{
  "markdown": "<div align=\"center\">\n  <a href=\"https://grimoire.jeffreytse.net\">\n    <img alt=\"grimoire\" src=\"https://raw.githubusercontent.com/jeffreytse/grimoire/main/assets/banner.svg\" width=\"700\">\n  </a>\n  <p>The official best-practices package for <a href=\"https://github.com/jeffreytse/grimoire\">grimoire</a> — curated, peer-reviewed expert practices across 27 domains. Declare the practices your project follows. Enforce them in CI with <code>grimoire check</code>.</p>\n  <br><h1>📖 grimoire-core 📖</h1>\n</div>\n\n<h4 align=\"center\">\n  The official package. Declare the practices you need, install them in one command,<br>\n  enforce compliance with <code>grimoire check</code> — across every AI agent, every project.\n</h4>\n\n<p align=\"center\">\n  <a href=\"https://github.com/jeffreytse/grimoire-core/actions/workflows/validate.yml\">\n    <img src=\"https://github.com/jeffreytse/grimoire-core/actions/workflows/validate.yml/badge.svg\"\n      alt=\"Skill Validation\" />\n  </a>\n\n  <a href=\"https://github.com/jeffreytse/grimoire-core/releases\">\n    <img src=\"https://img.shields.io/github/v/release/jeffreytse/grimoire-core?color=brightgreen\"\n      alt=\"Release Version\" />\n  </a>\n\n  <a href=\"https://github.com/jeffreytse/grimoire-core/graphs/contributors\">\n    <img src=\"https://img.shields.io/github/contributors/jeffreytse/grimoire-core?color=brightgreen\"\n      alt=\"Contributors\" />\n  </a>\n\n  <a href=\"./LICENSE\">\n    <img src=\"https://img.shields.io/badge/License-MIT-greygreen.svg\"\n      alt=\"License: MIT\" />\n  </a>\n\n  <a href=\"https://github.com/sponsors/jeffreytse\">\n    <img src=\"https://img.shields.io/static/v1?label=sponsor&message=%E2%9D%A4&logo=GitHub&link=&color=greygreen\"\n      alt=\"Donate (GitHub Sponsor)\" />\n  </a>\n\n  <a href=\"#-agent-support\">\n    <img src=\"https://img.shields.io/badge/works%20with-Claude%20%C2%B7%20Codex%20%C2%B7%20Cursor%20%C2%B7%20Gemini%20%C2%B7%20OpenCode-blue\"\n      alt=\"Works with\" />\n  </a>\n\n  <a href=\"./SKILLS.md\">\n    <img src=\"https://img.shields.io/badge/skills-1000%2B-blue\"\n      alt=\"1000+ Skills\" />\n  </a>\n</p>\n\n<div align=\"center\">\n  <h4>\n    <a href=\"#-why-grimoire-core\">Why</a> |\n    <a href=\"#%EF%B8%8F-install\">Install</a> |\n    <a href=\"#-quick-start\">Quick Start</a> |\n    <a href=\"#-agent-support\">Agents</a> |\n    <a href=\"#%EF%B8%8F-domains\">Domains</a> |\n    <a href=\"#-the-grimoire-skill-standard\">Standard</a> |\n    <a href=\"#-contributing\">Contributing</a> |\n    <a href=\"https://github.com/jeffreytse/grimoire-core/releases\">Changelog</a> |\n    <a href=\"#-license\">License</a>\n  </h4>\n</div>\n\n<div align=\"center\">\n  <sub>Built with ❤︎ by\n  <a href=\"https://jeffreytse.net\">jeffreytse</a> and\n  <a href=\"https://github.com/jeffreytse/grimoire-core/graphs/contributors\">contributors</a>\n  </sub>\n</div>\n<br>\n\n## 🤔 Why grimoire-core?\n\n> Your AI knows everything — Grimoire makes it practice it.\n\nBooks gave everyone knowledge. Google gave everyone access. AI gave everyone comprehension. None of them gave everyone *practice*. Grimoire does.\n\nThe model knows SOLID, DDD, Google SRE, and the ABA Model Rules. Without explicit guidance, it enforces none of them. This library is the enforcement layer — **skills**: named, citable, executable units of expert practice. One concept. One source. One set of steps.\n\n- 🔍 **You don't know what you don't know.** Grimoire surfaces the governing standard you didn't know applied.\n- 🤖 **Knowing is not enough. Grimoire enforces.** Specific steps, verifiable criteria, repeatable results. Not summaries — verdicts.\n- 🌍 **The world's best practices belong to everyone.** McKinsey charges $1M. Senior lawyers bill $800/hr. The practices they follow are not proprietary. Grimoire makes them free — as executable steps, cited and verified.\n- 🧱 **Every profession. Every AI.** 1000+ skills across 27 domains. Works with Claude, Copilot, Codex, Cursor, Gemini, OpenCode, OpenClaw, and Antigravity.\n- 🔬 **Not just distribution — enforcement.** Skills registries distribute files. grimoire-core provides the practice rules `grimoire check` validates your project against. 1000+ skills are both instructions for your AI *and* compliance criteria for your codebase.\n\n| Repo | Role | Unique value |\n|------|------|-------------|\n| [jeffreytse/grimoire](https://github.com/jeffreytse/grimoire) | CLI — package manager + BPDD linter | `grimoire check` enforces declared practices |\n| **jeffreytse/grimoire-core** (this repo) | Official package — 27 domains, STANDARD.md quality gate | Semantic compliance rules, not just skills |\n| Any git repo | Community / private package | grimoire installs and manages it — standard encouraged, not required |\n\nIf you've spent 10,000 hours mastering something, your practice belongs here.\n\n## 🛠️ Install\n\n**macOS / Linux:**\n\n```bash\n# 1. Install the grimoire CLI\ncurl -fsSL https://raw.githubusercontent.com/jeffreytse/grimoire/main/scripts/install.sh | bash\n\n# 2. Add + install grimoire-core in one step\ngrimoire init                              # creates grimoire.toml, auto-detects AI agents\ngrimoire install jeffreytse/grimoire-core  # adds to grimoire.toml + links to all AI agents\n```\n\n**Go:**\n\n```bash\ngo install github.com/jeffreytse/grimoire@latest\ngrimoire init && grimoire install jeffreytse/grimoire-core\n```\n\n**`grimoire.toml` — declare grimoire-core as a dependency:**\n\n```toml\n# grimoire.toml — commit this to your repo\n[package]\nname = \"my-project\"\n\n[dependencies]\n\"jeffreytse/grimoire-core\" = \"*\"        # always latest\n# \"jeffreytse/grimoire-core\" = \"~1.0\"  # pin to 1.x\n# \"jeffreytse/grimoire-core\" = \"1.2.3\" # exact pin\n```\n\n**Native plugin install (Claude Code):**\n\n```bash\n/plugin marketplace add jeffreytse/grimoire-core\n/plugin install grimoire@grimoire-core           # all domains\n/plugin install grimoire-engineering@grimoire-core  # one domain\n```\n\n## 🤖 Agent Support\n\n| Agent | Plugin install | Script install |\n|-------|----------------|----------------|\n| Claude Code | `/plugin marketplace add jeffreytse/grimoire-core` then `/plugin install grimoire@grimoire-core` | `grimoire install --target claude` |\n| GitHub Copilot CLI | `copilot plugin marketplace add jeffreytse/grimoire-core` then `copilot plugin install grimoire@grimoire-core` | `grimoire install --target all` |\n| Gemini CLI | `gemini extensions install https://github.com/jeffreytse/grimoire-core` | `grimoire install --target gemini` |\n| OpenCode | See [`.opencode/INSTALL.md`](./.opencode/INSTALL.md) | `grimoire install --target opencode` |\n| Codex CLI | `AGENTS.md` auto-loaded | `grimoire install --target codex` |\n| Cursor | `AGENTS.md` context injection | `grimoire install --target cursor` |\n| OpenClaw | See [`.openclaw/INSTALL.md`](./.openclaw/INSTALL.md) | `grimoire install --target openclaw` |\n| Antigravity CLI (agy) | See [`.agy/INSTALL.md`](./.agy/INSTALL.md) | `grimoire install --target antigravity` |\n\n## 🚀 Quick Start\n\n**Describe any problem in plain language — grimoire routes to the right skill:**\n\n```\nUser: I need to raise a Series A but don't know how to pitch investors.\n\nClaude: Situation matches: write-value-proposition + design-go-to-market + apply-pyramid-principle\n        → Start with your value prop. /write-value-proposition\n```\n\n**Or invoke a skill directly:**\n\n```\n/suggest-best-practice     # describe any problem — auto-routes to the right skill\n/review-pull-request       # engineering code review\n/calculate-fire-number     # how much do I need to retire?\n/review-saas-contract      # flag the 3 highest-risk clauses\n/design-sleep-protocol     # evidence-based sleep improvement\n/negotiate-salary          # structure your compensation negotiation\n```\n\n**Common paths:**\n\n| You want to… | Use |\n|---|---|\n| Know exactly which skill you need | `/skill-name` directly |\n| Have a problem, unsure which skill | `/suggest-best-practice` |\n| Already have a plan, want gaps checked | `/review-best-practice-fit` |\n| Need 2+ practices coordinated in sequence | `/plan-best-practice-solution` |\n| Complex problem — sub-problems emerge during execution | `/apply-best-practice-tree` |\n| Don't know what practices exist for a topic | `/discover-best-practices` |\n| About to start a task — want to catch gaps first | `/start-best-practice` |\n\n## 📦 Using as a Package\n\ngrimoire-core is the official package of the [grimoire](https://github.com/jeffreytse/grimoire) skills manager — one package among many, just the curated one. Declare it in `grimoire.toml`:\n\n```toml\n[dependencies]\n\"jeffreytse/grimoire-core\"                 = \"*\"  # all 1000+ skills\n\"jeffreytse/grimoire-core:engineering\"     = \"*\"  # engineering domain only\n\"jeffreytse/grimoire-core:health\"          = \"*\"  # health domain only\n\"myorg/internal-skills\"                    = \"*\"  # your private package\n```\n\nVersioning follows semver. Pin with `\"~1.0\"` (patch updates) or `\"1.2.3\"` (exact). Use `\"*\"` to track the latest verified release.\n\nThe `:path` suffix filters which skills are linked. No `:` = all skills from that package. Paths are Standard Glob patterns (doublestar) matched against the skill's domain path. `**` matches any directory depth; `*` matches within a single segment; `?`, `{a,b}`, and `[...]` are also supported. Examples: `engineering/**` (all engineering subdomains), `health/sleep/**` (one subdomain), `**/development` (development subdomain in any domain).\n\nInstalling grimoire-core gives you both: 1000+ skills your AI can invoke, and the practice rules `grimoire check` validates your project against. One package, two modes.\n\n## 🗺️ Domains\n\n| Domain | Sub-domains |\n|--------|-------------|\n| [meta](./skills/meta/) | suggest-best-practice, plan-best-practice-solution, discover-best-practices, learn-best-practice, learn-grimoire, teach-best-practice, explain-best-practice, write-best-practice-skill, review-best-practice-skill, … |\n| [engineering](./skills/engineering/) | development, frontend, architecture, testing, reliability, devops, cloud, networking, security, data, ai, hardware, mobile, performance, project-management, product, documentation |\n| [business](./skills/business/) | strategy, operations, leadership, entrepreneurship, hr |\n| [science](./skills/science/) | biology, physics, chemistry, mathematics, earth-science, astronomy |\n| [health](./skills/health/) | fitness, nutrition, mental-health, sleep, medicine |\n| [writing](./skills/writing/) | creative, technical, copywriting, academic, journalism |\n| [design](./skills/design/) | ui-ux, graphic, branding, motion, product |\n| [marketing](./skills/marketing/) | seo, content, social-media, paid-ads, growth, analytics |\n| [finance](./skills/finance/) | personal-finance, investing, accounting, real-estate, corporate |\n| [law](./skills/law/) | contracts, ip, employment, privacy, corporate |\n| [education](./skills/education/) | curriculum, teaching, e-learning, assessment, learning-science |\n| [film](./skills/film/) | cinematography, directing, editing, screenwriting, production |\n| [photography](./skills/photography/) | composition, lighting, editing, genres |\n| [music](./skills/music/) | composition, production, mixing, theory, performance |\n| [cooking](./skills/cooking/) | techniques, baking, flavor, nutrition, world-cuisine |\n| [language](./skills/language/) | learning, linguistics, translation, communication |\n| [art](./skills/art/) | drawing, painting, digital-art, illustration, color-theory |\n| [sports](./skills/sports/) | training, coaching, nutrition, tactics, recovery |\n| [productivity](./skills/productivity/) | time-management, habits, focus, goals, tools |\n| [travel](./skills/travel/) | planning, budgeting, cultural, adventure |\n| [psychology](./skills/psychology/) | cognitive, behavioral, social, clinical, positive |\n| [home](./skills/home/) | renovation, interior-design, gardening, organization, smart-home |\n| [environment](./skills/environment/) | sustainability, ecology, climate, energy, policy |\n| [pets](./skills/pets/) | dogs, cats, training, nutrition, health |\n| [fashion](./skills/fashion/) | styling, wardrobe, design, sustainability, accessories |\n| [parenting](./skills/parenting/) | infant, toddler, school-age, teen |\n| [automotive](./skills/automotive/) | maintenance, troubleshooting, buying, modifications, ev |\n\n→ [Browse all skills](./SKILLS.md)\n\n## 🌟 Featured Skills\n\n| Skill | Domain | Source methodology | Verified |\n|-------|--------|--------------------|----------|\n| [`review-saas-contract`](./skills/law/contracts/skills/review-saas-contract/) | law/contracts | ABA model SaaS agreements | ✓ |\n| [`calculate-fire-number`](./skills/finance/personal-finance/skills/calculate-fire-number/) | finance/personal-finance | Bengen (1994) / Trinity Study | ✓ |\n| [`negotiate-salary`](./skills/finance/personal-finance/skills/negotiate-salary/) | finance/personal-finance | Fisher & Ury \"Getting to Yes\" | ✓ |\n| [`design-sleep-protocol`](./skills/health/sleep/skills/design-sleep-protocol/) | health/sleep | Walker \"Why We Sleep\" / AASM | ✓ |\n| [`apply-mise-en-place`](./skills/cooking/techniques/skills/apply-mise-en-place/) | cooking/techniques | Culinary Institute of America | ✓ |\n| [`apply-five-whys`](./skills/engineering/reliability/skills/apply-five-whys/) | engineering/reliability | Toyota Production System | ✓ |\n| [`review-pull-request`](./skills/engineering/development/skills/review-pull-request/) | engineering/development | Google Engineering Practices | ✓ |\n| [`design-training-program`](./skills/sports/training/skills/design-training-program/) | sports/training | NSCA / Bompa \"Periodization\" | ✓ |\n\n**Law** — audit a SaaS contract before signing:\n\n```\nUser: /review-saas-contract\n\nClaude: Red flags found.\n\n  🔴 CRITICAL  Liability cap is $500 — your contract value is $240,000\n  🔴 CRITICAL  No data processing agreement — GDPR Art.28 requires one\n               before processing any EU customer data\n  🟡 WARNING   Auto-renewal clause: 90-day cancellation window in §14.3\n  🟡 WARNING   IP ownership of custom integrations is unassigned\n  ✓  PASS      SLA 99.9% with defined service credits\n\n  Do not sign. Renegotiate: liability cap, DPA, IP clause.\n  Source: ABA model SaaS agreements\n```\n\n**Finance** — calculate how much you need to retire:\n\n```\nUser: /calculate-fire-number\n\nClaude: Applying Trinity Study model (Bengen 1994, 95% 30-year success rate)\n\n  Annual expenses:       $60,000\n  Safe withdrawal rate:  4.0%\n  ─────────────────────────────\n  FIRE number:           $1,500,000\n\n  At $4,000/month invested + 7% real return → retire in 20.4 years\n  Cut annual spend by $12,000               → retire in 16.8 years\n\n  Next: /design-portfolio-allocation\n```\n\n**Sports** — design a training program:\n\n```\nUser: /design-training-program\n\nClaude: Hypertrophy block — intermediate, 4 days/week\n\n  UPPER (Mon/Thu)   Bench 4×8 · Row 4×8 · OHP 3×10 · Face pull 3×15\n  LOWER (Tue/Fri)   Squat 4×6 · RDL 3×8 · Leg press 3×12\n\n  Progressive overload: +2.5 kg when all reps completed clean\n  Week 5: deload — 40% volume, same intensity\n\n  Source: NSCA CSCS + Israetel volume landmarks (2019)\n```\n\n→ [Browse all skills by domain](./SKILLS.md)\n\n## 📐 The Grimoire Skill Standard\n\ngrimoire maintains an open standard for AI agent skill quality — freely adoptable by any skill library.\n\nEvery skill must pass [`review-best-practice-skill`](./skills/meta/skills/review-best-practice-skill/) before merge:\n\n| Criterion | Requirement | Rejection example |\n|-----------|-------------|-------------------|\n| **Adopted by** | Named organizations or institutions | \"Many top companies\" |\n| **Impact** | Cited study or % number | \"Significantly improves quality\" |\n| **Steps** | Immediately executable | Abstract theory or advice |\n| **Scope** | One concept per skill | \"Nutrition and training program\" |\n| **Source** | External institution or standard body | Internal opinion |\n\nEach skill lives at `skills/<domain>/<subdomain>/skills/<skill-name>/SKILL.md`:\n\n```markdown\n---\nname: skill-name\ndescription: Use when <triggering conditions>\nsource: Author/Org, \"Title\", Year\ntags: [problem-keyword, tool, role, outcome]\n---\n\n# Skill Name\n\nOne-sentence purpose.\n\n## Why This Is Best Practice\n\n**Adopted by:** ...\n**Impact:** ...\n\n## Steps\n...\n```\n\n→ [Read the full standard](./STANDARD.md) · [Adopt this standard](./STANDARD.md#adopting-this-standard)\n\n## 🤝 Contributing\n\n**Your first skill in ~30 minutes:**\n\n1. Pick a practice you've used at the highest level in your field\n2. Run `/write-best-practice-skill` — it guides you through the format step by step\n3. Open a PR — `/review-best-practice-skill` runs automatically and flags any gaps\n4. Merge after review passes\n\n> This workflow applies to contributions to **this repository** (the official package). Skills in your own package have no such requirement — see [docs/user-package.md](./docs/user-package.md).\n\n| Task | Skill |\n|------|-------|\n| Write a new skill | [`write-best-practice-skill`](./skills/meta/skills/write-best-practice-skill/) |\n| Review a skill PR | [`review-best-practice-skill`](./skills/meta/skills/review-best-practice-skill/) |\n| Fix review findings | [`revise-best-practice-skill`](./skills/meta/skills/revise-best-practice-skill/) |\n| Add a new domain | [`design-best-practice-domain`](./skills/meta/skills/design-best-practice-domain/) |\n| Audit a domain's health | [`audit-best-practice-domain`](./skills/meta/skills/audit-best-practice-domain/) |\n| Retire an outdated skill | [`deprecate-best-practice-skill`](./skills/meta/skills/deprecate-best-practice-skill/) |\n\nSee [CONTRIBUTING.md](./CONTRIBUTING.md) · [GOVERNANCE.md](./GOVERNANCE.md) · [STANDARD.md](./STANDARD.md)\n\n## 🛠️ Build Your Own Package\n\nYou don't have to contribute here. Any git repo is a grimoire package — no spec required.\n\n**Three tiers:**\n\n| Tier | Requirement | What you get |\n|------|-------------|--------------|\n| **Unofficial** | Any file layout | Works with `grimoire install myrepo/my-skills` |\n| **Compatible** | SKILL.md frontmatter (`name`, `description`, `tags`) | Skill metadata, `grimoire list`, search |\n| **Standard** | Passes [STANDARD.md](./STANDARD.md) review | PR welcome here, or publish as a standalone package |\n\n**Quickstart:**\n\n```bash\n# Create a new skills package\nmkdir my-skills && cd my-skills\ngit init\nmkdir -p skills/engineering/development/skills/my-skill\ncat > skills/engineering/development/skills/my-skill/SKILL.md << 'EOF'\n---\nname: my-skill\ndescription: Use when ...\ntags: [engineering, development]\n---\n# My Skill\n...\nEOF\n\n# Push to GitHub, then add + install in any project:\ngrimoire install yourusername/my-skills                        # all skills\ngrimoire install \"yourusername/my-skills:engineering/**\"       # one domain only\ngrimoire update                                                # keep it up to date\n```\n\nPublish as `grimoire-<name>` (e.g. `grimoire-cooking`, `grimoire-fintech`) to make it discoverable by others.\n\n→ [Full package authoring guide and ecosystem overview](https://github.com/jeffreytse/grimoire#-skills-as-packages) in the grimoire README.\n\n## 🔧 Maintainer\n\n**Update plugin manifest before each release** (keeps Claude Code marketplace in sync with new skills):\n\n```bash\nmake update-plugin-manifest   # auto-generates .claude-plugin/plugin.json from directory structure\nmake check-manifest           # CI gate: fails if manifest is out of sync\n```\n\n## 📄 License\n\nThis project is licensed under the [MIT license](https://opensource.org/licenses/mit-license.php) © [Jeffrey Tse](https://jeffreytse.net)\n",
  "bytes": 19423,
  "sha": "aaa888eae4d23ce8356f8c4a08f636b6f9a88e35938f63b1b5b5abcdeb4f114c",
  "repo_slug": "jeffreytse/grimoire-core",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_jeffreytse_grimoire_core_642a9abc/readme"
}