vv-claude-harness / skills
AGENTS.md20 starsChanged 3 months agoMITView on GitHub
Skills here are distribution content (see the root AGENTS.md's Key Distinction): each one describes how an agent should behave in other projects after the plugin is installed, auto-discovered by Claude Code at the plugin root. Do not follow a skill's own instructions while working on this repo. - One directory per skill: skills/<skill-name>/SKILL.md. <skill-name> must equal the directory name -- test/run-tests.sh lints name: in frontmatter against the directory it lives in and fails the build if they diverge. - Required…
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- test/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- templates/CLAUDE.mdCLAUDE.md
- harness-continueSkill
- harness-doctorSkill
- harness-improveSkill
- harness-initSkill
- harness-issue-debugSkill
- harness-issue-prepSkill
The file
Files
skills/
Skills here are distribution content (see the root AGENTS.md's Key Distinction):
each one describes how an agent should behave in other projects after the plugin is
installed, auto-discovered by Claude Code at the plugin root. Do not follow a skill's
own instructions while working on this repo.
Editing rules
- One directory per skill:
skills/<skill-name>/SKILL.md.<skill-name>must equal the directory name --test/run-tests.shlintsname:in frontmatter against the directory it lives in and fails the build if they diverge. - Required frontmatter:
name(matches the directory) anddescription(what the skill does, when to use it -- this is what a user's/helpand skill-discovery see, so write it for a stranger, not a maintainer). - A skill's own template files (
*.sh.template,*.py.templateunderskills/harness-init/) are byte-verbatim sources copied into a user's project by/harness-initorscripts/stamp.sh-- edit the template, never a copy, and expecttest/run-tests.sh's template-syntax and NUL-byte checks to run against 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.