{"id":51223117,"url":"https://github.com/majiayu000/spellbook","last_synced_at":"2026-07-09T07:00:32.039Z","repository":{"id":327946300,"uuid":"1112879061","full_name":"majiayu000/spellbook","owner":"majiayu000","description":"Cross-runtime skills for Claude Code, Codex, and multi-agent workflows.","archived":false,"fork":false,"pushed_at":"2026-07-02T17:45:38.000Z","size":2142,"stargazers_count":230,"open_issues_count":5,"forks_count":21,"subscribers_count":2,"default_branch":"main","last_synced_at":"2026-07-02T19:27:01.571Z","etag":null,"topics":["agent-skills","ai-agent-skills","ai-agents","ai-coding-assistant","automation","claude","claude-code","claude-code-skills","code-review","codex","codex-skills","cross-runtime","developer-tools","multi-agent","productivity","prompt-engineering","skill-library","software-development","spellbook","workflows"],"latest_commit_sha":null,"homepage":"https://github.com/majiayu000/spellbook#quick-start","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/majiayu000.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2025-12-09T08:17:18.000Z","updated_at":"2026-07-02T17:45:43.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/majiayu000/spellbook","commit_stats":null,"previous_names":["majiayu000/claude-arsenal","majiayu000/spellbook"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/majiayu000/spellbook","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/majiayu000%2Fspellbook","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/majiayu000%2Fspellbook/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/majiayu000%2Fspellbook/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/majiayu000%2Fspellbook/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/majiayu000","download_url":"https://codeload.github.com/majiayu000/spellbook/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/majiayu000%2Fspellbook/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35290235,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-09T02:00:07.329Z","response_time":57,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent-skills","ai-agent-skills","ai-agents","ai-coding-assistant","automation","claude","claude-code","claude-code-skills","code-review","codex","codex-skills","cross-runtime","developer-tools","multi-agent","productivity","prompt-engineering","skill-library","software-development","spellbook","workflows"],"created_at":"2026-06-28T09:00:31.117Z","updated_at":"2026-07-09T07:00:32.024Z","avatar_url":"https://github.com/majiayu000.png","language":"Python","funding_links":[],"categories":["Source Catalog"],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n  \u003ch1\u003eSpellbook\u003c/h1\u003e\n  \u003cp\u003e\u003cstrong\u003e101 Cross-Runtime Skills | 7 Claude Code Agents | One Command Install\u003c/strong\u003e\u003c/p\u003e\n\n  \u003cp\u003eA cross-runtime skill library for Claude Code, Codex, and multi-agent workflows.\u003c/p\u003e\n\n  \u003cp\u003e\n    \u003ca href=\"https://github.com/majiayu000/spellbook/stargazers\"\u003e\u003cimg src=\"https://img.shields.io/github/stars/majiayu000/spellbook?style=flat-square\u0026logo=github\" alt=\"Stars\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://github.com/majiayu000/spellbook/blob/main/LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/github/license/majiayu000/spellbook?style=flat-square\" alt=\"License\"\u003e\u003c/a\u003e\n    \u003cimg src=\"https://img.shields.io/badge/skills-101-blue?style=flat-square\" alt=\"Skills\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/agents-7-green?style=flat-square\" alt=\"Agents\"\u003e\n  \u003c/p\u003e\n\n  \u003cp\u003e\n    \u003ca href=\"#quick-start\"\u003eQuick Start\u003c/a\u003e •\n    \u003ca href=\"#runtime-targets\"\u003eRuntime Targets\u003c/a\u003e •\n    \u003ca href=\"#pick-a-workflow\"\u003ePick a Workflow\u003c/a\u003e •\n    \u003ca href=\"#skills\"\u003eSkills\u003c/a\u003e •\n    \u003ca href=\"#agents\"\u003eAgents\u003c/a\u003e •\n    \u003ca href=\"./CHANGELOG.md\"\u003eChangelog\u003c/a\u003e •\n    \u003ca href=\"#release-status\"\u003eRelease Status\u003c/a\u003e •\n    \u003ca href=\"#contributing\"\u003eContributing\u003c/a\u003e •\n    \u003ca href=\"./README_CN.md\"\u003e中文\u003c/a\u003e\n  \u003c/p\u003e\n\u003c/div\u003e\n\n---\n\n\u003e **Rename notice:** Spellbook was formerly **Claude Arsenal**. Claude Code remains a first-class target; the new name reflects the broader roadmap for Claude Code, Codex, and cross-runtime agent skills. See the [migration note](./docs/migration-from-claude-arsenal.md) for details.\n\n---\n\n## Quick Start\n\n### One-Line Install (All Skills)\n\n```bash\ncurl -fsSL https://raw.githubusercontent.com/majiayu000/spellbook/main/install.sh | bash -s -- --target all\n```\n\n### Manual Install (Selective)\n\n```bash\n# Clone the repository\ngit clone https://github.com/majiayu000/spellbook.git\ncd spellbook\n\n# Install specific skills for Claude Code and Codex\n./install.sh --target all --skills typescript-project,python-project,devops-excellence\n\n# Or install everything for one runtime\n./install.sh --target claude --all\n./install.sh --target codex --all\n```\n\n### Verify Installation\n\n- Claude Code: type `/` to see your installed skills.\n- Codex: restart Codex so it reloads `~/.agents/skills`.\n\n---\n\n## Runtime Targets\n\nSpellbook keeps the skill source in one place and installs it into the runtime you use.\n\n| Target | Installed To | Status |\n|--------|--------------|--------|\n| Claude Code | `~/.claude/skills` plus `~/.claude/agents` | Skills and agents supported |\n| Codex | `~/.agents/skills` | Skills supported; agents skipped |\n| All | Both Claude Code and Codex paths | Recommended for multi-tool users |\n\nClaude Code remains a first-class target and search entry. The project was formerly known as Claude Arsenal; the new Spellbook name reflects the broader goal: reusable skills that can travel across coding agents.\nOlder Spellbook versions installed Codex skills under `~/.codex/skills`; reinstall with the current installer to use the documented Codex user-level skill path.\n\n---\n\n## Pick a Workflow\n\nStart with a small bundle that matches the job, then add more skills when the workflow sticks.\n\n| Workflow | Install | Good for |\n|---|---|---|\n| Frontend and UI | `./install.sh --target all --skills frontend-design,app-ui-design,ui-design-system,figma-to-react` | Product UI, landing pages, design systems, Figma handoff |\n| Code quality | `./install.sh --target all --skills codebase-audit,fixflow,optflow,systematic-debugging` | Audits, bug fixes, refactors, root-cause debugging |\n| Ops and deploy | `./install.sh --target all --skills server-deploy,server-security,clash-doctor,system-doctor` | Shipping apps, hardening servers, diagnosing local and network issues |\n| Product and docs | `./install.sh --target all --skills product-discovery,prd-master,technical-spec,product-analytics` | Discovery, PRDs, technical specs, metrics plans |\n| Agent workflows | `./install.sh --target all --skills codex-agent,multi-ai-research,strategic-compact,vibeguard` | Cross-review, multi-AI research, context handoff, anti-hallucination checks |\n\nHigh-signal individual skills to try first: `github-trending`, `harmonyos-app`, `app-ui-design`, `product-discovery`, `xiaohongshu`, `codebase-audit`, and `server-deploy`.\n\nSee [Showcase](./docs/showcase.md) for copy-paste prompts and expected outputs.\nRelease history lives in [Changelog](./CHANGELOG.md).\n\n---\n\n## Why Spellbook\n\n- **Cross-runtime install**: one source tree can install into Claude Code and Codex.\n- **Validated registry**: every installable skill is checked by `python3 scripts/validate_skills.py --check`.\n- **Progressive disclosure**: larger skills use `references/`, `templates/`, `scripts/`, and eval files instead of one giant prompt.\n- **Practical coverage**: engineering, operations, product, UI, content, and agent workflows live in one catalog.\n\n---\n\n## Skills\n\n\u003e The generated full skill inventory lives in [Skill Registry](./docs/skill-registry.md).\n\u003e Skill layout rules live in [Skill Format Policy](./docs/skill-format-policy.md).\n\u003e Skill authoring quality rules live in [Skill Quality Playbook](./docs/skill-quality-playbook.md).\n\n### Search the Registry\n\n```bash\n# Free-text query (AND semantics across name, description, category, tags)\npython3 scripts/validate_skills.py search rust testing\n\n# Filter by tag\npython3 scripts/validate_skills.py search --tag agent\n\n# Restrict to a description language\npython3 scripts/validate_skills.py search --language zh deploy\n\n# Machine-readable output\npython3 scripts/validate_skills.py search --tag react --json\n```\n\nThe tag index lives in [`registry/tags.json`](./registry/tags.json) for tooling and dashboards. Curated overrides for skills the keyword heuristic cannot infer live in [`registry/tag_overrides.yml`](./registry/tag_overrides.yml).\n\nAudit non-blocking skill quality signals:\n\n```bash\npython3 scripts/audit_skill_quality.py\npython3 scripts/audit_skill_quality.py skill-creator\n```\n\n### AI \u0026 Agent Workflow\n\nSkills for orchestrating, guarding, and maintaining AI agent workflows — the core of Spellbook's cross-runtime mission.\n\n| Skill | Description |\n|-------|-------------|\n| [`multi-model-orchestrator`](./skills/multi-model-orchestrator/) | Coordinate multi-agent tasks via a centralized handoff document |\n| [`flowguard`](./skills/flowguard/) | Guard long, ambiguous, or stateful agent tasks from drift |\n| [`skill-lifeguard`](./skills/skill-lifeguard/) | Add reliable-skill contracts, checkpoints, smoke hooks, and drift signals |\n| [`review-gate`](./skills/review-gate/) | Produce review packs and require human approval before landing agent changes |\n| [`skill-audit`](./skills/skill-audit/) | Audit, design, categorize, and measure agent skills |\n| [`threads`](./skills/threads/) | Codex-native subagents and parallel GitHub queue lanes |\n| [`codex-fluent`](./skills/codex-fluent/) | Codex session hygiene, archive strategy, and handoff discipline |\n| [`codex-retrospective`](./skills/codex-retrospective/) | Codex self-review of recent history to improve behavior |\n| [`brainstorming`](./skills/brainstorming/) | Socratic dialogue for design refinement and architecture exploration |\n| [`personal-arsenal-lifecycle-doctor`](./skills/personal-arsenal-lifecycle-doctor/) | Diagnose the health of personal `~/.claude/skills` |\n\nSee [`docs/agent-reliability-trio.md`](./docs/agent-reliability-trio.md) for the Reliable Skill + Context Engineering + Review Gate workflow.\n\n### Development Architecture\n\nBuild production-ready projects with language-specific best practices.\n\n| Skill | Language | Key Features |\n|-------|----------|--------------|\n| [`typescript-project`](./skills/typescript-project/) | TypeScript | ESM, Zod, Biome, Clean Architecture |\n| [`python-project`](./skills/python-project/) | Python | uv, Pydantic, Ruff, FastAPI |\n| [`rust-project`](./skills/rust-project/) | Rust | Cargo workspace, error handling, async |\n| [`golang-web`](./skills/golang-web/) | Go | Chi/Echo, sqlc, structured logging |\n| [`zig-project`](./skills/zig-project/) | Zig | Build system, memory management |\n| [`architecture-foundation`](./skills/architecture-foundation/) | Cross-language | Runtime, state ownership, adapters, and convergence specs |\n| [`elegant-architecture`](./skills/elegant-architecture/) | Cross-language | Clean architecture with strict 200-line file limits |\n\n### Product Lifecycle\n\nEnd-to-end product development from discovery to deployment.\n\n| Skill | Phase | What You Get |\n|-------|-------|--------------|\n| [`product-discovery`](./skills/product-discovery/) | Discovery | JTBD, user interviews, market research |\n| [`prd-master`](./skills/prd-master/) | Definition | PRD writing, user stories, RICE prioritization |\n| [`technical-spec`](./skills/technical-spec/) | Design | Design docs, ADR, C4 diagrams |\n| [`product-analytics`](./skills/product-analytics/) | Growth | Event tracking, A/B testing, AARRR |\n| [`devops-excellence`](./skills/devops-excellence/) | Deployment | CI/CD, Docker, Kubernetes, GitOps |\n| [`observability-sre`](./skills/observability-sre/) | Operations | Monitoring, logging, tracing, SLO/SLI |\n| [`product-manager-toolkit`](./skills/product-manager-toolkit/) | Definition | RICE, customer interviews, PRD templates, discovery frameworks |\n\n### API \u0026 Backend\n\n| Skill | Description |\n|-------|-------------|\n| [`api-design`](./skills/api-design/) | REST/GraphQL/gRPC patterns, OpenAPI 3.2 |\n| [`auth-security`](./skills/auth-security/) | OAuth 2.1, JWT, security best practices |\n| [`database-patterns`](./skills/database-patterns/) | PostgreSQL, Redis, migrations, optimization |\n| [`codebase-audit`](./skills/codebase-audit/) | Deep adaptive repository audit with severity-ranked findings and repair roadmap |\n| [`structured-logging`](./skills/structured-logging/) | Log architecture, standards, observability, and tracing |\n| [`structured-logging-lite`](./skills/structured-logging-lite/) | Centralized logging, field standards, and distributed tracing |\n\n### Development Practices\n\n| Skill | Description | Origin |\n|-------|-------------|--------|\n| [`contributor`](./skills/contributor/) | End-to-end open source contribution workflow from issue discovery to PR submission | Custom |\n| [`repo-agent-context-audit`](./skills/repo-agent-context-audit/) | Audit and scaffold repo agent context across AGENTS, skills, and specs | Custom |\n| [`strategic-compact`](./skills/strategic-compact/) | Compress context at logical boundaries while preserving decisions and constraints | Custom |\n| [`skill-creator`](./skills/skill-creator/) | Create, improve, and benchmark reusable skills | Custom |\n| [`humanizer`](./skills/humanizer/) | Remove obvious AI writing patterns from user-facing text | External guide + custom adaptation |\n\n### Delivery Workflow\n\nDisciplined end-to-end delivery: testing, commits, health checks, and contribution flow.\n\n| Skill | Description |\n|-------|-------------|\n| [`app-user-story-qa`](./skills/app-user-story-qa/) | End-to-end app feature inventory, canonical tracker, user-story testing, fixes, and retest loop |\n| [`test-driven-development`](./skills/test-driven-development/) | Enforce RED-GREEN-REFACTOR TDD discipline |\n| [`comprehensive-testing`](./skills/comprehensive-testing/) | Test pyramid, unit/integration/E2E/property testing, framework best practices |\n| [`git-commit-smart`](./skills/git-commit-smart/) | Generate meaningful conventional commit messages from diff |\n| [`push-all`](./skills/push-all/) | Stage, commit, and push all changes after safety checks |\n| [`project-health-auditor`](./skills/project-health-auditor/) | Codebase health, tech debt, dependency, and project risk analysis |\n| [`contribution-architect`](./skills/contribution-architect/) | Move from bug fixes to architectural improvements and debt discovery |\n\n### Cross-Tool Interop\n\nSkills for using multiple coding agents and CLI tools together.\n\n| Skill | Description |\n|-------|-------------|\n| [`codex`](./skills/codex/) | Invoke Codex CLI sessions from another agent workflow |\n| [`codex-agent`](./skills/codex-agent/) | Optional second-opinion review, cross-verification, and alternatives through Codex CLI |\n| [`ask-opencli`](./skills/ask-opencli/) | Ask Grok or Gemini through opencli and an existing browser session |\n| [`multi-ai-research`](./skills/multi-ai-research/) | Parallel research across multiple AI tools and internal agents |\n\n### UI/UX \u0026 Design\n\n| Skill | Description |\n|-------|-------------|\n| [`app-ui-design`](./skills/app-ui-design/) | iOS/Android UI design, Material Design 3, HIG |\n| [`product-ux-expert`](./skills/product-ux-expert/) | UX evaluation, heuristics, accessibility |\n| [`frontend-design`](./skills/frontend-design/) | Web frontend design patterns |\n| [`ui-designer`](./skills/ui-designer/) | Extract design systems from UI screenshots and references |\n| [`ui-design-system`](./skills/ui-design-system/) | Design system toolkit and design-dev handoff support |\n| [`web-artifacts-builder`](./skills/web-artifacts-builder/) | Claude.ai HTML artifacts |\n| [`react-best-practices`](./skills/react-best-practices/) | React and Next.js performance patterns distilled from Vercel guidance |\n| [`react-hooks-best-practices`](./skills/react-hooks-best-practices/) | React hooks, effects, refs, and component design patterns |\n| [`slides`](./skills/slides/) | Speech-friendly slide deck and background slide generation |\n| [`ui-ux-pro-max`](./skills/ui-ux-pro-max/) | Compact UI/UX tables for product patterns, landing pages, charts, and 9 stacks |\n| [`figma-to-code`](./skills/figma-to-code/) | Figma designs to production React/Next.js with TypeScript and Tailwind |\n| [`css-debug`](./skills/css-debug/) | Diagnose CSS/layout issues, Tailwind conflicts, z-index stacking |\n| [`playwright-automation`](./skills/playwright-automation/) | Browser automation and testing with Playwright |\n\n### Tooling \u0026 Automation\n\n| Skill | Description |\n|-------|-------------|\n| [`web-asset-generator`](./skills/web-asset-generator/) | Favicons, app icons, OG images |\n| [`github-trending`](./skills/github-trending/) | GitHub trending analysis |\n| [`auto-optimize`](./skills/auto-optimize/) | Autonomous codebase optimization with dimension rotation |\n| [`fixflow`](./skills/fixflow/) | Strict plan-implement-test-commit workflow for delivery tasks |\n| [`optflow`](./skills/optflow/) | Optimization discovery and execution workflow with continuous validation |\n| [`plan-flow`](./skills/plan-flow/) | Repository-level redundancy analysis with step-test-update planning |\n| [`vibeguard`](./skills/vibeguard/) | Task contracts, finding scoring, and lightweight anti-hallucination reviews |\n| [`clash-doctor`](./skills/clash-doctor/) | Clash proxy \u0026 network diagnostics |\n| [`clash-routes`](./skills/clash-routes/) | Inspect active proxy routes for specific processes via Mihomo API |\n| [`optimize-network`](./skills/optimize-network/) | Safe local network speed, latency, DNS, Wi-Fi, and bufferbloat diagnostics with VPN/proxy guardrails |\n| [`disk-cleaner`](./skills/disk-cleaner/) | Scan and reclaim disk space with interactive cleanup guidance |\n| [`system-doctor`](./skills/system-doctor/) | Diagnose CPU, memory, and process-level system slowdowns |\n| [`codex-log-guard`](./skills/codex-log-guard/) | Diagnose and mitigate excessive Codex local SQLite diagnostic log writes |\n| [`server-deploy`](./skills/server-deploy/) | Deploy Node, Python, Rust, Go, or static projects to remote servers |\n| [`server-security`](./skills/server-security/) | Audit and harden Linux server SSH, firewall, and exposed services |\n| [`cliproxy-deploy`](./skills/cliproxy-deploy/) | Deploy router-for-me/CLIProxyAPI on a Linux VPS, exposing Codex/Claude/Gemini OAuth subscription accounts as an OpenAI-compatible API |\n| [`cliproxy-newapi-stack`](./skills/cliproxy-newapi-stack/) | Layer NewAPI metering on top of CLIProxyAPI: Docker deploy, ratio-based pricing, quota top-up, dual-path verification, and OAuth account hot-swap |\n\n### Operations \u0026 Deploy\n\nDeploy models and diagnose local and remote environments.\n\n| Skill | Description |\n|-------|-------------|\n| [`gemma4-local-deploy`](./skills/gemma4-local-deploy/) | Deploy Gemma 4 12B locally on Mac/Apple Silicon via llama.cpp or Ollama |\n| [`gpu-use`](./skills/gpu-use/) | Inspect remote server GPU usage (per-card VRAM, processes, containers) |\n| [`openclaw-deploy`](./skills/openclaw-deploy/) | One-click OpenClaw deployment on a remote server |\n| [`rustdesk-doctor`](./skills/rustdesk-doctor/) | Diagnose RustDesk connection issues |\n| [`vscode-doctor`](./skills/vscode-doctor/) | Diagnose slow or freezing VS Code-compatible editors |\n\n### Content \u0026 Social Media\n\n| Skill | Description |\n|-------|-------------|\n| [`xiaohongshu`](./skills/xiaohongshu/) | Xiaohongshu content creation \u0026 publishing |\n| [`trip-planner`](./skills/trip-planner/) | Travel itinerary planning |\n| [`weekly`](./skills/weekly/) | Weekly report from Git, Claude Code, and Codex sessions |\n| [`xiaohongshu-netfeel-guardian`](./skills/xiaohongshu-netfeel-guardian/) | Remove translation-tone from Claude's Chinese content for native readability |\n\n### Mobile \u0026 Cross-Platform\n\n| Skill | Description |\n|-------|-------------|\n| [`harmonyos-app`](./skills/harmonyos-app/) | HarmonyOS with ArkTS, ArkUI, Stage Model |\n\n### Rust Specific\n\n| Skill | Description |\n|-------|-------------|\n| [`rust-best-practices`](./skills/rust-best-practices/) | Microsoft Rust guidelines, error handling |\n\n---\n\n## Agents\n\nSpecialized agents for complex tasks.\n\n| Agent | Expertise | Use Case |\n|-------|-----------|----------|\n| [`tech-lead-orchestrator`](./agents/tech-lead-orchestrator.md) | Coordination | Multi-step tasks, delegation |\n| [`code-archaeologist`](./agents/code-archaeologist.md) | Exploration | Legacy codebase documentation |\n| [`backend-typescript-architect`](./agents/backend-typescript-architect.md) | Architecture | Bun/Node.js, API design |\n| [`senior-code-reviewer`](./agents/senior-code-reviewer.md) | Review | Security, performance, architecture |\n| [`kubernetes-specialist`](./agents/kubernetes-specialist.md) | Infrastructure | K8s, Helm, GitOps |\n| [`security-auditor`](./agents/security-auditor.md) | Security | OWASP Top 10, SAST |\n| [`opensource-contributor`](./agents/opensource-contributor.md) | Contribution | Open source workflow |\n\n---\n\n## Skill Design Philosophy\n\nEvery skill in Spellbook follows these principles:\n\n1. **Hard Rules** - Mandatory constraints with `FORBIDDEN` / `REQUIRED` markers\n2. **Practical Examples** - Real code, not just theory\n3. **Verification Checklists** - Actionable validation steps\n4. **Battle-Tested** - Used in production environments\n\n---\n\n## Documentation\n\n| Document | Description |\n|----------|-------------|\n| [Changelog](./CHANGELOG.md) | Release history and current release status |\n| [Installation Guide](./docs/installation.md) | Detailed setup instructions |\n| [Runtime Targets](./docs/runtime-targets.md) | Claude Code and Codex installation targets |\n| [Showcase](./docs/showcase.md) | Copy-paste workflow demos |\n| [Spellbook Operating Contract](./docs/spellbook-operating-contract.md) | Agent behavior rules for autonomy, escalation, pushback, feedback loops, and done-when checks |\n| [Skill Format Policy](./docs/skill-format-policy.md) | Directory vs file skill layout rules |\n| [Skill Quality Playbook](./docs/skill-quality-playbook.md) | Trigger descriptions, gotchas, progressive disclosure, and verification |\n| [Skill Testing Guide](./docs/skill-testing-guide.md) | How to validate skills work |\n| [Creating Plugins](./docs/creating-plugins.md) | Build your own skills |\n| [Product Lifecycle (EN)](./docs/product-lifecycle-skills-en.md) | Full lifecycle coverage |\n| [Product Lifecycle (中文)](./docs/product-lifecycle-skills-zh.md) | 产品生命周期覆盖 |\n\n---\n\n## Release Status\n\nSpellbook is in pre-1.0 release-readiness mode. No numbered GitHub release tag\nhas been cut yet; the current install path uses the repository `main` branch.\nSee [Changelog](./CHANGELOG.md) for release history.\n\nCurrent limitations:\n\n- Codex installs skills only; Claude Code agents are skipped for Codex targets.\n- Some skills depend on external CLIs, accounts, credentials, or platform access\n  that are not bundled by the installer.\n- The registry validator checks installable skill structure, not every external\n  workflow end to end.\n\nSupport paths:\n\n- Bugs: [open an issue](https://github.com/majiayu000/spellbook/issues/new/choose)\n- Feature ideas: [open a feature request](https://github.com/majiayu000/spellbook/issues/new/choose)\n- Security vulnerabilities: follow [Security Policy](./SECURITY.md)\n\n---\n\n## Credits\n\nBuilt on the shoulders of giants:\n\n- [anthropics/skills](https://github.com/anthropics/skills) - Official Anthropic skills\n- [obra/superpowers](https://github.com/obra/superpowers) - Development methodology\n- [claude-code-plugins-plus](https://github.com/jeremylongshore/claude-code-plugins-plus) - Plugin hub\n- [VoltAgent/awesome-claude-code-subagents](https://github.com/VoltAgent/awesome-claude-code-subagents) - Agent collection\n\n---\n\n## Contributing\n\nContributions welcome! Please read our [Contributing Guide](./CONTRIBUTING.md) first.\n\n- Found a bug? [Open an issue](https://github.com/majiayu000/spellbook/issues)\n- Have a skill idea? [Open a feature request](https://github.com/majiayu000/spellbook/issues/new/choose)\n- Want to contribute? [Submit a PR](https://github.com/majiayu000/spellbook/pulls)\n\n---\n\n## The Agent Infra Stack\n\nThis project is one layer of an open-source stack for running coding agents (Claude Code, Codex) as serious infrastructure. Every piece works standalone; together they close the loop:\n\n`spellbook` sits in the **Extend** layer — the authoring side of the skill story: write once, run on Claude Code and Codex. Discovery and distribution live in `claude-skill-registry`.\n\n| Layer | Project | What it does |\n|---|---|---|\n| Extend | [claude-skill-registry](https://github.com/majiayu000/claude-skill-registry) | Discover and search community Claude Code skills |\n| Extend | [spellbook](https://github.com/majiayu000/spellbook) **◀ you are here** | Cross-runtime skills for Claude Code, Codex, and multi-agent workflows |\n| Trust | [argus](https://github.com/majiayu000/argus) | Static install-time scanner for supply-chain attacks (npm / PyPI / crates.io) |\n| Trust | [vibeguard](https://github.com/majiayu000/vibeguard) | Rules, hooks, and guards against hallucinated or unverified agent changes |\n| Remember | [remem](https://github.com/majiayu000/remem) | Local-first persistent memory for Claude Code and Codex sessions |\n| Orchestrate | [harness](https://github.com/majiayu000/harness) | Rust agent orchestration platform — rules, skills, GC, observability |\n| Route | [litellm-rs](https://github.com/majiayu000/litellm-rs) | High-performance Rust AI gateway — 100+ LLM APIs via OpenAI format |\n| Keep | [keepline](https://github.com/majiayu000/keepline) | Session command center — monitor, recover, never lose agent work |\n\n---\n\n## License\n\n[MIT License](./LICENSE) - Use freely in your projects.\n\n---\n\n\u003cdiv align=\"center\"\u003e\n  \u003cp\u003eIf this helps you, consider giving it a ⭐\u003c/p\u003e\n  \u003cp\u003eMade for builders using Claude Code, Codex, and multi-agent workflows\u003c/p\u003e\n\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmajiayu000%2Fspellbook","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmajiayu000%2Fspellbook","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmajiayu000%2Fspellbook/lists"}