agentleFS
Sign inStart free
epamepam/ketcher/.agents/skills/review-pr/SKILL.md

review-pr

Skill927 starsChanged 2 days agoApache-2.0View on GitHub

Review a Ketcher pull request with the code-review lenses its diff needs and post the verified findings and the review brief.

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 178 edited versions we read keep these.

  • 0

    Distinctive

    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. Very specific:

    Panel: Run node scripts/review-panel.mjs --pr <PR_NUMBER> --repo <REPO> and take the lenses it prints, as Panel in the code-review skill …

    line 16
  2. Very specific:

    The linked issue: Read the PR description with gh pr view, fetch the issue it links with gh issue view, and answer whether the diff fixes …

    line 19
  3. Very specific:

    The brief: Write it as Human review sets, even when no finding survives.

    line 21

“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

Arguments: $ARGUMENTS

The arguments name the pull request (PR_NUMBER) and may name the repository (REPO, epam/ketcher when absent). Run every gh call as gh <command> <PR_NUMBER> --repo <REPO>.

CI means the mcp__github_inline_comment__create_inline_comment tool is present: claude-review.yml provides it. Every finding follows the output contract.

  1. Get the diff with gh pr diff.
  2. Panel. Run node scripts/review-panel.mjs --pr <PR_NUMBER> --repo <REPO> and take the lenses it prints, as Panel in the code-review skill says. With No lens applies., go to step 5. Done when you have the panel.
  3. First pass, on the diff alone. Run one review subagent per lens on the panel, in parallel, each with the code-review skill and its lens file. They can read files but not run gh, so pass each the diff text, with read-only file tools. Per-tool dispatch melodies, and what to do in a tool without subagents, are in ROLES.md under the reviewer row. Done when every lens on the panel has reported.
  4. Verify. For each finding, open the cited file:line and confirm its failing scenario, as the output contract says. Done when every finding is confirmed, dropped, or an open question.
  5. The linked issue. Read the PR description with gh pr view, fetch the issue it links with gh issue view, and answer whether the diff fixes it. With no linked issue, the answer is "no linked issue". The answer goes in the brief.
  6. Findings. In CI, post each confirmed finding as an inline comment with the CI tool, in the order and within the cap the output contract sets; the rest, and the open questions, go in the brief. Outside CI, every finding goes in the brief, one line each. Done when each one is posted or in the brief.
  7. The brief. Write it as Human review sets, even when no finding survives. In CI, post it as one top-level comment with gh pr comment. Outside CI, show it to the user and post it only on their approval: it is public on the PR.

Download now (ZIP)

  • Other versions185 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 185

    1. denoland/deno★ 109ksame name
    2. ToolJet/ToolJet★ 41ksame name
    3. remix-run/remix★ 33ksame name
    4. tirth8205/code-review-graph★ 32ksame name
    5. alpinejs/alpine★ 32ksame name
    6. nrwl/nx★ 29ksame name
    7. jlowin/fastmcp★ 28ksame name
    8. PrefectHQ/fastmcp★ 28ksame name
    9. livewire/livewire★ 24ksame name
    10. microsoft/fluentui★ 20ksame name

    175 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use write-product-spec, diagnose-ci-failures 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

      write-product-spec

      Write a PRODUCT.md spec for a significant user-facing feature in Zap, focused on detailed behavior and validation. Use when the user asks for a product spec, desired behavior doc, or PRD, wants to define feature behavior before implementation, or when the feature is substantial or behaviorally ambiguous enough that a written spec would improve implementation or review.

      Also in 4 projects that use this

    • 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

    • 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

    • charlesmatteSkill

      write-tech-spec

      Generate a technical specification document from an existing PRD through relentless technical interview and codebase exploration. Use when user wants to write a tech spec, technical specification, technical design document, TDD (technical design doc), or go deeper on the technical details of a PRD.

      Also in 4 projects that use this

    • dekozaSkill

      fix-pr

      Repair an existing pull request's review findings and target-branch conflicts, verify the result, and update the same open PR.

      Also in 5 projects that use this

    • +2 more from zerx-lab
    • +1 more from n24q02m
  • In this repository24 other files it gives its agents.

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