[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AEK1MYDXMM5B648M0CSPGT":3,"skill-same:01M6AEK1MYDXMM5B648M0CSPGT":106},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":29,"publishedAt":55,"linkOnly":56,"markdownContent":57,"markdownBody":58,"frontMatter":59,"refName":60,"commitSha":61,"skillDirectory":62,"forksCount":63,"repositoryHtmlUrl":64,"repositoryHomepageUrl":65,"ownerHtmlUrl":66,"ownerBlogUrl":67,"ownerDescription":68,"updatedAt":69,"install":70,"resources":83},"01M6AEK1MYDXMM5B648M0CSPGT","github-actions-creator",null,"Use when the user wants to create, generate, or set up a GitHub Actions workflow. Handles CI\u002FCD pipelines, testing, deployment, linting, security scanning, release automation, Docker builds, scheduled tasks, and any custom workflow for any language or framework.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33332,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Fgithub-actions-creator\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54],"github","creator","github actions creator","github actions","actions","SET","when","scheduled","testing","github actions workflow","CI\u002FCD","linting","up","scanning","docker","automation","security","ci","workflow","framework","release","generate","create","tasks","deployment","2026-11-10 10:12:30",false,"---\nname: github-actions-creator\ndescription: \"Use when the user wants to create, generate, or set up a GitHub Actions workflow. Handles CI\u002FCD pipelines, testing, deployment, linting, security scanning, release automation, Docker builds, scheduled tasks, and any custom workflow for any language or framework.\"\n---\n\n# GitHub Actions Creator\n\nYou are an expert at creating GitHub Actions workflows. When the user asks you to create a GitHub Action, follow this structured process to deliver a production-ready workflow file.\n\n## Workflow Creation Process\n\n### Step 1: Analyze the Project\n\nBefore writing any YAML, scan the project to understand the stack:\n\n1. **Check for language\u002Fframework indicators:**\n   - `package.json` → Node.js (check for React, Next.js, Vue, Angular, Svelte, etc.)\n   - `requirements.txt` \u002F `pyproject.toml` \u002F `setup.py` → Python\n   - `go.mod` → Go\n   - `Cargo.toml` → Rust\n   - `pom.xml` \u002F `build.gradle` → Java\u002FKotlin\n   - `Gemfile` → Ruby\n   - `composer.json` → PHP\n   - `pubspec.yaml` → Dart\u002FFlutter\n   - `Package.swift` → Swift\n   - `*.csproj` \u002F `*.sln` → .NET\n\n2. **Check for existing CI\u002FCD:**\n   - `.github\u002Fworkflows\u002F` → existing workflows (avoid conflicts)\n   - `Dockerfile` → container builds available\n   - `docker-compose.yml` → multi-service setup\n   - `vercel.json` \u002F `netlify.toml` → deployment targets\n   - `terraform\u002F` \u002F `pulumi\u002F` → infrastructure as code\n\n3. **Check for tooling:**\n   - `.eslintrc*` \u002F `eslint.config.*` → ESLint configured\n   - `prettier*` → Prettier configured\n   - `jest.config*` \u002F `vitest.config*` \u002F `pytest.ini` → test framework\n   - `.env.example` → environment variables needed\n   - `Makefile` → build commands available\n\n### Step 2: Ask Clarifying Questions (if needed)\n\nIf the user's request is ambiguous, ask ONE focused question. Common clarifications:\n\n- **\"Create a CI pipeline\"** → \"Should it run tests only, or also lint and type-check?\"\n- **\"Add deployment\"** → \"Where does this deploy? (Vercel, AWS, GCP, Docker Hub, etc.)\"\n- **\"Set up tests\"** → \"Should tests run on PR only, or also on push to main?\"\n\nIf the intent is clear, skip this step and proceed.\n\n### Step 3: Generate the Workflow\n\nCreate the `.github\u002Fworkflows\u002F{name}.yml` file following these rules:\n\n#### File Naming\n- Use descriptive kebab-case names: `ci.yml`, `deploy-production.yml`, `release.yml`\n- For simple CI: `ci.yml`\n- For deployment: `deploy.yml` or `deploy-{target}.yml`\n- For scheduled tasks: `scheduled-{task}.yml`\n\n#### YAML Structure Rules\n\n```yaml\nname: Human-readable name        # Always include\n\non:                               # Use the most specific triggers\n  push:\n    branches: [main]              # Specify branches explicitly\n    paths-ignore:                 # Skip docs-only changes when appropriate\n      - '**.md'\n      - 'docs\u002F**'\n  pull_request:\n    branches: [main]\n\npermissions:                      # Always set minimal permissions\n  contents: read\n\nconcurrency:                      # Prevent duplicate runs on PRs\n  group: ${{ github.workflow }}-${{ github.ref }}\n  cancel-in-progress: true\n\njobs:\n  job-name:\n    runs-on: ubuntu-latest        # Default to ubuntu-latest\n    timeout-minutes: 15           # Always set a timeout\n    steps:\n      - uses: actions\u002Fcheckout@v4 # Always pin to major version\n```\n\n## Core Patterns by Use Case\n\n### CI (Test + Lint)\n\n**Trigger:** `pull_request` + `push` to main\n**Jobs:** lint, test (parallel when possible)\n**Key features:** dependency caching, matrix testing for multiple versions\n\n### Deployment\n\n**Trigger:** `push` to main (or release tags)\n**Jobs:** test → build → deploy (sequential with `needs`)\n**Key features:** environment protection, secrets for credentials, status checks\n\n### Release \u002F Publish\n\n**Trigger:** `push` tags matching `v*` or `workflow_dispatch`\n**Jobs:** test → build → publish → create GitHub Release\n**Key features:** changelog generation, artifact upload, npm\u002FPyPI\u002FDocker publish\n\n### Scheduled Tasks\n\n**Trigger:** `schedule` with cron expression\n**Jobs:** single job with the task\n**Key features:** `workflow_dispatch` for manual trigger too, failure notifications\n\n### Security Scanning\n\n**Trigger:** `pull_request` + `schedule` (weekly)\n**Jobs:** dependency audit, SAST, secret scanning\n**Key features:** SARIF upload to GitHub Security tab, fail on critical\n\n### Docker Build & Push\n\n**Trigger:** `push` to main + tags\n**Jobs:** build → push to registry\n**Key features:** multi-platform builds, layer caching, image tagging strategy\n\n## Essential Actions Reference\n\n### Setup Actions (always pin to major version)\n| Action | Purpose |\n|--------|---------|\n| `actions\u002Fcheckout@v4` | Clone repository |\n| `actions\u002Fsetup-node@v4` | Node.js with caching |\n| `actions\u002Fsetup-python@v5` | Python with caching |\n| `actions\u002Fsetup-go@v5` | Go with caching |\n| `actions\u002Fsetup-java@v4` | Java\u002FKotlin |\n| `dtolnay\u002Frust-toolchain@stable` | Rust toolchain |\n| `ruby\u002Fsetup-ruby@v1` | Ruby with bundler cache |\n| `actions\u002Fsetup-dotnet@v4` | .NET SDK |\n\n### Build & Deploy Actions\n| Action | Purpose |\n|--------|---------|\n| `docker\u002Fbuild-push-action@v6` | Docker multi-platform builds |\n| `docker\u002Flogin-action@v3` | Docker registry authentication |\n| `aws-actions\u002Fconfigure-aws-credentials@v4` | AWS authentication |\n| `google-github-actions\u002Fauth@v2` | GCP authentication |\n| `azure\u002Flogin@v2` | Azure authentication |\n| `cloudflare\u002Fwrangler-action@v3` | Cloudflare Workers deploy |\n| `amondnet\u002Fvercel-action@v25` | Vercel deployment |\n\n### Quality & Security Actions\n| Action | Purpose |\n|--------|---------|\n| `github\u002Fcodeql-action\u002Fanalyze@v3` | CodeQL SAST scanning |\n| `aquasecurity\u002Ftrivy-action@master` | Container vulnerability scan |\n| `codecov\u002Fcodecov-action@v4` | Coverage upload |\n| `actions\u002Fdependency-review-action@v4` | Dependency audit on PRs |\n\n### Utility Actions\n| Action | Purpose |\n|--------|---------|\n| `actions\u002Fcache@v4` | Generic caching |\n| `actions\u002Fupload-artifact@v4` | Store build artifacts |\n| `actions\u002Fdownload-artifact@v4` | Retrieve artifacts between jobs |\n| `softprops\u002Faction-gh-release@v2` | Create GitHub Releases |\n| `slackapi\u002Fslack-github-action@v2` | Slack notifications |\n| `peter-evans\u002Fcreate-pull-request@v7` | Automated PR creation |\n\n## Security Best Practices (ALWAYS follow)\n\n1. **Minimal permissions:** Always declare `permissions` at workflow or job level\n2. **Pin actions to major version:** Use `@v4` not `@main` or full SHA for readability\n3. **Never echo secrets:** Secrets are masked but avoid `echo ${{ secrets.X }}`\n4. **Use environments:** For production deploys, use GitHub Environments with protection rules\n5. **Validate inputs:** For `workflow_dispatch`, validate input values\n6. **Avoid script injection:** Never use `${{ github.event.*.body }}` directly in `run:` — pass via environment variables\n7. **Use GITHUB_TOKEN:** Prefer `${{ secrets.GITHUB_TOKEN }}` over PATs when possible\n8. **Concurrency controls:** Use `concurrency` to prevent parallel deploys\n\n```yaml\n# WRONG - script injection vulnerability\n- run: echo \"${{ github.event.issue.title }}\"\n\n# CORRECT - pass through environment variable\n- run: echo \"$ISSUE_TITLE\"\n  env:\n    ISSUE_TITLE: ${{ github.event.issue.title }}\n```\n\n## Caching Strategies\n\n### Node.js\n```yaml\n- uses: actions\u002Fsetup-node@v4\n  with:\n    node-version: 20\n    cache: 'npm'  # or 'yarn' or 'pnpm'\n```\n\n### Python\n```yaml\n- uses: actions\u002Fsetup-python@v5\n  with:\n    python-version: '3.12'\n    cache: 'pip'  # or 'poetry' or 'pipenv'\n```\n\n### Go\n```yaml\n- uses: actions\u002Fsetup-go@v5\n  with:\n    go-version: '1.22'\n    cache: true\n```\n\n### Rust\n```yaml\n- uses: actions\u002Fcache@v4\n  with:\n    path: |\n      ~\u002F.cargo\u002Fbin\u002F\n      ~\u002F.cargo\u002Fregistry\u002Findex\u002F\n      ~\u002F.cargo\u002Fregistry\u002Fcache\u002F\n      target\u002F\n    key: ${{ runner.os }}-cargo-${{ hashFiles('**\u002FCargo.lock') }}\n```\n\n### Docker\n```yaml\n- uses: docker\u002Fbuild-push-action@v6\n  with:\n    cache-from: type=gha\n    cache-to: type=gha,mode=max\n```\n\n## Matrix Testing Patterns\n\n### Multiple Node.js versions\n```yaml\nstrategy:\n  matrix:\n    node-version: [18, 20, 22]\n  fail-fast: false\n```\n\n### Multiple OS\n```yaml\nstrategy:\n  matrix:\n    os: [ubuntu-latest, macos-latest, windows-latest]\nruns-on: ${{ matrix.os }}\n```\n\n### Complex matrix with exclusions\n```yaml\nstrategy:\n  matrix:\n    os: [ubuntu-latest, windows-latest]\n    node-version: [18, 20]\n    exclude:\n      - os: windows-latest\n        node-version: 18\n```\n\n## Cron Syntax Quick Reference\n\n| Schedule | Cron |\n|----------|------|\n| Every hour | `0 * * * *` |\n| Daily at midnight UTC | `0 0 * * *` |\n| Weekdays at 9am UTC | `0 9 * * 1-5` |\n| Weekly on Sunday | `0 0 * * 0` |\n| Monthly 1st | `0 0 1 * *` |\n\n## Output Format\n\nAfter creating the workflow file, provide:\n\n1. **What the workflow does** — one-paragraph summary\n2. **Required secrets** — list any secrets the user needs to configure in Settings > Secrets\n3. **Required permissions** — if the workflow needs non-default repository permissions\n4. **How to test** — how to trigger the workflow (push, create PR, manual dispatch)\n\n## Common Patterns to Combine\n\nWhen the user asks for something generic like \"set up CI\u002FCD\", create a single workflow with multiple jobs:\n\n```yaml\njobs:\n  lint:        # Fast feedback\n  test:        # Core validation\n  build:       # Ensure it compiles\u002Fbundles\n    needs: [lint, test]\n  deploy:      # Only after everything passes\n    needs: build\n    if: github.ref == 'refs\u002Fheads\u002Fmain'\n```\n\nKeep workflows focused. Prefer one workflow per concern over one massive workflow, unless the jobs are tightly coupled.\n","# GitHub Actions Creator\n\nYou are an expert at creating GitHub Actions workflows. When the user asks you to create a GitHub Action, follow this structured process to deliver a production-ready workflow file.\n\n## Workflow Creation Process\n\n### Step 1: Analyze the Project\n\nBefore writing any YAML, scan the project to understand the stack:\n\n1. **Check for language\u002Fframework indicators:**\n   - `package.json` → Node.js (check for React, Next.js, Vue, Angular, Svelte, etc.)\n   - `requirements.txt` \u002F `pyproject.toml` \u002F `setup.py` → Python\n   - `go.mod` → Go\n   - `Cargo.toml` → Rust\n   - `pom.xml` \u002F `build.gradle` → Java\u002FKotlin\n   - `Gemfile` → Ruby\n   - `composer.json` → PHP\n   - `pubspec.yaml` → Dart\u002FFlutter\n   - `Package.swift` → Swift\n   - `*.csproj` \u002F `*.sln` → .NET\n\n2. **Check for existing CI\u002FCD:**\n   - `.github\u002Fworkflows\u002F` → existing workflows (avoid conflicts)\n   - `Dockerfile` → container builds available\n   - `docker-compose.yml` → multi-service setup\n   - `vercel.json` \u002F `netlify.toml` → deployment targets\n   - `terraform\u002F` \u002F `pulumi\u002F` → infrastructure as code\n\n3. **Check for tooling:**\n   - `.eslintrc*` \u002F `eslint.config.*` → ESLint configured\n   - `prettier*` → Prettier configured\n   - `jest.config*` \u002F `vitest.config*` \u002F `pytest.ini` → test framework\n   - `.env.example` → environment variables needed\n   - `Makefile` → build commands available\n\n### Step 2: Ask Clarifying Questions (if needed)\n\nIf the user's request is ambiguous, ask ONE focused question. Common clarifications:\n\n- **\"Create a CI pipeline\"** → \"Should it run tests only, or also lint and type-check?\"\n- **\"Add deployment\"** → \"Where does this deploy? (Vercel, AWS, GCP, Docker Hub, etc.)\"\n- **\"Set up tests\"** → \"Should tests run on PR only, or also on push to main?\"\n\nIf the intent is clear, skip this step and proceed.\n\n### Step 3: Generate the Workflow\n\nCreate the `.github\u002Fworkflows\u002F{name}.yml` file following these rules:\n\n#### File Naming\n- Use descriptive kebab-case names: `ci.yml`, `deploy-production.yml`, `release.yml`\n- For simple CI: `ci.yml`\n- For deployment: `deploy.yml` or `deploy-{target}.yml`\n- For scheduled tasks: `scheduled-{task}.yml`\n\n#### YAML Structure Rules\n\n```yaml\nname: Human-readable name        # Always include\n\non:                               # Use the most specific triggers\n  push:\n    branches: [main]              # Specify branches explicitly\n    paths-ignore:                 # Skip docs-only changes when appropriate\n      - '**.md'\n      - 'docs\u002F**'\n  pull_request:\n    branches: [main]\n\npermissions:                      # Always set minimal permissions\n  contents: read\n\nconcurrency:                      # Prevent duplicate runs on PRs\n  group: ${{ github.workflow }}-${{ github.ref }}\n  cancel-in-progress: true\n\njobs:\n  job-name:\n    runs-on: ubuntu-latest        # Default to ubuntu-latest\n    timeout-minutes: 15           # Always set a timeout\n    steps:\n      - uses: actions\u002Fcheckout@v4 # Always pin to major version\n```\n\n## Core Patterns by Use Case\n\n### CI (Test + Lint)\n\n**Trigger:** `pull_request` + `push` to main\n**Jobs:** lint, test (parallel when possible)\n**Key features:** dependency caching, matrix testing for multiple versions\n\n### Deployment\n\n**Trigger:** `push` to main (or release tags)\n**Jobs:** test → build → deploy (sequential with `needs`)\n**Key features:** environment protection, secrets for credentials, status checks\n\n### Release \u002F Publish\n\n**Trigger:** `push` tags matching `v*` or `workflow_dispatch`\n**Jobs:** test → build → publish → create GitHub Release\n**Key features:** changelog generation, artifact upload, npm\u002FPyPI\u002FDocker publish\n\n### Scheduled Tasks\n\n**Trigger:** `schedule` with cron expression\n**Jobs:** single job with the task\n**Key features:** `workflow_dispatch` for manual trigger too, failure notifications\n\n### Security Scanning\n\n**Trigger:** `pull_request` + `schedule` (weekly)\n**Jobs:** dependency audit, SAST, secret scanning\n**Key features:** SARIF upload to GitHub Security tab, fail on critical\n\n### Docker Build & Push\n\n**Trigger:** `push` to main + tags\n**Jobs:** build → push to registry\n**Key features:** multi-platform builds, layer caching, image tagging strategy\n\n## Essential Actions Reference\n\n### Setup Actions (always pin to major version)\n| Action | Purpose |\n|--------|---------|\n| `actions\u002Fcheckout@v4` | Clone repository |\n| `actions\u002Fsetup-node@v4` | Node.js with caching |\n| `actions\u002Fsetup-python@v5` | Python with caching |\n| `actions\u002Fsetup-go@v5` | Go with caching |\n| `actions\u002Fsetup-java@v4` | Java\u002FKotlin |\n| `dtolnay\u002Frust-toolchain@stable` | Rust toolchain |\n| `ruby\u002Fsetup-ruby@v1` | Ruby with bundler cache |\n| `actions\u002Fsetup-dotnet@v4` | .NET SDK |\n\n### Build & Deploy Actions\n| Action | Purpose |\n|--------|---------|\n| `docker\u002Fbuild-push-action@v6` | Docker multi-platform builds |\n| `docker\u002Flogin-action@v3` | Docker registry authentication |\n| `aws-actions\u002Fconfigure-aws-credentials@v4` | AWS authentication |\n| `google-github-actions\u002Fauth@v2` | GCP authentication |\n| `azure\u002Flogin@v2` | Azure authentication |\n| `cloudflare\u002Fwrangler-action@v3` | Cloudflare Workers deploy |\n| `amondnet\u002Fvercel-action@v25` | Vercel deployment |\n\n### Quality & Security Actions\n| Action | Purpose |\n|--------|---------|\n| `github\u002Fcodeql-action\u002Fanalyze@v3` | CodeQL SAST scanning |\n| `aquasecurity\u002Ftrivy-action@master` | Container vulnerability scan |\n| `codecov\u002Fcodecov-action@v4` | Coverage upload |\n| `actions\u002Fdependency-review-action@v4` | Dependency audit on PRs |\n\n### Utility Actions\n| Action | Purpose |\n|--------|---------|\n| `actions\u002Fcache@v4` | Generic caching |\n| `actions\u002Fupload-artifact@v4` | Store build artifacts |\n| `actions\u002Fdownload-artifact@v4` | Retrieve artifacts between jobs |\n| `softprops\u002Faction-gh-release@v2` | Create GitHub Releases |\n| `slackapi\u002Fslack-github-action@v2` | Slack notifications |\n| `peter-evans\u002Fcreate-pull-request@v7` | Automated PR creation |\n\n## Security Best Practices (ALWAYS follow)\n\n1. **Minimal permissions:** Always declare `permissions` at workflow or job level\n2. **Pin actions to major version:** Use `@v4` not `@main` or full SHA for readability\n3. **Never echo secrets:** Secrets are masked but avoid `echo ${{ secrets.X }}`\n4. **Use environments:** For production deploys, use GitHub Environments with protection rules\n5. **Validate inputs:** For `workflow_dispatch`, validate input values\n6. **Avoid script injection:** Never use `${{ github.event.*.body }}` directly in `run:` — pass via environment variables\n7. **Use GITHUB_TOKEN:** Prefer `${{ secrets.GITHUB_TOKEN }}` over PATs when possible\n8. **Concurrency controls:** Use `concurrency` to prevent parallel deploys\n\n```yaml\n# WRONG - script injection vulnerability\n- run: echo \"${{ github.event.issue.title }}\"\n\n# CORRECT - pass through environment variable\n- run: echo \"$ISSUE_TITLE\"\n  env:\n    ISSUE_TITLE: ${{ github.event.issue.title }}\n```\n\n## Caching Strategies\n\n### Node.js\n```yaml\n- uses: actions\u002Fsetup-node@v4\n  with:\n    node-version: 20\n    cache: 'npm'  # or 'yarn' or 'pnpm'\n```\n\n### Python\n```yaml\n- uses: actions\u002Fsetup-python@v5\n  with:\n    python-version: '3.12'\n    cache: 'pip'  # or 'poetry' or 'pipenv'\n```\n\n### Go\n```yaml\n- uses: actions\u002Fsetup-go@v5\n  with:\n    go-version: '1.22'\n    cache: true\n```\n\n### Rust\n```yaml\n- uses: actions\u002Fcache@v4\n  with:\n    path: |\n      ~\u002F.cargo\u002Fbin\u002F\n      ~\u002F.cargo\u002Fregistry\u002Findex\u002F\n      ~\u002F.cargo\u002Fregistry\u002Fcache\u002F\n      target\u002F\n    key: ${{ runner.os }}-cargo-${{ hashFiles('**\u002FCargo.lock') }}\n```\n\n### Docker\n```yaml\n- uses: docker\u002Fbuild-push-action@v6\n  with:\n    cache-from: type=gha\n    cache-to: type=gha,mode=max\n```\n\n## Matrix Testing Patterns\n\n### Multiple Node.js versions\n```yaml\nstrategy:\n  matrix:\n    node-version: [18, 20, 22]\n  fail-fast: false\n```\n\n### Multiple OS\n```yaml\nstrategy:\n  matrix:\n    os: [ubuntu-latest, macos-latest, windows-latest]\nruns-on: ${{ matrix.os }}\n```\n\n### Complex matrix with exclusions\n```yaml\nstrategy:\n  matrix:\n    os: [ubuntu-latest, windows-latest]\n    node-version: [18, 20]\n    exclude:\n      - os: windows-latest\n        node-version: 18\n```\n\n## Cron Syntax Quick Reference\n\n| Schedule | Cron |\n|----------|------|\n| Every hour | `0 * * * *` |\n| Daily at midnight UTC | `0 0 * * *` |\n| Weekdays at 9am UTC | `0 9 * * 1-5` |\n| Weekly on Sunday | `0 0 * * 0` |\n| Monthly 1st | `0 0 1 * *` |\n\n## Output Format\n\nAfter creating the workflow file, provide:\n\n1. **What the workflow does** — one-paragraph summary\n2. **Required secrets** — list any secrets the user needs to configure in Settings > Secrets\n3. **Required permissions** — if the workflow needs non-default repository permissions\n4. **How to test** — how to trigger the workflow (push, create PR, manual dispatch)\n\n## Common Patterns to Combine\n\nWhen the user asks for something generic like \"set up CI\u002FCD\", create a single workflow with multiple jobs:\n\n```yaml\njobs:\n  lint:        # Fast feedback\n  test:        # Core validation\n  build:       # Ensure it compiles\u002Fbundles\n    needs: [lint, test]\n  deploy:      # Only after everything passes\n    needs: build\n    if: github.ref == 'refs\u002Fheads\u002Fmain'\n```\n\nKeep workflows focused. Prefer one workflow per concern over one massive workflow, unless the jobs are tightly coupled.\n",{"name":5,"description":7},"main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Fgithub-actions-creator",3911,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-11 21:38:31",{"source":8,"skillName":5,"commands":71,"prompt":81,"zipAvailable":82},[72,75,78],{"tool":73,"command":74},"npx","npx skills add davila7\u002Fclaude-code-templates --skill github-actions-creator",{"tool":76,"command":77},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill github-actions-creator",{"tool":79,"command":80},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill github-actions-creator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Fgithub-actions-creator\u002FSKILL.md",true,[84,90,94,98,102],{"path":85,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":88,"sourceHtmlUrl":89},"reference\u002Fcompras.md","REFERENCE","参考文档",1618,"https:\u002F\u002Fgithub.com\u002Fmatheusnorjosa\u002Faprender_sistema\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Faprender-domain\u002Freference\u002Fcompras.md",{"path":91,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":92,"sourceHtmlUrl":93},"reference\u002Fdat-module.md",2914,"https:\u002F\u002Fgithub.com\u002Fmatheusnorjosa\u002Faprender_sistema\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Faprender-domain\u002Freference\u002Fdat-module.md",{"path":95,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":96,"sourceHtmlUrl":97},"reference\u002Fkey-models.md",3044,"https:\u002F\u002Fgithub.com\u002Fmatheusnorjosa\u002Faprender_sistema\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Faprender-domain\u002Freference\u002Fkey-models.md",{"path":99,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":100,"sourceHtmlUrl":101},"reference\u002Fplano-formacoes.md",2715,"https:\u002F\u002Fgithub.com\u002Fmatheusnorjosa\u002Faprender_sistema\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Faprender-domain\u002Freference\u002Fplano-formacoes.md",{"path":103,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":104,"sourceHtmlUrl":105},"references\u002Fworkflow-templates.md",17875,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Fgithub-actions-creator\u002Freferences\u002Fworkflow-templates.md",[107,134,161,194,229,250],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":114,"publishedAt":55},"01M70NHBTQ8BV0A2SCAZXEPHCX","wealthville-pool-scoring","Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter\u002FHold\u002FExit\u002FReduce\u002FAvoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fweb-data\u002Fwealthville-pool-scoring\u002FSKILL.md",[113],{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},[115,116,117,118,119,120,121,122,123,36,124,125,126,127,128,129,130,131,132,133],"scoring","pool","wealthville pool scoring","liquidity","which","for","exit","now","use","reduce","with","record","track","verdict","evm","solana","how","public","look",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":141,"publishedAt":55},"01M70MB6VR8ERJ4EM8D5KHBMEV","technical-debt-auditor","Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO\u002FFIXME\u002FHACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like \"where should I focus refactoring\", \"find code smells\", \"audit my codebase\", \"what technical debt do we have\", \"prioritize cleanup work\", or asks about code quality metrics. Also trigger when the user mentions \"code rot\", \"legacy cleanup\", \"refactoring priorities\", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say \"technical debt\" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Ftechnical-debt-auditor\u002FSKILL.md",[140],{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},[142,143,144,145,146,147,148,149,150,151,152,36,153,154,155,156,157,158,159,160],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","code","todo","work","plan","focus","signals","audit","dependency",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":176,"publishedAt":55},"01M70KPYH9QNHCNME5GJQGE22K","readonly-sql-guard","Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production\u002FERP\u002Fanalytics database (a \"query\" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write\u002FDDL\u002Fside-effect\u002Ftransaction-escape risks. Checks what a statement CALLS, not just its shape.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdatabase\u002Freadonly-sql-guard\u002FSKILL.md",[167,170,171],{"categoryNo":168,"categoryName":169,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":172,"categoryName":173,"taxonomyType":174,"taxonomyTypeDesc":175},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[177,178,179,180,181,182,183,120,184,185,186,187,188,189,190,123,191,192,36,193],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","access","database","query",{"skillNo":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":198,"licenseFileUrl":199,"sourceHtmlUrl":200,"categories":201,"keywords":205,"publishedAt":55},"01M6AFY6F7CC2BBZP1QD6VTNVC","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[202],{"categoryNo":203,"categoryName":204,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,120,228],"artifacts builder","web","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","Tools","file","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":230,"name":231,"nameZh":6,"description":232,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":198,"licenseFileUrl":233,"sourceHtmlUrl":234,"categories":235,"keywords":238,"publishedAt":55},"01M6AFWF33SFV9Z3SF4PEEE4BF","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[236,237],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":203,"categoryName":204,"taxonomyType":21,"taxonomyTypeDesc":22},[239,38,240,241,242,207,243,216,217,244,245,246,247,120,248,125,249],"webapp testing","webapp","browser","playwright","applications","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":251,"name":252,"nameZh":6,"description":253,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":198,"licenseFileUrl":254,"sourceHtmlUrl":255,"categories":256,"keywords":264,"publishedAt":55},"01M6AF67Q67JJJ5V51JR2P52KA","discernment-nudge","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FSKILL.md",[257,260,261],{"categoryNo":258,"categoryName":259,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":262,"categoryName":263,"taxonomyType":174,"taxonomyTypeDesc":175},"01JBSEEDCAT000000000000036","内容创作者",[265,266,267,268,269,270,271,272,209,273,219,153,274,275,276,277,42,189,278,36,279,280,281,282,283,131,284],"discernment nudge","nudge","interpretation","help","run","reasoning","data","writing","lookup","content","review","conversation","short","invoke","you","analysis","claims","argument","assemble","recommendations"]