fix-with-the-kit
Skill0 starsChanged 12 days agoMITView on GitHub
Write a repository's missing standard files (licence, security and contributing guides, code of conduct, GEMINI.md, NOTICE, the Claude Code plugin and marketplace, the Gemini CLI extension, the A2A agent card) and its README blocks from a facts file, with a dry run first. Use after an audit lists gaps marked "the kit writes it", or when bringing a new repository up to the standard.
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Write the facts file: Start from facts.example.json: the one-liner, the kind, the CLI and MCP bins, the skills you wrote, the runtime …
- Distinctive: line 23
Run it again: after you update the facts file.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
Fix with the kit
When to use
An audit shows gaps the kit can fill, or a new repository needs the standard files and README blocks.
Steps
- Write the facts file. Start from
facts.example.json: the one-liner, the kind, the CLI and MCP bins, the skills you wrote, the runtime (pythongives uvx commands, anything else npx) and, once tested, the component grades. - Dry run:
fleet-audit kit <path> --facts <facts.json> --owner <github-owner> --author "<licence holder>" --dry-run. Read the list. - Write: the same command without
--dry-run. It creates only missing files and replaces only its own marked README blocks. - Write the README body around the blocks: two or three plain sentences on what it is and who it is for, a Quick start with commands you ran, and how it works.
- Run it again after you update the facts file. The blocks are replaced in place, never duplicated.
- Commit by explicit path, then run
fleet-audit check <path>again.
Output
The list of files written, the README with its blocks, and the check table after the commit.
Anti-patterns
- Writing without a dry run in a repository you do not know.
- Editing inside the marked blocks by hand: the next run replaces them. Change the facts file instead.
- Grading a component in the facts file before you have tested it.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- audit-a-repoSkill
- scrub-before-publicSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

