agentleFS
Sign inStart free
connext-solutionsconnext-solutions/flowctl/.claude/skills/review-pr/SKILL.md

review-pr

Skill1 starsChanged 5 days agoApache-2.0View on GitHub

Use when asked to review a flowctl pull request (by number or branch). Checks CI, runs verify locally, delegates the checklist to the flowctl-reviewer subagent, adds what only a human-facing review can judge, and drafts comments for the user to approve before anything is posted.

185 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use diagnose-ci-failures, docs-loop and 10 more.

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.
  • zerx-labSkill

    diagnose-ci-failures

    Diagnose CI failures for a PR using the GitHub CLI, extract error logs, and generate a plan to fix them. Use when the user asks to check CI status, pull CI issues, triage test failures, or investigate PR build failures.

    Also in 3 projects that use this

  • GeiserXSkill

    docs-loop

    Use when the user asks to audit docs, check documentation for stale claims, or verify docs against the code.

    Also in 3 projects that use this

  • GeiserXSkill

    full-loop

    Drive a repository to done with sergio-loop, then keep improving it with refine-loop at a descending theta. Use only when the user explicitly invokes full-loop.

    Also in 3 projects that use this

  • n24q02mSkill

    review-delta

    Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.

    Also in 3 projects that use this

  • n24q02mSkill

    build-graph

    Build or update the code review knowledge graph. Run this first to initialize, or let hooks keep it updated automatically.

    Also in 3 projects that use this

  • +7 more from GeiserX

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 178 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    If CI is red or pending, report that first.

    line 11
  2. Very specific:

    Use a separate clone, never a worktree: a worktree shares .git/config, so a git config run by the PR's tests (core.fsmonitor, …

    line 17
  3. Very specific:

    Show the draft to the user and wait: Only after a go: gh pr review <n> --comment|--approve|--request-changes --body-file <draft> (inline …

    line 37

“Common” is measured: kept by at least 6 in 10 of the 178 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

Review a pull request

The checklist lives in one place: .claude/agents/flowctl-reviewer.md. This skill is the procedure around it.

  1. Read the PR: gh pr view <n> (body, base, labels, linked issue), gh pr diff <n> --name-only, gh pr checks <n>. If CI is red or pending, report that first; do not review a red PR line by line.

  2. Run it locally: the PR's own scripts, tests and config run with your environment, so look before you run.

    • git fetch origin, then branch=$(gh pr view <n> --json headRefName -q .headRefName); never paste a branch name into a command by hand.
    • git diff --name-only "origin/<base>...refs/remotes/origin/$branch" -- package.json bun.lock vitest.config.ts .githooks .claude scripts: if anything is listed, stop and show the user those files before running anything.
    • Use a separate clone, never a worktree: a worktree shares .git/config, so a git config run by the PR's tests (core.fsmonitor, core.hooksPath) would keep running in the main checkout. git clone --no-hardlinks --no-checkout . "../flowctl-review-<n>", then in it git fetch origin "refs/remotes/origin/$branch" && git checkout --detach FETCH_HEAD (its origin is your local checkout, which already fetched the PR branch).
    • In the clone: bun install --frozen-lockfile --ignore-scripts && bun run verify.

    A green CI run does not replace this when the PR touches browser behaviour. Delete the clone when done (rm -r -f "../flowctl-review-<n>", which asks first).

  3. Checklist: dispatch the flowctl-reviewer subagent on origin/<base>..origin/<head>. Do not re-run its checks yourself; read its findings and verify any you are going to repeat.
  4. What the subagent cannot judge:
    • Does the PR do what its issue / acceptance criteria ask, and nothing unrelated?
    • Touches explore, replay or heal → is there a result of a trial on a real app in the body? If not, ask for one.
    • Golden file __golden__/system1-request.json changed → is there a contract-tier run and a new docs/benchmarks/jev.jsonl line?
    • Changes a contract (flow YAML, config, --json, exit codes, MCP results) → ADR and "Breaking changes" filled?
    • Stacked → base is the branch below, status:stacked label, "Stack: n/N" in the body.
  5. Draft the review. One comment per finding, prefixed blocker:, should-fix: or nit:, with file:line, the rule it breaks, and the smallest fix. Separate verdict line: approve, comment, or request changes.
  6. Show the draft to the user and wait. Only after a go: gh pr review <n> --comment|--approve|--request-changes --body-file <draft> (inline comments through gh api if asked). Never merge; merging is the user's action.

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