agentleFS
SkyWalker2506SkyWalker2506/ccplugin-ai-review/skills/ai-review/SKILL.md

ai-review

Skill0 starsChanged 6 months agoMITView on GitHub

This skill should be used when the user asks to "review a PR", "code review", "AI review", "check the pull request", or asks about automated review via OpenRouter or Gemma. Also activates when setting up GitHub Actions for PR review.

  • Reads credentials

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    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. Very specific:

    Add .github/workflows/ai-review.yml to your repo (also available in this plugin repo):

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

AI PR Review Skill

Automated pull request review using OpenRouter free models.

How It Works

  1. GitHub Action triggers on every PR open or sync
  2. Gets the PR diff via gh pr diff (truncated at 8000 chars)
  3. Sends to OpenRouter (primary: Gemma 3 27B Free, fallback: Mistral 7B Free) for analysis
  4. Posts structured review as PR comment (Summary / Issues / Suggestions)

Models

RoleModel IDNotes
Primarygoogle/gemma-3-27b-it:freeBest quality, try first
Fallbackmistralai/mistral-7b-instruct:freeUsed if primary is at capacity

Both models are free-tier on OpenRouter. If both are unavailable, the workflow exits with a clear error message.

Setup

Requirements

  • OPENROUTER_API_KEY in ~/.claude/secrets/secrets.env
  • GH_TOKEN or GITHUB_TOKEN with PR write permissions
  • gh CLI installed

GitHub Action Setup

Add .github/workflows/ai-review.yml to your repo (also available in this plugin repo):

name: AI Code Review
on:
  pull_request:
    types: [opened, synchronize]
jobs:
  review:
    runs-on: ubuntu-latest
    permissions:
      pull-requests: write
    steps:
      - uses: actions/checkout@v4

      - name: Validate API key
        run: |
          if [ -z "$OPENROUTER_API_KEY" ]; then
            echo "::error::OPENROUTER_API_KEY secret is not set."
            exit 1
          fi
        env:
          OPENROUTER_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}

      - name: Get PR diff
        id: diff
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: |
          PR_DIFF=$(gh pr diff ${{ github.event.pull_request.number }} 2>/dev/null || echo "")
          if [ -z "$PR_DIFF" ]; then
            echo "skip=true" >> "$GITHUB_OUTPUT"
            exit 0
          fi
          PR_DIFF_TRUNCATED="${PR_DIFF:0:8000}"
          { echo "diff<<EOF_DIFF"; echo "$PR_DIFF_TRUNCATED"; echo "EOF_DIFF"; } >> "$GITHUB_OUTPUT"
          echo "skip=false" >> "$GITHUB_OUTPUT"

      - name: AI Review via OpenRouter
        if: steps.diff.outputs.skip == 'false'
        env:
          OPENROUTER_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          PR_DIFF: ${{ steps.diff.outputs.diff }}
          PR_NUMBER: ${{ github.event.pull_request.number }}
          PR_TITLE: ${{ github.event.pull_request.title }}
        run: |
          PRIMARY_MODEL="google/gemma-3-27b-it:free"
          FALLBACK_MODEL="mistralai/mistral-7b-instruct:free"

          PROMPT="Review PR #${PR_NUMBER}: ${PR_TITLE}\n\nDiff:\n${PR_DIFF}\n\nProvide:\n## Summary\n## Issues\n## Suggestions"

          for MODEL in "$PRIMARY_MODEL" "$FALLBACK_MODEL"; do
            PAYLOAD=$(python3 -c "
          import json,sys
          print(json.dumps({'model':'$MODEL','messages':[{'role':'user','content':sys.stdin.read()}],'max_tokens':1024}))" <<< "$PROMPT")
            RESPONSE=$(curl -s -w "\n%{http_code}" \
              -X POST https://openrouter.ai/api/v1/chat/completions \
              -H "Authorization: Bearer $OPENROUTER_API_KEY" \
              -H "Content-Type: application/json" \
              -d "$PAYLOAD")
            HTTP_CODE=$(echo "$RESPONSE" | tail -n1)
            BODY=$(echo "$RESPONSE" | head -n -1)
            if [ "$HTTP_CODE" = "200" ]; then
              REVIEW=$(echo "$BODY" | python3 -c "import json,sys; print(json.load(sys.stdin)['choices'][0]['message']['content'])")
              gh pr comment "$PR_NUMBER" --body "## 🤖 AI Code Review\n\n${REVIEW}\n\n---\n_Powered by ccplugin-ai-review · Free via OpenRouter_"
              exit 0
            fi
            echo "Model $MODEL returned HTTP $HTTP_CODE, trying next..."
          done
          echo "::error::All OpenRouter models unavailable."
          exit 1

Cost

$0 — uses OpenRouter free tier (Gemma 3 27B Free, Mistral 7B Free fallback).

Download now (ZIP)

  • Other versions5 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 5

    1. PaddlePaddle/Paddle★ 24ksame name
    2. dgilford/ai-science-toolkit★ 80same name
    3. tingyulu/MyR2D2★ 18same name
    4. eins78/agent-skills★ 2same name
    5. SanHsien/agent-astromech★ 0same name

    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 pickup.

    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.
    • HermeticOrmusSkill

      pickup

      Read a HANDOFF.md and restore session context. The entry ritual -- the opposite of /handoff. Use at the start of a new session after a handoff, machine switch, or context clear.

      Also in 3 projects that use this

  • In this repositoryOne other file 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.