SP

spec-driven-ci

Automates CI/CD pipeline generation for DevForgeAI projects, enforcing strict validation phases.

Install

mkdir -p .claude/skills/spec-driven-ci && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13474" && unzip -o skill.zip -d .claude/skills/spec-driven-ci && rm skill.zip

Installs to .claude/skills/spec-driven-ci

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Generate CI/CD pipeline workflows through spec-driven workflow generation with structural anti-skip enforcement. Implements 5 phases covering preflight validation, configuration loading, workflow template generation, cost optimization, and final validation using the Execute-Verify-Gate pattern at every step. Designed to prevent token optimization bias through lean orchestration and binary CLI gate enforcement. Currently supports GitHub Actions with cost-optimized Codex API integration (prompt caching, Haiku preference, max-turns limits). Use when setting up CI/CD automation for DevForgeAI projects. Always use this skill when the user runs /setup-github-actions. Also use when the user mentions GitHub Actions setup, CI/CD pipeline generation, headless DevForgeAI execution, or workflow automation for /dev and /qa commands.
831 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Advanced

Key capabilities

  • Generate GitHub Actions workflows for headless `/dev` execution
  • Create PR quality gates with automated `/qa` validation
  • Configure parallel story execution with a matrix
  • Generate optional workflows for DevForgeAI installer testing
  • Optimize CI costs with prompt caching and model preferences
  • Pre-configure `ask the user` responses with `ci-answers.yaml`

How it works

The skill generates CI/CD pipeline workflows based on specifications, enforcing anti-skip rules and integrating cost optimization strategies.

Inputs & outputs

You give it
Configuration from conversation context, existing config files, or user responses
You get back
GitHub Actions workflow files (`dev-story.yml`, `qa-validation.yml`, `parallel-stories.yml`, `installer-testing.yml`) and CI configuration files (`github-action

When to use spec-driven-ci

  • Set up GitHub Actions pipelines
  • Configure automated CI/CD workflows
  • Initialize headless DevForgeAI build processes

About spec-driven-ci

Generates CI/CD workflows using an Execute-Verify-Gate pattern. It enforces structural anti-skip rules and integrates with Codex for cost-optimized execution.

>

When not to use it

  • The user does not want to set up CI/CD automation for DevForgeAI projects
  • The user does not want to use GitHub Actions

Limitations

  • It currently supports only GitHub Actions
  • It requires GitHub Secrets for API keys
  • It relies on specific context files like `tech-stack.md` and `source-tree/`

How it compares

This workflow automates the generation of CI/CD pipelines with built-in anti-skip enforcement and cost optimization, providing a structured and efficient setup compared to manual configuration.

Compared to similar skills

spec-driven-ci side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
spec-driven-ci (this skill)01moReviewAdvanced
github-workflow-automation112moReviewAdvanced
github-actions-templates73moNo flagsIntermediate
hooks-automation34moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry