Multi-domain skill collection for AI assistants.
Why | Features | Install | Quick Start | Domains | Contributing | Changelog | License
"I'm 42, AI just took my job, I have a mortgage. What do I do?" — one question. Four grimoire skills. A plan.
Describe any problem in plain language. Claude reads your grimoire and auto-routes: apply-first-principles → calculate-fire-number → design-pricing-strategy → write-value-proposition
The world's knowledge is in your AI. The world's practice is not.
AI assistants have ingested every textbook, every paper, every article ever written. They understand fields. They do not practice them. Practice is what happens after 10,000 hours. Practice is what a senior surgeon does without thinking. Practice is what a staff engineer knows not to do. Practice is what grimoire encodes.
-
🌍 The world's best practices belong to everyone. A McKinsey engagement costs $1M. A senior lawyer bills $800/hr. A structural engineer isn't available at 2am. The practices they follow — proven at the highest levels — are not proprietary. They belong to the world. Grimoire makes them free.
-
⚡ Skills are verbs. Not descriptions of what experts know — the exact steps they take, in the exact situation they face, proven at scale. If you can't act on it in the next five minutes, it isn't a skill.
-
🔬 Every claim must be proven. One skill. One concept. Adopted by most top-tier institutions in the field, with measurable impact and a named source. If you can't prove it, you can't ship it.
-
🏔️ Consensus is the floor. If the world's best professionals are split, grimoire acknowledges the debate — and encodes the majority position. When there is no consensus, there is no best practice to ship.
-
🤝 Anyone who has mastered their craft can contribute. A nurse. A jazz musician. A securities lawyer. A structural engineer. Grimoire is not a developer project. It is a project for everyone who has spent 10,000 hours in a field and has something to say about how it's really done.
-
♾️ The skill outlasts the AI. Plain Markdown. No lock-in. No proprietary format. These skills will outlive every AI assistant currently running.
Engineering — propose a commit message from staged diff:
User: /propose-conventional-commit
Claude: Inspecting staged changes...
feat(auth): add OAuth2 PKCE flow for mobile clients
Replaces implicit grant with PKCE to address RFC 6749 §10.16
implicit flow vulnerabilities in native apps.
Approve? [y/n]
Law — audit a SaaS contract before signing:
User: /review-saas-contract
Claude: Red flags found.
🔴 CRITICAL Liability cap is $500 — your contract value is $240,000
🔴 CRITICAL No data processing agreement — GDPR Art.28 requires one
before processing any EU customer data
🟡 WARNING Auto-renewal clause: 90-day cancellation window in §14.3
🟡 WARNING IP ownership of custom integrations is unassigned
✓ PASS SLA 99.9% with defined service credits
Do not sign. Renegotiate: liability cap, DPA, IP clause.
Source: ABA model SaaS agreements
Finance — calculate how much you need to retire:
User: /calculate-fire-number
Claude: Applying Trinity Study model (Bengen 1994, 95% 30-year success rate)
Annual expenses: $60,000
Safe withdrawal rate: 4.0%
─────────────────────────────
FIRE number: $1,500,000
At $4,000/month invested + 7% real return → retire in 20.4 years
Cut annual spend by $12,000 → retire in 16.8 years
Next: /design-portfolio-allocation
Health — design a training program:
User: /design-training-program
Claude: Hypertrophy block — intermediate, 4 days/week
UPPER (Mon/Thu) Bench 4×8 · Row 4×8 · OHP 3×10 · Face pull 3×15
LOWER (Tue/Fri) Squat 4×6 · RDL 3×8 · Leg press 3×12
Progressive overload: +2.5 kg when all reps completed clean
Week 5: deload — 40% volume, same intensity
Source: NSCA CSCS + Israetel volume landmarks (2019)
Every skill is structured: triggering condition, verified source, numbered steps, no freeform guessing.
You don't need to know which skill applies. Just describe the problem:
User: I signed a vendor contract and now they're saying they own my data.
Claude: Situation matches: review-saas-contract (law/contracts)
Applying review-practice-fit...
🔴 CRITICAL Data ownership clause absent — defaults to vendor jurisdiction
→ Escalate to legal counsel immediately. Request amendment to §8.2.
User: My team keeps missing sprint goals and I don't know why.
Claude: Situation matches: plan-retrospective (engineering/project-management)
Run a blameless retrospective (Amazon format):
1. Timeline reconstruction — what actually happened
2. Five whys — surface root causes, not symptoms
3. Action items with owners and deadlines
→ /plan-retrospective to run the session now
suggest-practice auto-classifies any situation, routes to the matching skill,
or tells you exactly what to install if the skill isn't in your library yet.
One command. Every AI agent on your system.
curl -fsSL https://raw.githubusercontent.com/jeffreytse/grimoire/main/scripts/install.sh | bashAuto-detects Claude Code, Codex, and Gemini CLI. Installs to every agent found. No flags needed.
Windows (PowerShell):
Invoke-WebRequest https://raw.githubusercontent.com/jeffreytse/grimoire/main/scripts/install.ps1 -OutFile install.ps1; .\install.ps1Native plugin shortcuts (Claude Code / Codex):
/plugins add github:jeffreytse/grimoire # all skills (latest)
/plugins add github:jeffreytse/grimoire@v1.0.0 # pin to a release
/plugins add github:jeffreytse/grimoire/skills/engineering # one domain
/plugins add github:jeffreytse/grimoire/skills/engineering/development # one sub-domainGranular script installs:
./scripts/install.sh --domain engineering
./scripts/install.sh --domain engineering --subdomain development
./scripts/install.sh --skill engineering/development/propose-conventional-commit
./scripts/install.sh --target all # force install to all agents, even if not detectedGemini CLI:
gemini extensions install https://github.com/jeffreytse/grimoire # latest
gemini extensions install https://github.com/jeffreytse/grimoire@v1.0.0 # pin to a release
gemini extensions update grimoire # update laterCursor — in Agent chat:
/add-plugin grimoire
Or search "grimoire" in the plugin marketplace.
OpenCode: add to opencode.json:
{ "plugins": ["grimoire@git+https://github.com/jeffreytse/grimoire.git"] }After install, describe any problem in plain language:
User: I need to raise a Series A but don't know how to pitch investors.
Claude: Situation matches: write-value-proposition + design-go-to-market + apply-pyramid-principle
Applying suggest-practice...
→ Start with your value prop. /write-value-proposition
Or invoke a skill directly:
/suggest-practice # describe any problem — auto-routes to the right skill
/review-pull-request # engineering code review
/calculate-fire-number # how much do I need to retire?
/review-saas-contract # flag dangerous clauses before signing
/design-training-program # build a training programNew to grimoire? Start with /suggest-practice. Describe any professional or life situation — it reads your context and routes you to the matching skill, or tells you exactly what to install if the skill isn't in your library yet.
| Skill | Domain | Source methodology | Verified |
|---|---|---|---|
apply-five-whys |
engineering/reliability | Toyota Production System / Google SRE | ✓ |
design-go-to-market |
business/strategy | Moore "Crossing the Chasm" | ✓ |
audit-gdpr-compliance |
law/privacy | GDPR / EDPB guidelines | ✓ |
calculate-fire-number |
finance/personal-finance | Bengen (1994) / Trinity Study | ✓ |
design-training-program |
health/fitness | NSCA CSCS curriculum | ✓ |
apply-mise-en-place |
cooking/techniques | Culinary Institute of America | ✓ |
apply-acceptance-commitment-therapy |
psychology/cognitive | Hayes / ACBS meta-analyses | ✓ |
apply-spaced-repetition |
education/curriculum | Ebbinghaus / Roediger & Karpicke | ✓ |
write-value-proposition |
writing/copywriting | Osterwalder "Value Proposition Design" | ✓ |
design-training-periodization-plan |
sports/training | Bompa "Periodization" / NSCA | ✓ |
→ Browse all 514 skills by domain
grimoire maintains an open standard for AI agent skill quality — freely adoptable by any skill library.
Every skill must pass review-skill before merge:
| Criterion | Requirement | Rejection example |
|---|---|---|
| Adopted by | Named organizations or institutions | "Many top companies" |
| Impact | Cited study or % number | "Significantly improves quality" |
| Steps | Immediately executable | Abstract theory or advice |
| Scope | One concept per skill | "Nutrition and training program" |
| Source | External institution or standard body | grimoire STANDARD.md |
→ Read the full standard · Adopt this standard
See CONTRIBUTING.md to submit a skill.
grimoire is a framework + reference skills. The domain structure is ready — contribute to fill your domain.
| Agent | Plugin install | Script install |
|---|---|---|
| Claude Code | /plugins add github:jeffreytse/grimoire |
--target claude |
| Codex | /plugins add github:jeffreytse/grimoire |
--target codex |
| Cursor | /add-plugin grimoire (in Agent chat) |
--target all |
| OpenCode | See .opencode/INSTALL.md |
--target all |
| Gemini CLI | gemini extensions install https://github.com/jeffreytse/grimoire |
--target gemini |
grimoire has 514 skills. It needs 1000. Pick a domain.
Every domain has empty sub-domains waiting for skills. If you know a field — engineering, law, finance, music, cooking, anything — add the practices you've seen work at the highest level.
Your first skill in ~30 minutes:
- Pick a practice you've used at the highest level in your field
- Run
/write-skill— it guides you through the format step by step - Open a PR —
/review-skillruns automatically and flags any gaps - Merge after review passes
Not sure where to start? Browse open issues for requested skills, or pick any empty sub-domain from the table below.
Skills must pass review-skill before merge.
The meta skills guide the full contribution workflow:
| Task | Skill |
|---|---|
| Write a new skill | write-skill |
| Review a skill PR | review-skill |
| Fix review findings | revise-skill |
| Add a new domain | design-domain |
| Audit a domain's health | audit-domain |
| Retire an outdated skill | deprecate-skill |
See CONTRIBUTING.md for the full standard and GOVERNANCE.md for how the project and standard evolve.
grimoire is free. It replaces $500/hr lawyers, $300 doctor visits, and $1M McKinsey engagements — at zero cost, forever.
If it saved you time, money, or a bad decision:
- ⭐ Star this repo — takes 2 seconds, helps thousands of people find it
- 💖 Sponsor on GitHub — keeps the maintainer funded to add more skills across more domains
- ☕ Ko-fi · Patreon · Liberapay — one-time or recurring
Every star makes grimoire more visible. Every sponsorship funds one more domain.
This project is licensed under the MIT license © Jeffrey Tse.