agentleFS
Sign inStart free
MelvynxMelvynx/ai-maxxing-skills/skills/safe-ship/SKILL.md

safe-ship

Skill32 starsChanged 25 days agoMITView on GitHub

Ship local changes by inspecting dirty state, scoping the stage, running targeted validation, then committing, pushing, and checking remote gates. Use when the user asks to commit, push, ship, merge, deploy, or whether a diff is safe to push.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Commit with a concise commitizen-style message.

    line 12
  2. Distinctive:

    Verify with git status --short --branch, git rev-parse HEAD, and the real external gate until it reaches the requested state or blocks.

    line 13
  3. Very specific:

    Use trash for deletions. Quote paths that contain brackets.

    line 15

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Inspect dirty state, stage only the requested scope, validate the touched surface, then commit, push, and verify the remote gate.

  1. git status --short --branch, git diff --stat, git diff --name-only, git log --oneline --decorate -5.
  2. Stage only the files for the asked fix. Stage the full dirty tree only when the user says all or commit all. Leave unrelated dirty files untouched and name them.
  3. git diff --check, then the project format/lint/type/test/build commands that match the touched surface. Prefer targeted tests; widen when shared code, generated files, auth, payment, data, or routes changed.
  4. Separate introduced failures from baseline noise. Local green is not a PR or deploy ready if GitHub, Vercel, or Netlify is the decisive gate.
  5. Commit with a concise commitizen-style message. Push the correct branch.
  6. Verify with git status --short --branch, git rev-parse HEAD, and the real external gate until it reaches the requested state or blocks.

Use trash for deletions. Quote paths that contain brackets. If generated files are a framework contract, check the sibling or starter repo before ignoring or committing them.

Finish with the SHA and branch, validation run, skipped or pending gates, and unrelated dirty files left alone.

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.

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free