agentleFS
Sign inStart free
ForeactLabsForeactLabs/OpenExecutive/.claude/skills/steward/SKILL.md

steward

Skill5.8k starsChanged 50 days agoApache-2.0View on GitHub

Repo rules for driving an Open Executive pull request to green - CI failures, the pr-checks job, and findings from the automated Claude review. Use when watching, fixing or babysitting a PR in this repo.

18 other projects use a version of this.

Adopted by

Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data

Week of Sep 13: 0 new projectsWeek of Sep 20: 0 new projectsWeek of Sep 27: 0 new projectsWeek of Oct 4: 0 new projectsWeek of Oct 11: 0 new projectsWeek of Oct 18: 0 new projectsWeek of Oct 25: 0 new projectsWeek of Nov 1: 0 new projects
Sep 2026Oct 2026Nov 2026
New projects taking a version of this file each week, over the 8 weeks our latest run read: only 0 in all, so this is a hint, not a trend.

Most recently taken up by

Used with

Projects with it also use release.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    release

    Use ONLY when the user explicitly asks to cut/publish a Huabu desktop release or tag a version. Performs an outward action — bumps the version in apps/desktop/package.json, commits + annotated-tags vX.Y.Z, and pushes the branch + tag. That tag push auto-builds the macOS/Windows installers and publishes a GitHub Release. Provides `status`, `bump`, `tag-push`, and a one-command `run` (bump → tag-push).

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 16 edited versions we read keep these.

  • 1

    Distinctive

    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:

    Only what is specific to this repo.

    line 8
  2. Very specific:

    If a test fails only in the full run, rerun it serially (no -n).

    line 19

“Common” is measured: kept by at least 6 in 10 of the 16 edited versions of this file we could read. “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

Steward: driving an Open Executive PR

Only what is specific to this repo. CLAUDE.md covers the code rules.

Before every push

  • First push: run make check once. Later pushes in the same round: run make test-changed (the tests covering your change) and ruff on the files you touched; CI runs the rest. Rerun the full make check only if the fix touched shared code (tests/conftest.py, pyproject.toml, a base class). CI cancels a superseded run, so don't push piecemeal.
  • make check It runs what CI runs (lint, unit and integration tests, the UI build if packages/ui changed, scripts/pr_checks.py) with the BACKEND_SHARED_SECRET / OE_PUBLIC_DEPLOYMENT traps handled.
  • If a test fails only in the full run, rerun it serially (no -n). The usual cause is a ContextVar or audit-log leak from another module (see CLAUDE.md -> Testing), not a flake.
  • Batch every fix for a round into one push. Each push re-runs the paid Claude review.

PR rules job red

  • arch-doc-drift: re-author the named architecture/prebuilt/<section>.json and the matching architecture-facts.yaml notes. Waive with Arch-Docs: n/a - <reason> only when the change doesn't alter what the section describes. Never waive just to get green.
  • eval-scenarios: add the evals/_scenarios/*.yaml files the new-agent checklist in CLAUDE.md asks for.
  • no-stubs: finish the code; don't reword the marker.

Claude review findings

The Claude Code Review workflow starts each inline comment with a marker:

  • 🔴 must fix before merge (bug, security, CLAUDE.md invariant). Fix it, or reply with evidence that it doesn't reproduce.
  • 🟡 optional. Reply in one line; fold it into the next push only if it is plainly right. It never starts a push on its own.
  • 🟣 pre-existing, not introduced by this PR. Reply in one line and leave it.

Branch and title

  • PRs are squash-merged with the title as the commit subject, which release-please reads. Keep it type(scope): what changed.
  • Resolve conflicts by merging main into the branch, not by force-pushing.
  • Regenerate lockfiles with uv lock / npm install, never by hand. The uv lock --check step fails on a stale uv.lock.

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