agentleFS
Sign inStart free
zaxbysaucezaxbysauce/opencode-swarm/.agents/skills/pr-review-fix/SKILL.md

pr-review-fix

Skill517 starsChanged 3 days agoMITView on GitHub

Codex adapter for addressing pull request review feedback in opencode-swarm. Use when the user asks to fix PR review comments, requested changes, reviewer findings, CI-review notes, or a pasted review summary with low false-positive tolerance.

We split this skill into the rules it gives an agent

6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read ../../../.opencode/skills/swarm-pr-feedback/SKILL.md for the canonical workflow.

    line 11
  2. Distinctive:

    Treat each review item as a claim to verify against the current branch or live PR head before editing.

    line 16
  3. Very specific:

    Use the GitHub app when available, or gh, to inspect unresolved review threads and PR metadata.

    line 17
  4. Very specific:

    Use rg, file reads, and tests to classify each item as confirmed, disproved, pre-existing, or unverified.

    line 19
  5. Distinctive:

    Do not resolve GitHub review threads unless the user explicitly instructs it.

    line 21
  6. Very specific:

    When review feedback involves tests, also load $writing-tests.

    line 24

“Common” is measured: kept by at least 6 in 10 of the 3 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

PR Review Fix

Compatibility adapter. Prefer $swarm-pr-feedback for all new PR feedback work. Read ../../../.opencode/skills/swarm-pr-feedback/SKILL.md for the canonical workflow.

Codex-specific execution notes:

  • Treat each review item as a claim to verify against the current branch or live PR head before editing.
  • Use the GitHub app when available, or gh, to inspect unresolved review threads and PR metadata.
  • For bot or app reviews, inspect both the review comment and any commits the bot pushed; compare each claim against branch history and current code before classifying it.
  • Use rg, file reads, and tests to classify each item as confirmed, disproved, pre-existing, or unverified.
  • Patch only confirmed gaps unless the user explicitly asks for speculative cleanup.
  • Do not resolve GitHub review threads unless the user explicitly instructs it.
  • Load .agents/skills/commit-pr/SKILL.md before committing, pushing, or updating the PR.

When review feedback involves tests, also load $writing-tests; when it involves runtime invariants, also load $engineering-conventions.

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