letscooktech-studioletscooktech-studio/ai-engineering-arsenal/skills/agentic-skill-pack-integrator/SKILL.mdagentic-skill-pack-integrator
Skill7 starsChanged 6 days agoMITView on GitHub
Convert external AI skill packs, prompt packs, Claude skills, Codex skills, Cursor rules, Windsurf rules, Cline/Roo workflows, and CLI agent instructions into OutcomeLab-compatible skill frameworks with metadata, safety gates, evaluation rubrics, benchmark plans, and compatibility notes. Use when importing or upgrading skill collections for Codex, Claude Code, ChatGPT, Gemini, Cursor, Windsurf, Cline, Roo Code, Aider, or Antigravity-style agentic IDEs.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- letscooktech-studio/outcomelabword for word, first seen Nov 8, 2026
Other versions1 project uses a version of this.
Word for word · 1
- letscooktech-studio/outcomelab★ 7100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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 repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ai-agent-architecture-reviewerSkill
- ai-search-optimizerSkill
- competitor-analyzerSkill
- cost-explosion-detectorSkill
- cto-operating-systemSkill
- database-architectSkill
- nextjs-production-architecture-reviewerSkill
- nvidia-accelerated-ai-systems-operatorSkill
- production-ai-saas-builderSkill
- production-risk-labSkill
- security-auditorSkill
- seo-auditorSkill
- startup-validatorSkill
- supabase-production-auditorSkill
- system-architectSkill
- technical-debt-hunterSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
Add compatibility notes for Codex, Claude Code, ChatGPT, Gemini, Cursor, Windsurf, Cline, Roo Code, Aider, CLI installers, and …
- Distinctive: line 21
Add safety gates for secrets, credentials, production writes, destructive operations, network calls, vendor credentials, and user …
- Distinctive: line 22
Add proof artifacts: rubric, failure patterns, comparison template, and benchmark plan before claiming superiority.
- Distinctive: line 29
When writing repository files, create only maintainable OutcomeLab assets.
- Distinctive: line 33
No skill is accepted without clear trigger metadata, workflow, output contract, and quality gates.
- Distinctive: line 34
No vendor content is copied without license compatibility and attribution.
- Distinctive: line 35
No executable script is trusted without inspection and a safe test path.
- Distinctive: line 36
No production action is automated without permission, rollback, and human review.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Agentic Skill Pack Integrator
Developed by the LetsCookTech Open Source Team.
Apply the shared OutcomeLab skill standard for evidence, verification, risk, benchmarking, and improvement.
Turn raw skill packs into portable, production-grade AI operating skills. Preserve license requirements, remove filler, normalize metadata, add safety boundaries, and create evaluation paths.
Workflow
- Inventory the source pack: skill names, descriptions, licenses, required tools, environment variables, network requirements, scripts, assets, and supported clients.
- Classify each item as direct import, wrapper skill, reference-only material, duplicate, unsafe, vendor-specific, or reject.
- Normalize names to lowercase hyphen-case and create concise
SKILL.mdfrontmatter with clear trigger conditions. - Convert long instructions into progressive disclosure: keep
SKILL.mdoperational and move deep details into references only when needed. - Add compatibility notes for Codex, Claude Code, ChatGPT, Gemini, Cursor, Windsurf, Cline, Roo Code, Aider, CLI installers, and Antigravity-style agentic IDEs.
- Add safety gates for secrets, credentials, production writes, destructive operations, network calls, vendor credentials, and user authorization.
- Add proof artifacts: rubric, failure patterns, comparison template, and benchmark plan before claiming superiority.
- Validate structure, remove temp/vendor noise, and report what was imported, adapted, skipped, and why.
Output contract
Return source inventory, imported skills, wrapper skills, skipped files with reasons, license notes, client compatibility matrix, safety boundaries, benchmark plan, validation result, and next improvement list.
When writing repository files, create only maintainable OutcomeLab assets. Do not commit extracted archives, private certs, vendor caches, generated lock noise, or unreviewed large assets.
Quality gates
- No skill is accepted without clear trigger metadata, workflow, output contract, and quality gates.
- No vendor content is copied without license compatibility and attribution.
- No executable script is trusted without inspection and a safe test path.
- No production action is automated without permission, rollback, and human review.
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.