agentleFS
alsy99alsy99/agent-enterprise-os/skills/eng-pr/SKILL.md

eng-pr

Skill0 starsChanged 2 months agoMITView on GitHub

Turn a ticket into a small PR with tests and a verifier checklist. Use when implementing a scoped engineering change or opening a draft PR. Do not merge to main without approval.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No customer PII on NIM trial

    line 21
  2. Very specific:

    Read wiki/engineering/conventions.md and related SOPs.

    line 27
  3. Distinctive:

    Add/adjust tests; run them.

    line 29
  4. Very specific:

    Run verifier checks in evals/ / Promptfoo assertions for this skill.

    line 31
  5. Very specific:

    Stop at draft PR — merge requires APPROVE_MERGE.

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

When to use

  • Ticket / issue is scoped to one thin slice
  • Coding harness is OpenCode or OpenHands

Models

  • Actor: coder (Mistral Codestral free; NIM Nemotron Super alternate)
  • Verifier: tests first; LLM second opinion = worker or verifier (Groq) — not another coding model agreeing with itself
  • No customer PII on NIM trial
  • Resolve: ./scripts/resolve-model.sh eng-pr

Steps

  1. Restate the ticket and out-of-scope in 3 bullets.
  2. Read wiki/engineering/conventions.md and related SOPs.
  3. Implement the smallest change that meets acceptance.
  4. Add/adjust tests; run them.
  5. Open a draft PR (or write artifacts/pr-drafts/<slug>.md if no GitHub MCP).
  6. Run verifier checks in evals/ / Promptfoo assertions for this skill.
  7. Stop at draft PR — merge requires APPROVE_MERGE.

Tools allowed

  • GitHub MCP (branch, commit, draft PR)
  • Shell/tests in sandbox
  • Wiki read

Definition of done

  • Diff matches ticket scope
  • Tests exist and pass (or documented why not)
  • Draft PR or artifact PR description present
  • Verifier checklist attached

Never do

  • Merge to main without approval
  • Commit secrets
  • Expand scope mid-flight without updating the ticket

Escalation

  • Ambiguous acceptance criteria → human
  • Verifier fail → do not mark done

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.