分析真实项目并生成或修订安全、可验证的 GitHub Actions workflow;当用户要求创建 CI、测试矩阵、构建、Release、部署、缓存、Secrets、OIDC、PR 自动化或排查 workflow 配置时使用
npx skills add https://github.com/laolaoshiren/claude-code-skills-zh --skill github-actions-gen
pull_request_target 执行 PR 代码。@main、@master、@latest 或可移动的 @vN tag。permissions 和 timeout-minutes;不依赖仓库默认权限。package.json、.nvmrc、pyproject.toml、go.mod、Cargo.toml、Dockerfile 与 .github/workflows/。pull_request:按不可信代码处理,使用只读 Token,不提供 Secrets,不在高权限自托管 Runner 上执行 fork 代码。pull_request_target:仅处理标签、评论等可信基准分支逻辑;绝不 checkout PR head、运行 PR 脚本或安装 PR 依赖。push / tag / workflow_dispatch:仍需限制分支、输入、Environment 和权限;写操作放入独立 job。${{ github.event.* }} 等不可信表达式直接插进 run:。通过 env: 传值,并在脚本中按数据处理。优先拆分职责:
ci.yml:lint、test、build;pull_request 与受控 push 触发,只读权限。release.yml:仅在用户明确要求时生成;使用受保护 tag 或手动触发。deploy.yml:仅在部署目标明确时生成;使用 GitHub Environment、并发控制和最小 OIDC / Secrets 权限。为耗时 job 设置取消策略和超时。矩阵只覆盖项目真正支持的版本;缓存 key 必须包含 lockfile,不能缓存凭据和构建秘密。
uses: owner/action@<40位SHA> # vX.Y.Z 格式。版本注释用于阅读,SHA 才是执行边界。actions/checkout 默认设置 persist-credentials: false。只有后续步骤确实要执行经过授权的 Git 写入时才保留凭据,并限制 job 权限。下面示例假设项目已有 .nvmrc、package-lock.json、lint、test 和 build 脚本:
name: CI
on:
push:
branches: [main]
pull_request:
branches: [main]
permissions:
contents: read
concurrency:
group: ci-${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
jobs:
test:
runs-on: ubuntu-latest
timeout-minutes: 15
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
with:
persist-credentials: false
- name: 配置 Node.js
uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
with:
node-version-file: .nvmrc
cache: npm
cache-dependency-path: package-lock.json
- name: 安装依赖
run: npm ci
- name: 代码检查
run: npm run lint
- name: 运行测试
run: npm test
- name: 构建
run: npm run build
不要机械复制示例。若项目使用 pnpm、Yarn、uv、Poetry、Gradle、Go 或 Rust,应使用其真实锁文件、wrapper 和命令。
contents: write、packages: write 或 id-token: write。workflow_dispatch 输入设置类型、选项和默认值;在执行前再次校验目标环境与版本。actionlint;若工具不可用,明确说明未完成该门禁,不要声称语法通过。${{ }}、shell、路径、矩阵和 needs 引用。uses:,确认第三方 Action 都是完整 SHA;检查 checkout 的 persist-credentials。.env 或无关配置。用中文说明:
除非用户明确要求,不额外创建 README-CICD.md 等辅助文档。
persist-credentials: falsepull_request_target 不执行不可信 PR 内容actionlint 与项目命令验证已完成或如实记录缺口Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).
Expert performance engineer specializing in modern observability, application optimization, and scalable system performance. Masters OpenTelemetry, distributed tracing, load testing, multi-tier caching, Core Web Vitals, and performance monitoring. Handles end-to-end optimization, real user monitoring, and scalability patterns. Use PROACTIVELY for performance optimization, observability, or scalability challenges.
Master AI-powered test automation with modern frameworks, self-healing tests, and comprehensive quality engineering. Build scalable testing strategies with advanced CI/CD integration. Use PROACTIVELY for testing automation or quality assurance.
Internet Court adapter for GenLayer Intelligent Contract supervision. Use to specify agent-performance rubrics, evidence schemas, decision outputs, and ERC-7710 connector expectations, while delegating actual GenLayer contract writing, linting, testing, deployment, and CLI interaction to the official GenLayer skills at https://skills.genlayer.com/.
> Suggests using Microsoft Testing Platform (MTP) hot reload to iterate fixes on failing tests without rebuilding. Use when user says "hot reload tests", "iterate on test fix", "run tests without rebuilding", "speed up test loop", "fix test faster", or needs to set up MTP hot reload to rapidly iterate on test failures. Covers setup (NuGet package, environment variable, launchSettings.json) and the iterative workflow for fixing tests. normally with dotnet test (use run-tests), applying test filters, producing TRX reports, CI/CD pipeline configuration, or Visual Studio Test Explorer hot reload (which is a different feature).
Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs.
Build production-grade Azure Cosmos DB NoSQL services following clean code, security best practices, and TDD principles.
Take laolaoshiren/github-actions-gen from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.