init-rules
Skill12 starsChanged 48 days agoMITView on GitHub
Interactively generate personalized agent rules. Asks about tech stack, work style, and preferences, then writes customized rule files. Use when user says \"init rules\", \"set up my rules\", or \"configure agent rules\".
5 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- GopkoDev/motion-flowtheir own version, first seen Oct 20, 2026
- The-Syntax-Slayer/skill-genieedited, first seen Oct 9, 2026
- trapple/skillstheir own version, first seen Jul 21, 2026
- dldush/claude-skill-settheir own version, first seen Mar 31, 2026
- lifedever/claude-rulestheir own version, first seen Mar 18, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- The-Syntax-Slayer/skill-genie★ 197% same
Wrote their own version · 4
- lifedever/claude-rules★ 189same name
- dldush/claude-skill-set★ 2same name
- GopkoDev/motion-flow★ 1same name
- trapple/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository37 other files it gives its agents.
- 3mf-print-editorSkill
- aegis-protocolSkill
- ai-address-parser-debugSkill
- ai-address-parserSkill
- ai-csuiteSkill
- browser-driverSkill
- chatgpt-web-delegationSkill
- chinese-humanizerSkill
- claude-agent-sdk-authSkill
- close-loopSkill
- de-ai-englishSkill
- dev-inboxSkill
- dokploy-deploySkill
- dokploy-upgradeSkill
- ecommerce-golive-checkSkill
- fork-upstream-syncSkill
- foxcode-openclawSkill
- git-cryptSkill
- git-worktree-decisionSkill
- handoff-receiverSkill
- image-prompt-engineerSkill
- landing-launch-checkSkill
- linuxdo-applicationSkill
- npm-publishSkill
- omnidebug-autopilotSkill
- psychology-masterSkill
- refactor-agents-mdSkill
- research-to-wechatSkill
- right-sized-solutionSkill
- rtk-token-saverSkill
- session-handoffSkill
- shared-memorySkill
- stalwart-dokploy-resend-relaySkill
- typed-decisions-around-llmsSkill
- web-compliance-builderSkill
- wechat-compliance-checkSkill
- wordpress-vps-installSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 7 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
7
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Ask the user these questions ONE AT A TIME.
- Very specific: line 45
Before writing, if rules/ already contains .md files:
- Distinctive: line 46
Read all existing rule files fully — understand the user's current preferences and intent
- Distinctive: line 48
When generating new rules, compare the user's new answers against their existing rules:
- Distinctive: line 49
No conflict: Keep the existing rule as-is in the new output
- Distinctive: line 51
New rule with no existing equivalent: Add it
- Very specific: line 54
After collecting answers, generate these files in the skill-genie rules/ directory:
- Distinctive: line 78
Do NOT include project-specific details — those belong in project AGENTS.md
- Distinctive: line 79
Keep rules universal (apply to any project the user works on)
- Very specific: line 80
If user says "same as example", copy from rules.example/
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Init Rules
Requires Skill Genie. This skill generates rule files for the skill-genie
rules/directory. Install skill-genie first, then run this skill.
Generate personalized agent rule files through a short interview.
Process
Ask the user these questions ONE AT A TIME. After each answer, move to the next. Skip questions the user says aren't relevant.
1. Work style
- "How should I behave? (e.g., execute without asking, ask before acting, explain reasoning, be concise)"
2. Tech stack
- "What's your default tech stack? (e.g., Nuxt + Appwrite, Next.js + Supabase, Rails, Swift/macOS, none)"
3. Package manager
- "Package manager preference? (pnpm, npm, yarn, bun, or N/A)"
4. Deployment
- "How do you deploy? (e.g., Vercel, Dokploy, Docker, AWS, manual, none)"
5. Git workflow
- "Git rules? (e.g., never push without asking, auto-push OK, use PRs, conventional commits)"
6. Code quality
- "Any hard code rules? (e.g., no
any, max file length, test required, specific linter)"
7. Skills integration
- "Should I auto-load skills when a task matches? (yes/no)"
8. Session behavior
- "Anything special at session start? (e.g., check upstream, read AGENTS.md, run status)"
Output
Before writing, if rules/ already contains .md files:
- Read all existing rule files fully — understand the user's current preferences and intent
- Back them up:
mv rules/ rules.bak.$(date +%Y%m%d%H%M)/ && mkdir rules/ - When generating new rules, compare the user's new answers against their existing rules:
- No conflict: Keep the existing rule as-is in the new output
- Conflict detected: Explain the conflict to the user, suggest which version is better and why, then ask which to use
- New rule with no existing equivalent: Add it
- The goal is to produce rules that reflect the user's FULL intent — both what they said in this interview AND what they previously established
After collecting answers, generate these files in the skill-genie rules/ directory:
rules/router.md— Universal top-level rulesrules/session-sync.md— Session start behaviorrules/workflow-tools.md— Tool and workflow preferencesrules/stack-and-deployment.md— Tech stack and deployment (skip if "none")rules/external-tools.md— Skills and external tool usage
Then run setup.sh to apply them.
Rules format
Each file should be concise Markdown, under 30 lines. Use bullet points. No fluff. Example:
# Workflow and tools
- Prefer CLI over MCP when both can do the job.
- Batch independent operations.
- Verify feature doesn't already exist before creating it.Important
- Do NOT include project-specific details — those belong in project AGENTS.md
- Keep rules universal (apply to any project the user works on)
- If user says "same as example", copy from
rules.example/
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

