Generator-Evaluator iteration loop for building features against a scored rubric. Use when user says "gan", "gan loop", "generator evaluator", "iterate to threshold", "build with feedback loop", or needs an iteration pattern stronger than /loop for feature work that has a measurable quality signal. Do NOT use for one-shot implementations (use /plan + direct edits), recurring schedules (use /loop), or visual design exploration (use /design variants).
EnglishManage infrastructure for local development. Subcommands: docker, terraform, db. Covers container orchestration with Colima awareness, IaC workflows with safety gates, and database migrations with ORM detection. Use when user says "docker compose", "start containers", "terraform plan", "run migration", "create migration", "database setup", or needs to manage local dev infrastructure. Do NOT use for deploying to production (use CI/CD), security scanning (use /audit), or Terraform test patterns (check standards/terraform-testing.md).
EnglishRespond to incoming code review comments on a PR you authored. Fetches unresolved threads, classifies each by author and intent, verifies against the current code, drafts replies in a natural voice, applies code changes with local validation, posts replies, resolves threads, and monitors CI. Use when user says "respond to review", "address comments", "handle reviewer feedback", "reply to PR comments", "my PR has comments", or wants a structured pass over reviewer feedback. Do NOT use for performing a review (use /review), or for unattended AI bot thread handling (use /ship --pipeline).
EnglishScaffold a new SKILL.md with the enforced frontmatter and 6-section template, then validate with the skill linter. Use when user says "new skill", "create a skill", "scaffold a skill", or asks to add a slash command. Do NOT use for editing existing skills (use Edit directly), for renaming a skill (use Bash mv + linter), or for deleting a skill (no skill required).
EnglishExplore the listed skills and choose the workflows that fit your task.
Supported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Gan
Generator-Evaluator iteration loop for building features against a scored rubric. Use when user says "gan", "gan loop", "generator evaluator", "iterate to threshold", "build with feedback loop", or needs an iteration pattern stronger than /loop for feature work that has a measurable quality signal. Do NOT use for one-shot implementations (use /plan + direct edits), recurring schedules (use /loop), or visual design exploration (use /design variants).
Infra
Manage infrastructure for local development. Subcommands: docker, terraform, db. Covers container orchestration with Colima awareness, IaC workflows with safety gates, and database migrations with ORM detection. Use when user says "docker compose", "start containers", "terraform plan", "run migration", "create migration", "database setup", or needs to manage local dev infrastructure. Do NOT use for deploying to production (use CI/CD), security scanning (use /audit), or Terraform test patterns (check standards/terraform-testing.md).
Respond
Respond to incoming code review comments on a PR you authored. Fetches unresolved threads, classifies each by author and intent, verifies against the current code, drafts replies in a natural voice, applies code changes with local validation, posts replies, resolves threads, and monitors CI. Use when user says "respond to review", "address comments", "handle reviewer feedback", "reply to PR comments", "my PR has comments", or wants a structured pass over reviewer feedback. Do NOT use for performing a review (use /review), or for unattended AI bot thread handling (use /ship --pipeline).
Skill New
Scaffold a new SKILL.md with the enforced frontmatter and 6-section template, then validate with the skill linter. Use when user says "new skill", "create a skill", "scaffold a skill", or asks to add a slash command. Do NOT use for editing existing skills (use Edit directly), for renaming a skill (use Bash mv + linter), or for deleting a skill (no skill required).
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Gan skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.