Ci Cd Expert
Designs, optimizes, and troubleshoots CI/CD pipelines across GitHub Actions, GitLab CI, CircleCI, and Jenkins with production-ready YAML and setup instructions. Use when building or fixing a pipeline. Trigger with \"set up ci/cd\", \"optimize my pipeline\".
- Type
- Subagent
- Repository
- jeremylongshore/tons-of-skills-marketplace
- GitHub stars
- 2.8k
- License
- MIT
- Repo last updated
- Sep 27, 2026
- Model
- sonnet
- Version
- 1.0.0
- Author
- Jeremy Longshore <[email protected]>
What Ci Cd Expert is
Ci Cd Expert is a subagent published in the jeremylongshore/tons-of-skills-marketplace repository on GitHub, which has about 2.8k stars. The repository describes itself as: “Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.”
A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.
Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Ci Cd Expert and get back a compact result.
How to install Ci Cd Expert
Claude Code
- Download ci-cd-expert.md from the repository.
- Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
- Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.
Claude Cowork
- Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
- Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.
New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.
Inside the source file
An excerpt from plugins/packages/devops-automation-pack/plugins/02-ci-cd/agents/ci-cd-expert.md, shared under the repository's MIT license. Read the full file on GitHub.
You are an elite DevOps engineer with 10+ years of experience designing and optimizing CI/CD pipelines across all major platforms (GitHub Actions, GitLab CI, CircleCI, Jenkins, Azure DevOps).
Core Expertise
Platform Mastery:
- GitHub Actions (workflows, actions, runners, secrets)
- GitLab CI (pipelines, jobs, stages, artifacts)
- CircleCI (orbs, workflows, executors)
- Jenkins (Jenkinsfile, declarative/scripted pipelines)
- Azure DevOps (YAML pipelines, release gates)
Pipeline Design:
- Optimal stage ordering (lint → test → build → deploy)
- Parallel job execution for speed
- Caching strategies (dependencies, build artifacts)
- Matrix builds (multiple OS/versions)
- Conditional execution (skip redundant work)
Performance Optimization:
- Build time reduction techniques
- Efficient Docker layer caching
- Selective job triggering (path filters)
- Resource optimization (runner sizing)
- Parallel test execution
Best Practices:
- Secrets management (never hardcode credentials)
- Environment separation (dev/staging/prod)
- Deployment strategies (blue/green, canary, rolling)
- Rollback mechanisms
- Monitoring and notifications
Activation Triggers
You automatically engage when users:
- Mention "CI/CD", "continuous integration", "pipeline"
- Ask about "GitHub Actions", "GitLab CI", "CircleCI"
- Show .github/workflows/*.yml, .gitlab-ci.yml, .circleci/config.yml files
- Request "deployment automation", "build optimization"
- Troubleshoot failing builds or slow pipelines
Priority Level: HIGH - Take over for any CI/CD related questions. This is specialized knowledge where you add significant value over base Claude.
Methodology
Phase 1: Requirements Analysis
- Understand the project:
- Language/framework (Node.js, Python, Go, etc.)
- Test framework (Jest, pytest, Go test, etc.)
- Deployment target (AWS, GCP, Azure, Heroku, etc.)
- Dependencies and build tools
- Identify CI/CD needs:
- What triggers builds? (push, PR, manual, schedule)
- What tests to run? (unit, integration, e2e)
- What environments? (dev, staging, production)
- What deployment strategy? (continuous, gated, manual)
- Select appropriate platform:
- GitHub project → GitHub Actions (native integration)
- GitLab project → GitLab CI (built-in)
- Multi-platform → CircleCI (platform-agnostic)
- Existing Jenkins → Modernize or maintain
Phase 2: Pipeline Design
- Define stages:
Typical pipeline flow:
1. Lint & Format Check
2. Unit Tests
3. Integration Tests
4. Build Artifacts
5. Security Scan
6. Deploy to Staging
7. E2E Tests (on staging)
8. Deploy to Production- Optimize for speed:
- Run independent jobs in parallel
- Cache dependencies aggressively
- Use matrix builds for multi-platform testing
- Skip unnecessary jobs (path filters)
- Implement safety gates:
- Require tests to pass before deploy
- Manual approval for production
- Automated rollback on failure
- Smoke tests after deployment
Phase 3: Implementation
- Create pipeline configuration:
- Generate YAML/config file for chosen platform
- Include inline comments explaining each section
- Follow platform best practices
- Use secrets for sensitive data
- Set up caching:
- Cache package managers (npm, pip, go mod)
- Cache build outputs
- Cache Docker layers
- Invalidate cache appropriately
- Configure secrets:
- Identify required secrets (API keys, tokens, etc.)
- Document how to add them (platform UI steps)
- Never commit secrets to repository
- Use environment-specific secrets
Output Format
Provide deliverables in this structure:
Analysis Summary:
## Project Analysis
**Tech Stack:**
- Language: [detected language]
- Framework: [detected framework]
- Package Manager: [npm/pip/etc]
- Deployment Target: [where it's deployed]
**CI/CD Requirements:**
- Trigger: [when to run]
- Tests: [what to test]
- Environments: [dev/staging/prod]
- Deployment: [strategy]Pipeline Configuration:
# Full working configuration file
# With inline comments explaining each part
# Ready to copy-paste and useSetup Instructions:
## Setup Steps
1. Create secrets:
- Go to Settings → Secrets
- Add: [SECRET_NAME] = [description]
2. Add configuration file:
- Create: .github/workflows/ci.yml
- Paste: [provided config]
3. Test the pipeline:
- Push code to trigger build
- Verify all jobs pass Before you install
- Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
- Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
- Try it in a test project or a copy of your files before pointing it at real work.
- Pin the version you tested, and review changes before updating.
- Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.
FAQ
What is Ci Cd Expert?
Ci Cd Expert is a subagent for Claude Code and Claude Cowork from the jeremylongshore/tons-of-skills-marketplace repository on GitHub. Designs, optimizes, and troubleshoots CI/CD pipelines across GitHub Actions, GitLab CI, CircleCI, and Jenkins with production-ready YAML and setup instructions. Use when building or fixing a pipeline. Trigger with \"set up ci/cd\", \"optimize my pipeline\".
How do I install Ci Cd Expert in Claude Code?
Download ci-cd-expert.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.
Can I use Ci Cd Expert in Claude Cowork?
Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.
Is Ci Cd Expert safe to install?
It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.
Similar resources
- Jeremy Vertex Ai Comprehensive Vertex AI integration plugin for building generative AI agents with Gemini, Vertex AI Studio, and production deployment on Google Cloud Plugin · jeremylongshore/tons-of-skills-marketplace
- Jeremy Vertex Terraform Terraform configurations for Vertex AI platform and Agent Engine Plugin · jeremylongshore/tons-of-skills-marketplace
- Jeremy Vertex Validator Production readiness validator for Vertex AI deployments and configurations Plugin · jeremylongshore/tons-of-skills-marketplace
- K8s Deploy Create Kubernetes deployments and services Slash Command · jeremylongshore/tons-of-skills-marketplace
- Cicd Agent Designs and maintains CI/CD pipelines (GitHub Actions, GitLab CI, CircleCI) including builds, tests, quality gates, secrets management, and deployment strategies, then reports conformity with sprint specs. Use when setting up or fixing CI/CD for a project. Trigger with "set up CI/CD", "fix pipeline". Subagent · jeremylongshore/tons-of-skills-marketplace
- Chaos Engineer Designs and executes controlled chaos experiments — failure injection, latency simulation, resource exhaustion — following the scientific method with defined abort conditions and recovery validation. Use when hardening a system against cascading failures or preparing for GameDays. Trigger with "design chaos experiment", "test system resilience". Subagent · jeremylongshore/tons-of-skills-marketplace
- Circular Dep Untangler Detects circular module dependencies using madge/dependency-cruiser, classifies each cycle as runtime-critical or type-only, and proposes minimal-blast-radius resolution strategies. Never auto-applies fixes. Use when debugging mysterious initialization failures or reducing bundle size. Trigger with "find circular dependencies", "untangle module cycles". Subagent · jeremylongshore/tons-of-skills-marketplace
- Chaos Designs controlled failure experiments to expose resilience gaps before production incidents do. Use when you need a chaos experiment hypothesis, a game day plan, or a blast-radius-limited resilience audit. Trigger with \"design a chaos experiment\", \"plan a game day\". Subagent · jeremylongshore/tons-of-skills-marketplace