agentleFS
sakurablushsakurablush/zeroagent-studio/.cursor/skills/ship-patch/SKILL.md

ship-patch

Skill4 starsChanged 4 months agoMITView on GitHub

End-to-end patch workflow for ZeroAgent Studio — implement, test, review, version, commit. Use when shipping a fix or feature branch.

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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
  1. Distinctive:

    Commit on red CI

    line 28
  2. Distinctive:

    Add server deps or repo-stored secrets

    line 29

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Ship Patch

Focused branch → green gate → optional review → version/docs → commit (user request only).

Steps

  1. Branch — from main; one concern per branch
  2. Implement — .cursor/rules/zeroagent-engineer.mdc; minimal diff; no backend
  3. Test — npm ci + npm run ci (.cursor/skills/pre-commit-ci/SKILL.md)
  4. Review (optional) — .cursor/skills/review-before-merge/SKILL.md
  5. Document — user-visible → CHANGELOG.md + #/guide if behavior changed
  6. Version — .cursor/skills/release-versioning/SKILL.md when shipping
  7. Commit — only after green gate; user must ask
  8. Deploy — push to main (GitHub Actions) or npm run deploy when user asks

Do not

  • Commit on red CI
  • Add server deps or repo-stored secrets
  • Store API keys outside src/lib/keyStorage.ts / Settings panel

Final reply (token-efficient)

Execution plan with [x] · files touched · gate result · version bump (if any)

Download now (ZIP)

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.