legal-ai-engineering-lab / rules
AGENTS.md2 starsChanged 3 months agoMITView on GitHub
Everything in .agents/skills/ is generated. Do not edit it. The source of each file is .claude/skills/<name>/SKILL.md, the authoritative Claude Code representation. This tree is the portable Agent Skills representation, at the conventional location a number of harnesses read. Maintaining both by hand would be two copies that can disagree; deriving one removes that. Owner-invoked skills also carry an agents/openai.yaml here, because the Claude frontmatter key that says "never invoke this yourself" is not portable. docs/SKILL_ROUTING.md sets out which harnesses this…
In this repository21 other files it gives its agents.
- .agents/AGENTS.mdAGENTS.md
- AGENTS.mdAGENTS.md
- evals/AGENTS.mdAGENTS.md
- tests/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- architecture-reviewSkill
- code-reviewSkill
- evaluation-reviewSkill
- explainSkill
- interview-reviewSkill
- learning-reviewSkill
- security-reviewSkill
- start-projectSkill
- architecture-reviewSkill
- code-reviewSkill
- evaluation-reviewSkill
- explainSkill
- interview-reviewSkill
- learning-reviewSkill
- security-reviewSkill
- start-projectSkill
The file
Files
<!-- Generated from ../../.agents/AGENTS.md - do not edit this copy.
Edit the source and run `uv run python scripts/sync_agent_files.py`. -->Working under .agents/
Everything in .agents/skills/ is generated. Do not edit it.
The source of each file is .claude/skills/<name>/SKILL.md, the authoritative Claude Code
representation. This tree is the portable Agent Skills representation, at the conventional
location a number of harnesses read. Maintaining both by hand would be two copies that can
disagree; deriving one removes that.
Owner-invoked skills also carry an agents/openai.yaml here, because the Claude frontmatter
key that says "never invoke this yourself" is not portable. docs/SKILL_ROUTING.md sets out
which harnesses this repository actually supports, as against which could read these files.
To change a skill, edit the source and regenerate:
uv run python scripts/sync_agent_files.pyAnything written here directly is lost the next time that runs, and CI fails when this tree
has fallen behind its source. docs/decisions/0004-two-skill-directories.md records why the
repository generates this copy rather than maintaining it.
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.

