agent-skills
CLAUDE.md2 starsChanged 48 days agoMITView on GitHub
Public repo — ships to other people, so product regime (full effort, proactively improved, not a learning artifact). See Software_Engineering\CONTEXT.md for what regime means and Agentic_Engineering_Schema\project_setup_and_testing_ladder.md for what it implies. No testing ladder applies in the mechanical sense (this repo ships Markdown skill files, not executable code) — "correct" here means the skill files are internally consistent and genuinely agent-agnostic, checked by review, not a test suite. Content policy: this repo is public. Never add anything referencing James's private workspace…
In this repository3 other files it gives its agents.
- pair-programmerSkill
- review-prSkill
- wrapSkill
The file
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 12
No testing ladder applies in the mechanical sense (this repo ships Markdown skill files, not executable code) — "correct" here means the …
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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
agent-skills
Public repo — ships to other people, so product regime (full effort, proactively
improved, not a learning artifact). See Software_Engineering\CONTEXT.md for what regime
means and Agentic_Engineering_Schema\project_setup_and_testing_ladder.md for what it
implies.
No testing ladder applies in the mechanical sense (this repo ships Markdown skill files, not executable code) — "correct" here means the skill files are internally consistent and genuinely agent-agnostic, checked by review, not a test suite.
Content policy: this repo is public. Never add anything referencing James's private
workspace paths, real name in prose (author/copyright line in LICENSE is fine), other
projects (Greco, Teutoburg, Skill_Development), or any of this workspace's internal
doctrine files by path. Each skill here must stand alone for a stranger who has never
seen Software_Engineering\.
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.