AugmentClaude

CI Pipeline Synthesizer

Generate GitHub Actions workflows for automated building and testing of packages.

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.

    This copies the whole skill folder into ~/.claude/skills/ci-pipeline-synthesizer-kajisho5/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Works for every skill.

    What this command does
    1. Makes a new, empty temporary folder.
    2. Downloads the skill's folder, .claude/skills/ci-pipeline-synthesizer, from github.com/kajisho5/ffmpeg-skill (branch main), the GitHub repository it's listed from. You get the version that is there now, not a copy we keep.
    3. Copies that folder to ~/.claude/skills/ci-pipeline-synthesizer-kajisho5/.
    4. Deletes the temporary folder.

    Installing runs none of the skill's files; it only downloads and copies them. When you later use the skill, Claude follows its SKILL.md and may run scripts that come with it. Read them first.

    How we check skills, and what we don't · Report this skill

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    Sign up to copy
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

Generate GitHub Actions CI/CD pipeline configurations for automated building and testing of library and package projects. Use when creating or updating CI workflows for npm packages, Python packages, Go modules, Rust crates, or other library projects that need automated build and test pipelines. Includes templates for common package ecosystems with best practices for dependency caching, matrix testing, and artifact publishing.

What this skill does

CI Pipeline Synthesizer

Overview

Generate production-ready GitHub Actions workflow files for library and package projects with automated build and test stages, dependency caching, and multi-version testing matrices.

Workflow

1. Identify Project Type

Determine the package ecosystem by examining project files:

  • Node.js/npm: package.json present
  • Python: setup.py, pyproject.toml, or requirements.txt present
  • Go: go.mod present
  • Rust: Cargo.toml present

2. Select Template

Use the appropriate template from assets/ based on project type:

  • github-actions-nodejs.yml - Node.js/npm packages
  • github-actions-python.yml - Python packages
  • github-actions-go.yml - Go modules
  • github-actions-rust.yml - Rust crates

3. Customize Configuration

Adapt the template to project-specific needs:

Test commands: Update test scripts to match project conventions

  • Node.js: npm test, npm run test:coverage
  • Python: pytest, python -m unittest
  • Go: go test ./...
  • Rust: cargo test

Build commands: Adjust build steps if needed

  • Node.js: npm run build (if build step exists)
  • Python: python -m build
  • Go: go build
  • Rust: cargo build --release

Version matrix: Modify tested versions based on support policy

  • Node.js: LTS versions (16.x, 18.x, 20.x)
  • Python: Active versions (3.9, 3.10, 3.11, 3.12)
  • Go: Recent versions (1.21, 1.22)
  • Rust: stable, beta (optional)

Trigger conditions: Adjust when pipeline runs

  • Default: Push to main/master, all pull requests
  • Custom: Specific branches, paths, or schedules

4. Place Workflow File

Create the workflow file at .github/workflows/ci.yml in the project root. If .github/workflows/ doesn't exist, create the directory structure first.

5. Verify Configuration

Check that the generated workflow:

  • Uses appropriate actions versions (e.g., actions/checkout@v4, actions/setup-node@v4)
  • Includes dependency caching for faster builds
  • Runs on appropriate triggers (push, pull_request)
  • Tests against relevant version matrices
  • Has clear job and step names

Template Features

All templates include:

  • Dependency caching: Speeds up builds by caching package managers
  • Matrix testing: Tests across multiple language/runtime versions
  • Parallel execution: Runs tests for different versions concurrently
  • Clear naming: Descriptive job and step names for easy debugging
  • Best practices: Uses recommended actions and configurations

Customization Examples

Add code coverage reporting:

- name: Upload coverage to Codecov
  uses: codecov/codecov-action@v3
  with:
    file: ./coverage.xml

Add linting step:

- name: Run linter
  run: npm run lint  # or: pylint, golangci-lint, cargo clippy

Restrict to specific branches:

on:
  push:
    branches: [main, develop]
  pull_request:
    branches: [main]

Add scheduled runs:

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

Tips

  • Start with the template and customize incrementally
  • Test the workflow by creating a pull request or pushing to a test branch
  • Use actions/cache for dependencies to reduce build times
  • Keep matrix versions current with language support policies
  • Add status badges to README.md: ![CI](https://github.com/user/repo/workflows/CI/badge.svg)

Note for this repository (ffmpeg-skill)

This skill's generic templates assume ordinary language-toolchain dependencies (pip/npm/go/cargo). They do NOT model this repo's actual CI needs — installing a real ffmpeg binary per OS (apt/brew ffmpeg-full/choco), capturing its -filters/-encoders/-bsfs listings as an artifact, or the skipIf-based Windows test coverage in tests/test_contract.py — all of which .github/workflows/ci.yml already handles and this skill's templates would not reproduce. Treat this as reference/scaffolding for a plain Python/Node/Go/ Rust package elsewhere, not a drop-in replacement for this repo's own workflow.

Related skills