AGENT SKILL

github-workflow-automation

Automate GitHub workflows with AI assistance. Includes PR reviews, issue triage, CI/CD integration, and Git operations. Use when automating GitHub workflows, setting up PR review automation, creating GitHub Actions, or triaging issues.

License 许可
MIT
最近更新
2026-10-13
Stars
★ 0
Forks
0

01 前言 Front Matter

name
github-workflow-automation
description
Automate GitHub workflows with AI assistance. Includes PR reviews, issue triage, CI/CD integration, and Git operations. Use when automating GitHub workflows, setting up PR review automation, creating GitHub Actions, or triaging issues.

03 SKILL.md 正文

🔧 GitHub Workflow Automation

Patterns for automating GitHub workflows with AI assistance, inspired by Gemini CLI and modern DevOps practices.

When to Use This Skill

Use this skill when:

  • Automating PR reviews with AI
  • Setting up issue triage automation
  • Creating GitHub Actions workflows
  • Integrating AI into CI/CD pipelines
  • Automating Git operations (rebases, cherry-picks)

1. Automated PR Review

1.1 PR Review Action

# .github/workflows/ai-review.yml
name: AI Code Review

on:
  pull_request:
    types: [opened, synchronize]

jobs:
  review:
    runs-on: ubuntu-latest
    permissions:
      contents: read
      pull-requests: write

    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Get changed files
        id: changed
        run: |
          files=$(git diff --name-only origin/${{ github.base_ref }}...HEAD)
          echo "files<<EOF" >> $GITHUB_OUTPUT
          echo "$files" >> $GITHUB_OUTPUT
          echo "EOF" >> $GITHUB_OUTPUT

      - name: Get diff
        id: diff
        run: |
          diff=$(git diff origin/${{ github.base_ref }}...HEAD)
          echo "diff<<EOF" >> $GITHUB_OUTPUT
          echo "$diff" >> $GITHUB_OUTPUT
          echo "EOF" >> $GITHUB_OUTPUT

      - name: AI Review
        uses: actions/github-script@v7
        with:
          script: |
            const { Anthropic } = require('@anthropic-ai/sdk');
            const client = new Anthropic({ apiKey: process.env.ANTHROPIC_API_KEY });

            const response = await client.messages.create({
              model: "claude-sonnet-4-6",
              max_tokens: 4096,
              messages: [{
                role: "user",
                content: `Review this PR diff and provide feedback:
                
                Changed files: ${{ steps.changed.outputs.files }}
                
                Diff:
                ${{ steps.diff.outputs.diff }}
                
                Provide:
                1. Summary of changes
                2. Potential issues or bugs
                3. Suggestions for improvement
                4. Security concerns if any
                
                Format as GitHub markdown.`
              }]
            });

            await github.rest.pulls.createReview({
              owner: context.repo.owner,
              repo: context.repo.repo,
              pull_number: context.issue.number,
              body: response.content[0].text,
              event: 'COMMENT'
            });
        env:
          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}

1.2 Review Comment Patterns

# AI Review Structure

## 📋 Summary

Brief description of what this PR does.

## ✅ What looks good

- Well-structured code
- Good test coverage
- Clear naming conventions

## ⚠️ Potential Issues

1. **Line 42**: Possible null pointer exception
   ```javascript
   // Current
   user.profile.name;
   // Suggested
   user?.profile?.name ?? "Unknown";
   ```
  1. Line 78: Consider error handling
    // Add try-catch or .catch()
    

💡 Suggestions

  • Consider extracting the validation logic into a separate function
  • Add JSDoc comments for public methods

🔒 Security Notes

  • No sensitive data exposure detected
  • API key handling looks correct

### 1.3 Focused Reviews

```yaml
# Review only specific file types
- name: Filter code files
  run: |
    files=$(git diff --name-only origin/${{ github.base_ref }}...HEAD | \
            grep -E '\.(ts|tsx|js|jsx|py|go)$' || true)
    echo "code_files=$files" >> $GITHUB_OUTPUT

# Review with context
- name: AI Review with context
  run: |
    # Include relevant context files
    context=""
    for file in ${{ steps.changed.outputs.files }}; do
      if [[ -f "$file" ]]; then
        context+="=== $file ===\n$(cat $file)\n\n"
      fi
    done

    # Send to AI with full file context

2. Issue Triage Automation

2.1 Auto-label Issues

# .github/workflows/issue-triage.yml
name: Issue Triage

on:
  issues:
    types: [opened]

jobs:
  triage:
    runs-on: ubuntu-latest
    permissions:
      issues: write

    steps:
      - name: Analyze issue
        uses: actions/github-script@v7
        with:
          script: |
            const issue = context.payload.issue;

            // Call AI to analyze
            const analysis = await analyzeIssue(issue.title, issue.body);

            // Apply labels
            const labels = [];

            if (analysis.type === 'bug') {
              labels.push('bug');
              if (analysis.severity === 'high') labels.push('priority: high');
            } else if (analysis.type === 'feature') {
              labels.push('enhancement');
            } else if (analysis.type === 'question') {
              labels.push('question');
            }

            if (analysis.area) {
              labels.push(`area: ${analysis.area}`);
            }

            await github.rest.issues.addLabels({
              owner: context.repo.owner,
              repo: context.repo.repo,
              issue_number: issue.number,
              labels: labels
            });

            // Add initial response
            if (analysis.type === 'bug' && !analysis.hasReproSteps) {
              await github.rest.issues.createComment({
                owner: context.repo.owner,
                repo: context.repo.repo,
                issue_number: issue.number,
                body: `Thanks for reporting this issue!

To help us investigate, could you please provide:
- Steps to reproduce the issue
- Expected behavior
- Actual behavior
- Environment (OS, version, etc.)

This will help us resolve your issue faster. 🙏`
              });
            }

2.2 Issue Analysis Prompt

const TRIAGE_PROMPT = `
Analyze this GitHub issue and classify it:

Title: {title}
Body: {body}

Return JSON with:
{
  "type": "bug" | "feature" | "question" | "docs" | "other",
  "severity": "low" | "medium" | "high" | "critical",
  "area": "frontend" | "backend" | "api" | "docs" | "ci" | "other",
  "summary": "one-line summary",
  "hasReproSteps": boolean,
  "isFirstContribution": boolean,
  "suggestedLabels": ["label1", "label2"],
  "suggestedAssignees": ["username"] // based on area expertise
}
`;

2.3 Stale Issue Management

# .github/workflows/stale.yml
name: Manage Stale Issues

on:
  schedule:
    - cron: "0 0 * * *" # Daily

jobs:
  stale:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/stale@v9
        with:
          stale-issue-message: |
            This issue has been automatically marked as stale because it has not had 
            recent activity. It will be closed in 14 days if no further activity occurs.

            If this issue is still relevant:
            - Add a comment with an update
            - Remove the `stale` label

            Thank you for your contributions! 🙏

          stale-pr-message: |
            This PR has been automatically marked as stale. Please update it or it 
            will be closed in 14 days.

          days-before-stale: 60
          days-before-close: 14
          stale-issue-label: "stale"
          stale-pr-label: "stale"
          exempt-issue-labels: "pinned,security,in-progress"
          exempt-pr-labels: "pinned,security"

3. CI/CD Integration

3.1 Smart Test Selection

# .github/workflows/smart-tests.yml
name: Smart Test Selection

on:
  pull_request:

jobs:
  analyze:
    runs-on: ubuntu-latest
    outputs:
      test_suites: ${{ steps.analyze.outputs.suites }}

    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Analyze changes
        id: analyze
        run: |
          # Get changed files
          changed=$(git diff --name-only origin/${{ github.base_ref }}...HEAD)

          # Determine which test suites to run
          suites="[]"

          if echo "$changed" | grep -q "^src/api/"; then
            suites=$(echo $suites | jq '. + ["api"]')
          fi

          if echo "$changed" | grep -q "^src/frontend/"; then
            suites=$(echo $suites | jq '. + ["frontend"]')
          fi

          if echo "$changed" | grep -q "^src/database/"; then
            suites=$(echo $suites | jq '. + ["database", "api"]')
          fi

          # If nothing specific, run all
          if [ "$suites" = "[]" ]; then
            suites='["all"]'
          fi

          echo "suites=$suites" >> $GITHUB_OUTPUT

  test:
    needs: analyze
    runs-on: ubuntu-latest
    strategy:
      matrix:
        suite: ${{ fromJson(needs.analyze.outputs.test_suites) }}

    steps:
      - uses: actions/checkout@v4

      - name: Run tests
        run: |
          if [ "${{ matrix.suite }}" = "all" ]; then
            npm test
          else
            npm test -- --suite ${{ matrix.suite }}
          fi

3.2 Deployment with AI Validation

# .github/workflows/deploy.yml
name: Deploy with AI Validation

on:
  push:
    branches: [main]

jobs:
  validate:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - name: Get deployment changes
        id: changes
        run: |
          # Get commits since last deployment
          last_deploy=$(git describe --tags --abbrev=0 2>/dev/null || echo "")
          if [ -n "$last_deploy" ]; then
            changes=$(git log --oneline $last_deploy..HEAD)
          else
            changes=$(git log --oneline -10)
          fi
          echo "changes<<EOF" >> $GITHUB_OUTPUT
          echo "$changes" >> $GITHUB_OUTPUT
          echo "EOF" >> $GITHUB_OUTPUT

      - name: AI Risk Assessment
        id: assess
        uses: actions/github-script@v7
        with:
          script: |
            // Analyze changes for deployment risk
            const prompt = `
            Analyze these changes for deployment risk:

            ${process.env.CHANGES}

            Return JSON:
            {
              "riskLevel": "low" | "medium" | "high",
              "concerns": ["concern1", "concern2"],
              "recommendations": ["rec1", "rec2"],
              "requiresManualApproval": boolean
            }
            `;

            // Call AI and parse response
            const analysis = await callAI(prompt);

            if (analysis.riskLevel === 'high') {
              core.setFailed('High-risk deployment detected. Manual review required.');
            }

            return analysis;
        env:
          CHANGES: ${{ steps.changes.outputs.changes }}

  deploy:
    needs: validate
    runs-on: ubuntu-latest
    environment: production
    steps:
      - name: Deploy
        run: |
          echo "Deploying to production..."
          # Deployment commands here

3.3 Rollback Automation

# .github/workflows/rollback.yml
name: Automated Rollback

on:
  workflow_dispatch:
    inputs:
      reason:
        description: "Reason for rollback"
        required: true

jobs:
  rollback:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Find last stable version
        id: stable
        run: |
          # Find last successful deployment
          stable=$(git tag -l 'v*' --sort=-version:refname | head -1)
          echo "version=$stable" >> $GITHUB_OUTPUT

      - name: Rollback
        run: |
          git checkout ${{ steps.stable.outputs.version }}
          # Deploy stable version
          npm run deploy

      - name: Notify team
        uses: slackapi/slack-github-action@v1
        with:
          payload: |
            {
              "text": "🔄 Production rolled back to ${{ steps.stable.outputs.version }}",
              "blocks": [
                {
                  "type": "section",
                  "text": {
                    "type": "mrkdwn",
                    "text": "*Rollback executed*\n• Version: `${{ steps.stable.outputs.version }}`\n• Reason: ${{ inputs.reason }}\n• Triggered by: ${{ github.actor }}"
                  }
                }
              ]
            }

4. Git Operations

4.1 Automated Rebasing

# .github/workflows/auto-rebase.yml
name: Auto Rebase

on:
  issue_comment:
    types: [created]

jobs:
  rebase:
    if: github.event.issue.pull_request && contains(github.event.comment.body, '/rebase')
    runs-on: ubuntu-latest

    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0
          token: ${{ secrets.GITHUB_TOKEN }}

      - name: Setup Git
        run: |
          git config user.name "github-actions[bot]"
          git config user.email "github-actions[bot]@users.noreply.github.com"

      - name: Rebase PR
        run: |
          # Fetch PR branch
          gh pr checkout ${{ github.event.issue.number }}

          # Rebase onto main
          git fetch origin main
          git rebase origin/main

          # Force push
          git push --force-with-lease
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}

      - name: Comment result
        uses: actions/github-script@v7
        with:
          script: |
            github.rest.issues.createComment({
              owner: context.repo.owner,
              repo: context.repo.repo,
              issue_number: context.issue.number,
              body: '✅ Successfully rebased onto main!'
            })

4.2 Smart Cherry-Pick

// AI-assisted cherry-pick that handles conflicts
async function smartCherryPick(commitHash: string, targetBranch: string) {
  // Get commit info
  const commitInfo = await exec(`git show ${commitHash} --stat`);

  // Check for potential conflicts
  const targetDiff = await exec(
    `git diff ${targetBranch}...HEAD -- ${affectedFiles}`
  );

  // AI analysis
  const analysis = await ai.analyze(`
    I need to cherry-pick this commit to ${targetBranch}:
    
    ${commitInfo}
    
    Current state of affected files on ${targetBranch}:
    ${targetDiff}
    
    Will there be conflicts? If so, suggest resolution strategy.
  `);

  if (analysis.willConflict) {
    // Create branch for manual resolution
    await exec(
      `git checkout -b cherry-pick-${commitHash.slice(0, 7)} ${targetBranch}`
    );
    const result = await exec(`git cherry-pick ${commitHash}`, {
      allowFail: true,
    });

    if (result.failed) {
      // AI-assisted conflict resolution
      const conflicts = await getConflicts();
      for (const conflict of conflicts) {
        const resolution = await ai.resolveConflict(conflict);
        await applyResolution(conflict.file, resolution);
      }
    }
  } else {
    await exec(`git checkout ${targetBranch}`);
    await exec(`git cherry-pick ${commitHash}`);
  }
}

4.3 Branch Cleanup

# .github/workflows/branch-cleanup.yml
name: Branch Cleanup

on:
  schedule:
    - cron: '0 0 * * 0'  # Weekly
  workflow_dispatch:

jobs:
  cleanup:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Find stale branches
        id: stale
        run: |
          # Branches not updated in 30 days
          stale=$(git for-each-ref --sort=-committerdate refs/remotes/origin \
            --format='%(refname:short) %(committerdate:relative)' | \
            grep -E '[3-9][0-9]+ days|[0-9]+ months|[0-9]+ years' | \
            grep -v 'origin/main\|origin/develop' | \
            cut -d' ' -f1 | sed 's|origin/||')

          echo "branches<<EOF" >> $GITHUB_OUTPUT
          echo "$stale" >> $GITHUB_OUTPUT
          echo "EOF" >> $GITHUB_OUTPUT

      - name: Create cleanup PR
        if: steps.stale.outputs.branches != ''
        uses: actions/github-script@v7
        with:
          script: |
            const branches = `${{ steps.stale.outputs.branches }}`.split('\n').filter(Boolean);

            const body = `## 🧹 Stale Branch Cleanup

The following branches haven't been updated in over 30 days:

${branches.map(b => `- \`${b}\``).join('\n')}

### Actions:
- [ ] Review each branch
- [ ] Delete branches that are no longer needed
- Comment \`/keep branch-name\` to preserve specific branches
`;

            await github.rest.issues.create({
              owner: context.repo.owner,
              repo: context.repo.repo,
              title: 'Stale Branch Cleanup',
              body: body,
              labels: ['housekeeping']
            });

5. On-Demand Assistance

5.1 @mention Bot

# .github/workflows/mention-bot.yml
name: AI Mention Bot

on:
  issue_comment:
    types: [created]
  pull_request_review_comment:
    types: [created]

jobs:
  respond:
    if: contains(github.event.comment.body, '@ai-helper')
    runs-on: ubuntu-latest

    steps:
      - uses: actions/checkout@v4

      - name: Extract question
        id: question
        run: |
          # Extract text after @ai-helper
          question=$(echo "${{ github.event.comment.body }}" | sed 's/.*@ai-helper//')
          echo "question=$question" >> $GITHUB_OUTPUT

      - name: Get context
        id: context
        run: |
          if [ "${{ github.event.issue.pull_request }}" != "" ]; then
            # It's a PR - get diff
            gh pr diff ${{ github.event.issue.number }} > context.txt
          else
            # It's an issue - get description
            gh issue view ${{ github.event.issue.number }} --json body -q .body > context.txt
          fi
          echo "context=$(cat context.txt)" >> $GITHUB_OUTPUT
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}

      - name: AI Response
        uses: actions/github-script@v7
        with:
          script: |
            const response = await ai.chat(`
              Context: ${process.env.CONTEXT}
              
              Question: ${process.env.QUESTION}
              
              Provide a helpful, specific answer. Include code examples if relevant.
            `);

            await github.rest.issues.createComment({
              owner: context.repo.owner,
              repo: context.repo.repo,
              issue_number: context.issue.number,
              body: response
            });
        env:
          CONTEXT: ${{ steps.context.outputs.context }}
          QUESTION: ${{ steps.question.outputs.question }}

5.2 Command Patterns

## Available Commands

| Command              | Description                 |
| :------------------- | :-------------------------- |
| `@ai-helper explain` | Explain the code in this PR |
| `@ai-helper review`  | Request AI code review      |
| `@ai-helper fix`     | Suggest fixes for issues    |
| `@ai-helper test`    | Generate test cases         |
| `@ai-helper docs`    | Generate documentation      |
| `/rebase`            | Rebase PR onto main         |
| `/update`            | Update PR branch from main  |
| `/approve`           | Mark as approved by bot     |
| `/label bug`         | Add 'bug' label             |
| `/assign @user`      | Assign to user              |

6. Repository Configuration

6.1 CODEOWNERS

# .github/CODEOWNERS

# Global owners
* @org/core-team

# Frontend
/src/frontend/ @org/frontend-team
*.tsx @org/frontend-team
*.css @org/frontend-team

# Backend
/src/api/ @org/backend-team
/src/database/ @org/backend-team

# Infrastructure
/.github/ @org/devops-team
/terraform/ @org/devops-team
Dockerfile @org/devops-team

# Docs
/docs/ @org/docs-team
*.md @org/docs-team

# Security-sensitive
/src/auth/ @org/security-team
/src/crypto/ @org/security-team

6.2 Branch Protection

# Set up via GitHub API
- name: Configure branch protection
  uses: actions/github-script@v7
  with:
    script: |
      await github.rest.repos.updateBranchProtection({
        owner: context.repo.owner,
        repo: context.repo.repo,
        branch: 'main',
        required_status_checks: {
          strict: true,
          contexts: ['test', 'lint', 'ai-review']
        },
        enforce_admins: true,
        required_pull_request_reviews: {
          required_approving_review_count: 1,
          require_code_owner_reviews: true,
          dismiss_stale_reviews: true
        },
        restrictions: null,
        required_linear_history: true,
        allow_force_pushes: false,
        allow_deletions: false
      });

Best Practices

Security

  • [ ] Store API keys in GitHub Secrets
  • [ ] Use minimal permissions in workflows
  • [ ] Validate all inputs
  • [ ] Don't expose sensitive data in logs

Performance

  • [ ] Cache dependencies
  • [ ] Use matrix builds for parallel testing
  • [ ] Skip unnecessary jobs with path filters
  • [ ] Use self-hosted runners for heavy workloads

Reliability

  • [ ] Add timeouts to jobs
  • [ ] Handle rate limits gracefully
  • [ ] Implement retry logic
  • [ ] Have rollback procedures

Resources

04 同仓库更多 Skills

marnixGeerkens
marnixGeerkens/rocketlauncher-claude-code

zapier-make-patterns

No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points. This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power

★ 0
marnixGeerkens
marnixGeerkens/rocketlauncher-claude-code

yeet

Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).

★ 0
marnixGeerkens
marnixGeerkens/rocketlauncher-claude-code

workflow-automation

Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workflows resume exactly where they left off. This skill covers the platforms (n8n, Temporal, Inngest) and patterns (sequential, parallel, orchestrator-worker) that turn brittle scripts into production-grade automation. Key insight: The platforms make different tradeoffs. n8n optimizes for accessibility

★ 0
marnixGeerkens
marnixGeerkens/rocketlauncher-claude-code

trigger-dev

Trigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and TypeScript-first design. Use when: trigger.dev, trigger dev, background task, ai background job, long running task.

★ 0
marnixGeerkens
marnixGeerkens/rocketlauncher-claude-code

slack-automation

Automate Slack workspace operations including messaging, search, channel management, and reaction workflows through Composio's Slack toolkit.

★ 0
marnixGeerkens
marnixGeerkens/rocketlauncher-claude-code

rote

Compile a proven agent skill (a SKILL.md plus references) into a deterministic pipeline that runs without an LLM in the loop, then serve it back to Claude as an MCP tool. Use when: rote, compile this skill, turn this skill into a workflow, make this skill deterministic, make this skill cheaper or faster, harden this skill for production, run this skill as a background job.

★ 0