cat-skills
AGENTS.md3 starsChanged 3 months agoMITView on GitHub
AI agent skills by catcatcat. Each skill is a self-contained instruction set in skills/.
In this repository42 other files it gives its agents.
- adversarySkill
- architectSkill
- eatSkill
- elevateSkill
- eyeSkill
- fortifySkill
- liquid-cat-physicsSkill
- mementoSkill
- notebookSkill
- prodevSkill
- reconSkill
- scorched-earthSkill
- vetSkill
- xraySkill
- adversarySkill
- architectSkill
- eatSkill
- elevateSkill
- eyeSkill
- fortifySkill
- liquid-cat-physicsSkill
- mementoSkill
- notebookSkill
- prodevSkill
- reconSkill
- scorched-earthSkill
- vetSkill
- xraySkill
- adversarySkill
- architectSkill
- eatSkill
- elevateSkill
- eyeSkill
- fortifySkill
- liquid-cat-physicsSkill
- mementoSkill
- notebookSkill
- prodevSkill
- reconSkill
- scorched-earthSkill
- vetSkill
- xraySkill
The file
Files
cat-skills
AI agent skills by catcatcat. Each skill is a self-contained instruction set in skills/.
Skill Directory
| Skill | Trigger | Description |
| eat | /eat | Knowledge extraction from URLs — YouTube, articles, podcasts, X threads |
| notebook | /notebook | Project notes — decisions, failures, lessons, context recovery |
| architect | /architect | Staged build methodology — spike, design, plan, build |
| recon | /recon | Pre-build intelligence — best practices, pitfalls, architecture research |
| xray | /xray | X/Twitter content intelligence — scout, pulse, track, mirror, prospect |
| elevate | /elevate | Expert elevation — shifts model from executor to critical advisor |
| prodev | /prodev | Engineering standard enforcement — ownership, blast radius, anti-sycophancy |
| memento | /memento | Context handoff for fresh sessions |
| liquid-cat-physics | /liquid-cat-physics | Autonomous deep-work loop — expert lens + prodev standard, confidence gating, persists, loops |
| fortify | /fortify | Testing infrastructure, coverage, and mutation testing |
| vet | /vet | Thorough codebase investigation — find every problem, plan fixes, execute |
Reference Files
| File | Path |
| Build methodology | skills/architect/references/methodology.md |
| Testing obligations | skills/architect/references/testing.md |
| Stage template | skills/architect/references/stage-template.md |
| Notebook standalone | skills/notebook/INSTRUCTIONS.md |
| Expert questions | skills/recon/references/expert-questions.md |
| Research categories | skills/recon/references/research-categories.md |
| X API reference | skills/xray/references/x-api.md |
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.