-CN localizes page title, Legend, states/errors, a11y, HTML/SVG lang—never authored content. Otherwise omit; preserve requested-language copy; disclose English fallback. Static omits animation; classic defaults. Explore and share the output | Action | Control | |---|---| | Open the factual Diagram Guide | ? | | Find and focus a semantic node | / | | Trace upstream/downstream authored reach | Focus a node → Upstream / Downstream | | Probe a directed route and inspect its journey | R or PATH | | Compare one or two semantic roles | L or LENS | | Open the live overview radar | M or MAP | | Play a guided story / change chapter | P / [ ] | | Enter Presentation Stage | F | | Choose visual style (S cycles) / toggle theme / open Export | S / T / E | | Zoom or reset | + / - / 0 | Stable links can restore #focus=, #focus=&reach=upstream|downstream, #relation=, #route=, #lens=, and #view=. Reader-driven motion is finite, respects prefers-reduced-motion, and never enters canonical exports. The complete generation and viewer contract lives in [archify/SKILL.md. Installation options | Surface | Install location or method | Capability | |---|---|---| | Raven | Manual ZIP into /.raven/workspace/skills → /.raven/workspace/skills/archify | Full renderer + validation workflow | | Claude Code | ~/.claude/skills/ or .claude/skills/ | Full renderer + validation workflow | | Codex CLI | ~/.agents/skills/ or .agents/skills/ | Full renderer + validation workflow | | opencode | ~/.config/opencode/skills/, .opencode/skills/, or .agents/skills/ | Full renderer + validation workflow | | Claude.ai | Upload archify.zip under Settings → Capabilities → Skills | Depends on Node.js access in the sandbox | | Project Knowledge | Upload archify.zip to the project | Prompt-driven architecture fallback | DeepSeek Harness: Community integration, not an official DeepSeek product; developer-preview @deepseek-ai/dsh@0.1.0-rc.6, Node ^22.19.0 || >=24.0.0. Install: dsh plugin --profile web add @tt-a1i/archify-dsh@0.1.0; invoke: Use the archify skill to map this repository's runtime architecture.; remove: dsh plugin --profile web remove @tt-a1i/archify-dsh. No telemetry. Shell files need exact workspace paths, not Web Produced Files. Details. Reference and scope Schema reference · Skill · Examples · Agent cookbook Changelog Roadmap Generated Proof Lab Automatic Mermaid parsing, general-purpose auto-layout, hosted sharing, and WYSIWYG editing are intentionally outside the current scope. License MIT — free to use, modify, and distribute. Contributing Issues, pull requests, and real-world diagrams are welcome. Start with the contribution guide, use the reproducible bug form for failures, or submit a validated diagram through the community showcase form. · LINUX DO Star History

Beautiful, Modern & Opinionated Linux

Apache Maka (Incubating) Incubating at The Apache Software Foundation A local-first Agent workspace built for real work. Maka inspects projects, runs tools under a sandbox boundary, and records model messages and tool calls as recoverable execution facts — on your machine, through one Runtime Host. Daily builds from main for developers and testers. Not an ASF release, not intended for production use. Maka — Your work. Your agent. !NOTE] Apache Maka (Incubating) is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator PMC. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision-making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF. [DISCLAIMER-WIP records the issues the project is currently aware of. !IMPORTANT] Maka is under active development. Data formats, CLI commands, and experimental capabilities may still change. Why Maka Your machine, your data. Sessions, settings, and run records stay local by default. You bring the model: a cloud API, a local model, or a compatible gateway. The record is kept. Model messages, tool calls, tool results, and how a turn ended are written down. The UI and the next model call are views of that record, not the only copy. Shorter context is not deleted history. Maka can omit old tool output from the next prompt without throwing away the saved evidence. One place runs the agent. Desktop, the terminal, and Maka evaluation all go through Runtime Host. Eval only owns the experiment and its scores. Read [Maka Backend Architecture for the design. Surfaces | Entry point | Best for | Current capability | |---|---|---| | Desktop | Daily interaction, file and Artifact workflows, model and permission setup | Electron + React with streaming sessions, tool timelines, branching, search, and recovery | | TUI / CLI | Using Maka in the current project directory or running one non-interactive Turn | maka, maka run; shares workspace and model connections with Desktop | | Eval | Reproducible benchmark experiments across Maka and external subjects | maka eval run --out | Current capabilities Agent Runtime Multiple model connections, streaming output, thinking, usage, and clearer provider errors; Built-in tools: Read, Write, Edit, Bash, Glob, Grep. Computer Use and catalog skills are optional and not on by default; Tools that leave the sandbox must be approved; runs can be aborted; failures are classified; A durable execution record, crash recovery, and optional resume of an interrupted turn. Desktop workspace Create, archive, search, rename, retry, regenerate, and branch sessions from a Turn; Artifact lists and previews, workspace instructions, model settings, and sandbox settings; Local memory and web search when configured; Chat apps (IM bots) are experimental. See IM onboarding. Evaluation Declarative multi-arm experiments expanded into task × repetition × subject cells; Immutable per-cell attempts with targeted infrastructure replacement and earliest-valid selection; A small result kernel for score, normalized usage, attributable cost, duration, status, failure reason, and artifacts; Maka subjects execute only through Runtime Host; external subjects use generic external subject adapters. Quick start Releases and downloads Apache Maka has not made an Apache release yet. Everything currently published from this repository or from a package registry was produced before or during incubation, is not an Apache Software Foundation release, and has not been reviewed or voted on by the Incubator PMC. Once Apache releases exist, the official release is the source release published by the ASF and approved by the podling PPMC and the Incubator PMC. A package built from that source and distributed elsewhere, for example through a package registry or as a Desktop installer, is a convenience artifact rather than the release itself, and it is valid only when it is built from an approved source release. .github/ASF_SOURCE_RELEASE.md holds the candidate contract, signing path, and verification steps. Desktop Nightly is built daily from main for developers and testers. It is not an ASF release and is not intended for production use. Desktop currently targets Apple Silicon Macs (arm64). Intel Macs and Linux are not supported yet. Windows is an unsigned preview, not a supported release tier. Requirements Node.js 22.19 or newer (CI uses Node.js 24); npm (the lockfile and scripts use npm; the current packageManager is npm 11); Git; ripgrep, used by Runtime's Grep tool. Start Desktop git clone https://github.com/apache/maka.git cd maka npm ci npm run dev npm run dev starts the Desktop development environment with HMR. To build every workspace before starting Electron, use: npm run dev:full Direct Peer and Peer Mesh development additionally requires Rust stable 1.98 or newer and the platform linker (Xcode Command Line Tools on macOS, MSVC Build Tools on Windows). Use the peer-enabled entry point so the native addon is built before Desktop starts: npm run dev:peer # HMR npm run dev:full:peer # full build If dependencies were installed with ELECTRON_SKIP_BINARY_DOWNLOAD=1, install the Electron platform binary before starting: node node_modules/electron/install.js First run Maka does not bundle a shared model account. On first launch: Open Settings → Models; Add an API, local-model, or supported account connection; Test it and choose a default model; Return to the workspace and start a task. The app distinguishes configured, send-ready, and experimental connection states. An account flow that is not wired into Runtime is not presented as a usable model. Terminal entry points For the public npm package, see the CLI installation and usage guide. The commands below run the development CLI from a source checkout. Build the workspaces first: npm run build Then start the TUI or run one Turn: npm run cli:dev npm run cli:dev -- run "Summarize this repository and identify its most important risk" npm run cli:dev -- run --graph "Implement two independent slices, integrate them, then review the result" npm run cli:dev -- --help The TUI also accepts /graph on, /graph off, and /graph . Non-interactive --graph runs wait for the durable Graph to finish before printing the final supervisor output. Graph implementation operators use isolated Git worktrees, so the source project must be a clean Git worktree. The repository CLI uses the same Maka Dev profile as a development Desktop build. The released maka binary continues to use the Maka profile; the two profiles are not copied or synchronized automatically. Evaluation specs and adapters live in packages/eval. Architecture The backend spine is: Desktop / TUI / CLI → Runtime Host → SessionManager → AgentRun ↓ Model + Tool Runtime → Runtime Event Log ↓ Context / Session / UI projections Experiment → Cells → Attempts → Results ↓ Runtime Host executes Maka subjects Start with ARCHITECTURE.md. It provides the system map, code boundaries, problem-oriented reading paths, and six bilingual deep dives. Repository layout apps/desktop/ Electron main / preload / React renderer packages/core/ Pure contracts for Sessions, Events, Permissions, and Connections packages/storage/ SQLite operational state, configuration, and payload stores packages/mcp/ Provider-neutral Model Context Protocol client integration packages/runtime/ AgentRun, model adapters, tools, context, and recovery packages/runtime-host/ Single-owner Runtime Host lifecycle, protocol, and client bootstrap packages/eval/ Experiment cells, attempts, results, and executor/subject adapters packages/computer-use/ Computer-use backend selection, host lifecycle, and protocol adapters packages/cli/ TUI and non-interactive CLI packages/ui/ Shared conversation, Markdown, Artifact, and UI primitives docs/ Architecture, product, security, privacy, and test contracts scripts/ Build hygiene, visual checks, smoke tests, and release helpers Local data and recovery Workspace data lives under Electron userData by default: /workspaces/default/ runtime.sqlite connection-catalog.json credential-vault.json settings.json artifacts/ API keys and similar secrets are a local plaintext file (credential-vault.json), readable only by your OS account. The renderer never sees them. Tools that write files or run a shell must pass the sandbox boundary first. runtime.sqlite is the live record. Older JSONL transcripts and Electron safeStorage credential files are not imported; an upgraded workspace can show empty threads, and those credentials must be entered again. Resuming an interrupted turn is off by default. Set MAKA_RUNTIME_SAFE_BOUNDARY_RESUME=1 only if you want Desktop Safe resume, CLI /resume, and startup auto-resume — those calls hit the model and use tokens. Details: SECURITY.md, privacy, resume. Development and verification Before sending a change, read CONTRIBUTING.md. Common repository-level commands: npm run build npm run typecheck npm test npm run check:release Run one workspace in isolation: npm --workspace @maka/runtime test npm --workspace @maka/eval test npm --workspace @maka/desktop test Use refresh:model-metadata to fetch the current catalog from models.dev, update the committed snapshot, and regenerate the derived TypeScript files. A refresh fails closed when any committed model, capability, provider override, or pricing field disappears; after reviewing an intentional upstream removal, acknowledge it with npm run refresh:model-metadata -- --accept-upstream-removals. sync:model-metadata is intentionally offline: it only regenerates those files from the committed snapshot. Keep access-path-specific overrides in model-metadata.ts; do not edit the generated files by hand. npm run refresh:model-metadata npm --workspace @maka/core test Desktop real-window and visual verification: npm --workspace @maka/desktop run e2e npm --workspace @maka/desktop run smoke:real-window Before submitting code, run typecheck, build, and focused tests proportionate to the change, followed by git diff --check. Documentation Documentation index and authority map Backend architecture Product design Contributing guide Security policy License Maka is licensed under the Apache License 2.0. See NOTICE for attribution information. Third-party components remain subject to their respective licenses and notices. Apache Maka, Maka, Apache, the Apache feather, and the Apache Maka project logo are either registered trademarks or trademarks of The Apache Software Foundation.

7.4 billion tokens per month. 34 free LLM providers. 635 free model endpoints. All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted keys. Personal experimentation only.

AI Job Search The job search that runs on your machine. CI An AI-powered job application framework built on Claude Code. Fork it, fill in your profile, and let Claude evaluate job postings, tailor your CV, write cover letters, and prepare you for interviews. Note: This is an independent open-source project and is not affiliated with, endorsed by, sponsored by, or maintained by Anthropic. Anthropic and Claude Code are referenced only to describe the toolchain this workflow uses. This project has no affiliated cryptocurrency, token, or paid sponsorship program. Anything claiming otherwise is unauthorized and should be treated as a scam. The only ways to support the project are the Ko-fi link below and contributing on GitHub. Does it actually work? I'm a geophysicist by training. When my position was cut in late 2025, I built this framework to run my own job search - the same /scrape, /apply, and /interview workflow in this repo, used weekly, on my own career. I was upfront about it with every employer I spoke to, and instead of counting against me, it usually sparked a genuine technical conversation. Sixty-nine tailored applications, twenty first interviews, and one signed contract later, I started as an AI engineer in June 2026. People kept asking whether this actually works. It got me hired. Now it's yours. The longer version, including the full application funnel, is on LinkedIn. Did this save you a Sunday of cover-letter writing? Consider a coffee. Did it land you the job? Maybe two. ☕ What this is A structured workflow that turns Claude Code into a full-stack job application assistant. The core workflow (self-profiling, fit evaluation, and the drafter-reviewer application pipeline) is language- and country-agnostic. The job portal search skills are built for the Danish market (Jobindex, Jobnet, Akademikernes Jobbank, etc.), but the pattern is designed to be swapped for your local job boards. /setup /scrape /apply | | | v v v Fill in Search job Evaluate fit your profile portals Score & recommend | | | v v v Profile Present matches Draft CV + Cover Letter files ready with fit ratings (LaTeX, tailored) | | v v Pick a match Reviewer agent critiques -> /apply -> Revise -> Final output The framework encodes career guidance best practices, including structured evaluation criteria, forward-looking cover letter framing, and optional salary benchmarking. Prerequisites Claude Code (CLI). Using a different agent tool (Codex, Antigravity, Gemini CLI)? Start at AGENTS.md - the portal search skills work there out of the box, and community forks adapt the full workflow. Python 3.10+ Bun (for job search CLI tools) LaTeX distribution with lualatex and xelatex: TeX Live, MacTeX, TinyTeX, or MiKTeX. The CV compiles with lualatex (pdflatex often fails on modern MiKTeX installs with fontawesome5 font-expansion errors); the cover letter compiles with xelatex because cover.cls requires fontspec. If using a minimal TeX install such as TinyTeX or BasicTeX, install the extra packages listed in SETUP.md. Optional: pip install pypdf for /apply's ATS parseability check (BSD; no Poppler required). Poppler pdftotext remains a fallback (macOS: brew install poppler, Debian/Ubuntu: apt install poppler-utils, Windows: choco install poppler). If both are missing, the check degrades to a visual keyword review. Quick start 🎥 Prefer to see it in action first? The Next New Thing did a hands-on walkthrough of how the workflow is actually used, from setup to a finished application (recorded August 2026 - commands may have evolved since). 1. Fork and clone gh repo fork MadsLorentzen/ai-job-search --clone cd ai-job-search !IMPORTANT] A fork of this repo is always public — GitHub does not allow private forks of public repositories — and /setup (step 3 below) writes your personal data (name, contact details, employment history, salary expectations) into tracked files. If this copy is for your own job search rather than for contributing changes back, use a private repository with this repo as upstream instead — the two-minute recipe is in [SETUP.md section 8, and every update workflow works identically. Fork only to contribute. 2. Install job search tools PowerShell: $tools = @("jobbank-search", "jobdanmark-search", "jobindex-search", "jobnet-search", "linkedin-search", "freehire-search") foreach ($tool in $tools) { Push-Location ".agents/skills/$tool/cli" bun install Pop-Location } Bash / zsh / Git Bash: for tool in jobbank-search jobdanmark-search jobindex-search jobnet-search linkedin-search freehire-search; do (cd .agents/skills/$tool/cli && bun install) done For linkedin-search and freehire-search the install is optional: both have zero runtime dependencies and run with plain bun; bun install only pulls TypeScript dev types. 3. Set up your profile claude Then inside Claude Code: /setup /setup offers three paths: read your documents/ folder if you have one populated (CV PDF, LinkedIn export, diplomas, reference letters, past applications), import a single CV pasted in chat, or walk through an interview. It auto-detects what you have and asks. Documents-folder mode is idempotent and safe to re-run as you add more material; see documents/README.md for the layout. 4. Search for jobs /scrape This searches multiple job portals for positions matching your profile, deduplicates results, and presents them sorted by fit. Pick a match to run /apply on it directly — or, when a scrape returns more jobs than you want to eyeball, run /rank to batch-score them all against the fit framework and get a ranked shortlist first. 5. Apply to a job /apply https://jobindex.dk/job/1234567 If the URL can't be fetched (some job portals block automated access), you can paste the job description directly instead: /apply This runs the full workflow: evaluate fit, draft CV + cover letter, review with a second agent, revise, and present the final output. Postings are treated as untrusted input (the workflow follows no instructions embedded in them and fetches no links from their body), but agentic defenses are instruction-level, not a sandbox - on an unfamiliar job board, skim what was fetched and written before you hit send. Details in SECURITY.md. Other commands /setup, /scrape, and /apply form the core workflow. Ten more commands extend it once your profile is in place: /interview preps you for a scheduled interview on a tracked application. It builds a stage-specific prep pack from the application's archive (the exact posting, the CV and cover letter the interviewer actually read, feedback recorded from earlier rounds), researches the company and interviewers with a verify-before-use rule, maps likely questions to your STAR examples, and offers a mock interview following the roleplay protocol in 07-interview-prep.md. Gaps get honest bridge answers, never invented experience. /outcome records what happened to an application - interview stages, offers, rejections, silence. It archives the submitted CV, cover letter, and posting text into documents/applications/_/, keeps outcome.md in the format /setup Path A parses, and updates the tracker. It also owns the stretch before there is an outcome to record: /outcome followup surfaces open applications that have gone quiet (default 10 days), drafts a short channel-appropriate follow-up in your writing style using only claims from the materials you already submitted (drafts only, never sends; at most twice per application), and offers a thank-you note in the same turn an interview stage is recorded. Once a few applications resolve, it points you back to /setup to calibrate the fit framework from what actually got interviews. /notion-sync publishes a one-way, read-only view of the pipeline into a Notion database via the official Notion MCP server (OAuth, no API keys) - one row per ranked job plus every tracked application, with a write-once briefing page per row. The repo files stay the system of record: nothing syncs back, and documents sync as filenames only. Complements /html-report: that is the deep offline dashboard you regenerate at your desk; this is the glanceable live view from anywhere Notion runs (desktop, web, phone). /gmail-sync reads your Gmail (via the Gmail connector) for status signals on your open applications - interview invites, assessment links, offers, rejections - and proposes them as a batch for you to approve before anything is written to the tracker or outcome.md, citing the source email on every proposed change. Offers stop short of proposing hired/offer_declined since that's your call; conflicting or unmatched signals get flagged for a manual /outcome pass instead of guessed. /rank bridges /scrape and /apply: it batch-scores all newly scraped postings against the fit framework (parallel agents fetch each posting and score the five evaluation dimensions) and returns a ranked shortlist with honest per-job strengths and gaps. Deal-breakers veto, deadlines get urgency flags, dead postings get marked expired. Pick a number and it hands off to the full /apply workflow. /expand enriches your profile by scanning public sources you've already linked in it (GitHub repos, portfolio site, Kaggle, Google Scholar) and looking up syllabi for named courses and certifications. Discovered competencies are added to your profile with a source tag. Useful right after /setup to surface skills that documents alone don't make explicit. /upskill analyzes the gap between your profile, your tracked job postings, and your ranked-but-untracked postings (/rank's recorded gaps in seen_jobs.json) — or a single posting via /upskill . Produces a prioritized heatmap of skill gaps and a learning plan with web-searched study resources and time estimates. Useful for career planning between applications. /html-report generates a self-contained HTML dashboard from job_search_tracker.csv and the application archives — stat cards, status/sector/channel/funnel charts (inline SVG, no external dependencies), and a filterable applications table. Opens directly in a browser, fully offline. Re-run it any time after /apply or /outcome adds new entries. /add-template registers your own CV or cover letter template (LaTeX, Typst, or another toolchain) in place of the stock ones. It captures the template's instructions (source extension, compile command, fonts, style rules, page limit), runs a mandatory test compile, and wires the template into /apply. See Custom templates below. /add-portal generates a job-portal search skill for a job board in your market. It investigates the portal (search URL pattern, result structure, access rules), scaffolds the CLI skill from the same structure as the shipped ones, and test-runs a live query before registering. See Job search tools below. /reset is also available, see Starting over below. File structure ai-job-search/ ├── CLAUDE.md # Main candidate profile + workflow rules ├── .claude/ │ ├── commands/ │ │ ├── apply.md # /apply workflow (drafter-reviewer) │ │ ├── setup.md # /setup onboarding (documents folder, CV import, or interview) │ │ ├── expand.md # /expand competency enrichment from documents and online presence │ │ ├── add-template.md # /add-template register custom templates (LaTeX, Typst, ...) │ │ ├── add-portal.md # /add-portal generate a job-portal search skill for your market │ │ ├── rank.md # /rank triage scraped jobs into a ranked shortlist │ │ ├── outcome.md # /outcome record application results, archive materials │ │ ├── gmail-sync.md # /gmail-sync auto-detect application status from Gmail │ │ ├── interview.md # /interview stage-specific prep pack + mock interview │ │ ├── html-report.md # /html-report generate application tracker dashboard │ │ ├── notion-sync.md # /notion-sync one-way pipeline view in a Notion database │ │ └── reset.md # /reset wipe profile data or documents folder │ ├── skills/ │ │ ├── job-application-assistant/ # Core application skill │ │ │ ├── SKILL.md # Skill definition │ │ │ ├── 01-candidate-profile.md # Your education, experience, skills │ │ │ ├── 02-behavioral-profile.md# PI/DISC/personality assessment │ │ │ ├── 03-writing-style.md # Tone, structure, do's and don'ts │ │ │ ├── 04-job-evaluation.md # Scoring framework for job fit │ │ │ ├── 05-cv-templates.md # LaTeX CV structure + tailoring rules │ │ │ ├── 06-cover-letter-templates.md # LaTeX cover letter templates │ │ │ └── 07-interview-prep.md # STAR examples + interview framework │ │ ├── job-scraper/ # Job search orchestration │ │ └── upskill/ # /upskill skill gap analysis and learning plan │ └── settings.json # Claude Code permissions (shared, scoped) ├── .agents/skills/ # Job portal CLI tools │ ├── jobbank-search/ # Akademikernes Jobbank (Denmark) │ ├── jobdanmark-search/ # Jobdanmark.dk (Denmark) │ ├── jobindex-search/ # Jobindex.dk (Denmark) │ ├── jobnet-search/ # Jobnet.dk (Denmark, government portal) │ ├── linkedin-search/ # LinkedIn public job listings (country-agnostic) │ └── freehire-search/ # freehire.me tech job aggregator (multi-market, REST API) ├── cv/ │ └── main_example.tex # moderncv LaTeX template ├── cover_letters/ │ ├── cover.cls # Custom cover letter LaTeX class │ ├── cover_example.tex # Example cover letter (structural reference + CI smoke test) │ └── OpenFonts/ # Lato + Raleway fonts ├── templates/ # Custom templates registered via /add-template │ └── README.md # Folder layout instructions ├── documents/ # Career source materials for /setup Path A and /expand │ ├── README.md # Folder layout instructions │ ├── cv/ # Master CV (PDF or .tex) │ ├── linkedin/ # LinkedIn profile export (PDF) │ ├── diplomas/ # Degree certificates and transcripts │ ├── references/ # Reference letters │ └── applications/ # Past application records (_/) ├── .github/workflows/ci.yml # CI: LaTeX smoke compiles, skill lint, CLI typechecks ├── salary_lookup.py # Salary benchmarking tool (BYO data) ├── tools/ │ ├── check_framework_version.py # CI check: framework_version bumped when skill files change │ ├── check_upstream_updates.py # Preview which personalized files an upstream update touches │ ├── convert_salary_excel.py # Convert salary Excel to JSON │ ├── lint_skills.py # CI lint for skills, commands, settings.json │ ├── robots_check.py # Gate the browser-header retry against robots.txt │ ├── security_guards.py # CI guards: permission allowlist, gitignore rules, manifests │ ├── upstream_triage.py # Sort upstream commits into worth-reviewing vs probably-skip │ ├── verify_pdf.py # Verify a compiled PDF's page count and extractable text │ └── README_SALARY_TOOL.md # Salary tool setup instructions ├── job_scraper/ # Scraper state (seen jobs, results) ├── gmail_sync/ # /gmail-sync state (processed message IDs, last sync date) ├── upskill/ # /upskill report output (markdown reports per run) ├── job_search_tracker.csv # Application tracking spreadsheet └── SETUP.md # Detailed setup guide How /apply works The /apply command runs a drafter-reviewer workflow with mandatory PDF compilation: Parse the job posting (URL or text) Evaluate fit against your profile (skills, experience, culture, location, career alignment) Draft a tailored CV and cover letter in LaTeX Spawn a reviewer agent that researches the company and critiques the drafts Revise based on the reviewer's feedback Compile and inspect both PDFs: lualatex for the CV, xelatex for the cover letter. Claude reads the rendered pages and iterates on the LaTeX until the CV is exactly 2 pages with no orphaned entry titles, and the cover letter is exactly 1 page with the signature visible and fonts consistent. ATS-check the CV: extract the PDF's text layer (pdftotext, optional dependency) and verify it the way an ATS parser sees it — contact details present as literal text, no garbled glyphs, sane reading order — then score the posting's keyword coverage against the extraction. Keywords the profile genuinely supports get added; genuine gaps stay visible, never stuffed. Present the final output with a verification checklist All claims in the CV and cover letter are verified against your actual profile. The system never fabricates skills or experience. What makes this workflow different PDF verification loop. Most LaTeX-resume templates produce "looks fine in the .tex" output that breaks in the PDF: job titles orphan to the next page, cover letters spill onto page 2, bullet fonts silently fall back to the body font. The /apply command compiles and visually inspects every PDF and applies targeted fixes (\needspace, \enlargethispage, font-matching wrappers for list items) until the layout is clean. This runs automatically on every application. ATS verification on the PDF text layer. An ATS reads the PDF's embedded text, not the rendered page — and LaTeX can silently produce PDFs whose text extracts as garbage (icon glyphs where the email should be, interleaved lines from multi-column layouts). /apply extracts the compiled CV's text layer with pdftotext and verifies contact details, reading order, and the posting's keyword coverage against what a parser actually sees. Honesty rule enforced: a keyword the profile doesn't support is acknowledged as a gap, never stuffed in. Relevance-weighted CV cutting. When a CV overflows 2 pages, the workflow does not cut mechanically from the "oldest" section. It scores each candidate line by (a) relevance to the target posting, (b) uniqueness in the document, and (c) whether the cover letter depends on it, and cuts the lowest-total-score line first. An older-role bullet that hits posting keywords survives ahead of a recent-role bullet that does not. Drafter-reviewer separation. The drafter writes; a second Claude agent, spawned with a fresh context, researches the company and critiques the drafts. The drafter then revises. This catches missed keywords, weak framing, and generic language that a single pass often leaves in. Token-efficient reviewer dispatch. The reviewer agent receives drafts inline rather than re-reading them, and the verification checklist runs once at the end of the workflow rather than being duplicated by both agents. Note: the new compile-and-inspect step in Step 5 spends some of those savings on PDF rendering and layout iteration — the workflow trades some end-to-end token cost for a real reduction in broken PDFs reaching the user. Customization Which files to edit manually If you prefer editing files directly instead of using /setup: | File | What to change | |------|---------------| | CLAUDE.md | Your full profile (name, education, experience, skills, goals) | | 01-candidate-profile.md | Structured version of your CV data | | 02-behavioral-profile.md | Your behavioral assessment or self-assessment | | 04-job-evaluation.md | Skill match areas, career goals, motivation filters | | 05-cv-templates.md | Profile statement templates for different role types | | 07-interview-prep.md | Your STAR examples from actual experience | | search-queries.md | Job search queries for your skills and location | Updating your search queries As your priorities evolve, you can reconfigure just the job search without re-running the full profile setup: /setup --section search This re-runs the search configuration interview: which roles to target, which skills to search for, which locations, and which portals. It also suggests role types you may not have considered based on your profile. Custom templates The CV uses moderncv (banking style). The cover letter uses a custom cover.cls with Lato/Raleway fonts. Both are LaTeX — the reference engine this repo ships and maintains. To use your own template instead — LaTeX, Typst, or any other toolchain that compiles to PDF from the command line — run: /add-template Point it at your source file (a .tex file plus any .cls/.sty files or bundled fonts; a .typ file plus any local packages; or an equivalent for another toolchain). The command interviews you for the template's instructions — source extension, compile command, fonts and where they live, style rules to preserve, hard page limit — stores everything under templates/, runs a mandatory test compile, and activates the template so /apply drafts and compiles from it. Templates are stored with PLACEHOLDER] tokens instead of personal data, so they're safe to commit and share. /add-template --list shows registered templates /add-template --use switches between them /add-template --use default reverts to the stock moderncv / cover.cls templates If you prefer doing it by hand, the manual route still works: update the guidance in 05-cv-templates.md and 06-cover-letter-templates.md. Job search tools The four Danish CLI tools in .agents/skills/ (Jobbank, Jobdanmark, Jobindex, Jobnet) demonstrate the pattern for building a job-portal integration for a specific market. If you're in a different country, run: /add-portal Give it your local job board's URL. The command investigates the portal (search-URL pattern, result-page structure, robots.txt/access rules), scaffolds a CLI skill with the same structure, commands, and output contract as the shipped ones, and test-runs a live query before registering anything. Auth-walled portals are declined, and portals with restrictive terms get a prominent personal-use-only warning in the generated skill. The generated skill is market-specific and lives in your fork; the generator itself is the universal part. Maintaining a fork adapted to your market or language? Add it to the [Community forks & adaptations thread so others can find it. For country-agnostic starting points outside Denmark, the repo ships two portal skills alongside the Danish demos: linkedin-search — built on LinkedIn's public, unauthenticated jobs-guest endpoints. Field-agnostic, zero runtime dependencies (runs with just bun), and takes the search location as an explicit flag, so it works for any market out of the box (-l "Berlin, Germany", -l "Mumbai, Maharashtra, India", -l "Remote", …). Intended for personal use only — automated access is against LinkedIn's Terms of Service, so keep volume low. See .agents/skills/linkedin-search/SKILL.md. freehire-search — queries the freehire.me aggregator's public REST API (JSON, no API key). Tech-focused (software, data, engineering, DevOps, remote), multi-market via facet flags (--region, --country, --remote), and zero runtime dependencies. Unlike the HTML-scraping Danish portals, results come back structured (skills, seniority, category). The backend is MIT-licensed and self-hostable — point FREEHIRE_API_URL at your own instance if you prefer. See .agents/skills/freehire-search/SKILL.md. Extending the framework: portals, templates, criteria - and borrowing from other forks Everything above adds up to an extension model, so here it is stated plainly. The framework has three extension points, and none of them require touching upstream: Portal skills - the module system for job boards. Every *-search skill is a self-contained folder under .agents/skills/ with the same contract (a search/detail CLI, --format json|table|plain output, an enabled: flag in its SKILL.md, its own tests). /scrape auto-discovers any installed skill that follows the contract - nothing to register, nothing to wire up. /add-portal generates new ones; the community portal index catalogs the ones other forks have built. Document templates - /add-template registers any CV or cover-letter toolchain that compiles to PDF from the command line, LaTeX or otherwise. Evaluation criteria - deal-breakers and preferences in your profile are free-form, and the evaluation rubric scores against whatever you put there. "Strong parental-leave terms", "minimum salary X per my union's scale", "no on-call" - each is one profile line, no code, and it carries real weight in /rank and /apply fit evaluations. Language is the one deal-breaker type with dedicated, structured handling: /setup captures every language you work in and your level (asked directly, or inferred from your CV/LinkedIn export) into a Languages table, and the Language Gate (04-job-evaluation.md) hard-rejects a posting that requires a language you haven't declared at all, while flagging - not auto-rejecting - one that asks for a higher level than you declared in a language you do work in, so a borderline case (a strict "fluent" bar against your own B1/B2, say) gets your judgment instead of a silent drop. Borrowing a portal skill from another fork is the intended way to get a board that upstream doesn't ship: find it in the portal index, open that fork, and copy the one folder into your own .agents/skills/. Before you run it: Read the code. All of it - these CLIs run pre-approved on your machine (.claude/settings.json allowlists them) against your career data. Check that the only network calls go to the job board it claims to search, that package.json has no dependencies and no lifecycle scripts (postinstall etc.), and that nothing reads or writes outside its own folder. Run its tests offline (bun test in the skill's cli/ directory) - a well-built skill's tests pass with no network access. Check the enabled: flag and the skill's own ToS notes. The copy step is manual on purpose. Your settings already allow installed portal skills to run without asking each time - so an installer that fetched them from third-party repos for you would skip the one check that matters: you, reading the code first. There isn't one, and that's a security decision rather than a missing feature. Market-specific data sources (a national salary database, local award-rate tables) follow the same pattern as portals: they belong in a market fork, shared via #78, not upstream. Salary benchmarking The salary tool works with any salary data you provide (union statistics, Glassdoor exports, personal research, etc.). See tools/README_SALARY_TOOL.md for the expected format and setup. If you don't have salary data, the salary step is simply skipped. Starting over To wipe your profile data and start fresh: /reset profile # clears skill files, preserves framework rules /reset documents # deletes files from documents/ folder /reset all # both /reset shows exactly what will be deleted and requires you to type RESET to confirm. Nothing is deleted until you do. Staying up to date Upstream moves fast. Rather than pulling raw master and hoping, update your fork to a tagged release - a vetted checkpoint described in CHANGELOG.md. python3 tools/check_upstream_updates.py previews exactly which of your personalized files an update touches before you merge, and python3 tools/upstream_triage.py sorts the commits you're behind into "worth reviewing" vs "probably skip" (a weekly workflow can post this to a rolling issue). Full walkthrough in SETUP.md, section 8. Tips for better results Profile depth matters The single biggest factor in output quality is how much detail you put into your profile. A thin profile produces generic applications; a detailed one enables genuinely tailored results. Role descriptions: Don't just list job titles. Describe what you actually did in each position: specific projects, tools used, responsibilities, and measurable achievements. The more material you provide, the more precisely the system can reframe your experience for different roles. Skills in context: Instead of listing "Python" or "project management," describe how and where you applied them. "Built ML pipelines for customer churn prediction in Python using scikit-learn" gives the system far more to work with than "Python, machine learning." All onboarding paths work: Whether you point /setup at your documents/ folder, paste a single CV, or walk through the interview, the principle is the same: richer input produces sharper output. Career path discovery The framework supports two distinct modes of job searching: Explicit targeting: You know which roles or sectors you want. The system helps refine and prioritize based on fit. Latent opportunity discovery: By analyzing your full history (not just job titles, but the actual work you did), the system can surface career paths you haven't considered. Transferable skills that map to unexpected industries, patterns in what you enjoyed or excelled at, or emerging roles that combine your domain expertise with new technology. To get the most from this, invest time during /setup in describing not just your experience, but what energized you, what drained you, and what you'd want more of. This context directly shapes how the system evaluates fit and which roles it surfaces during /scrape. Contributing Thinking about a PR? Read CONTRIBUTING.md first - it explains what gets merged, what lives in forks, and why. Acknowledgements Mikkel Krogholm (skills repo) for the job search CLI skills Built with Claude Code by Anthropic License MIT

Official, Anthropic-managed directory of high quality Claude Code Plugins.

⚡️A native, local-first alternative to Logitech Options+, written in Rust 🦀 — remap buttons, DPI, and SmartShift over HID++. No account, no telemetry.

Learn it. Build it. Ship it for others.