
Implement a ticket using TDD and review in a converging loop. Use when you have an approved spec and implementation plan. Spawns TddEngineer for implementation, delegates to deep-review for adversarial analysis, and auto-fixes findings in an autonomous loop (max 5 rounds) before gating user approval.
Show the current state of an /swe pipeline run. Use when checking pipeline progress, resuming after an interruption, or reviewing what stage a ticket has reached. Accepts a ticket ID or lists all active pipelines if no argument given.
Review a GitHub PR or self-review local changes. Fetches PR data via gh CLI, analyzes code quality, verifies tests, checks best practices, and posts inline review comments. Use when asked to review a PR, check a pull request, or self-review before creating a PR.
Generates markdown API documentation from FastAPI routes, Pydantic models, DRF viewsets, and serializers — also detects drift between code and existing docs. Use when asked to "generate api docs", "document api", "api documentation", "openapi", "swagger docs", "update api docs", "check api drift", or "document endpoints".
Intelligently reviews git diffs and creates well-structured commits with descriptive messages. Automatically splits changes into multiple logical commits when modifications span unrelated concerns. Use when asked to "commit changes", "commit my work", "split commits", "create commits from diffs", "auto-commit", or "review and commit".
Manages Python dependencies — add, remove, audit for vulnerabilities with pip-audit, and detect unused packages. Use when asked to "manage deps", "add dependency", "remove dependency", "audit dependencies", "find unused packages", "pip audit", "security audit deps", "check vulnerabilities", or "dependency management".
Generates RFCs and Architecture Decision Records (ADRs) from feature descriptions — reads existing docs to maintain numbering and style. Use when asked to "write rfc", "create adr", "design doc", "architecture decision", "technical design", "write proposal", "document decision", or "design document".
Create new Agent Skills for GitHub Copilot from prompts or by duplicating this template. Use when asked to "create a skill", "make a new skill", "scaffold a skill", or when building specialized AI capabilities with bundled resources. Generates SKILL.md files with proper frontmatter, directory structure, and optional scripts/references/assets folders.
Create a GitHub pull request from the current branch with auto-generated title and description. Use when the user wants to create a PR, open a pull request, or submit changes for review.
Show a quick summary of PR review thread statuses on GitHub. Use when the user wants to check PR status, see remaining comments, review thread summary, or triage before resolving.
Runs ruff, mypy, and bandit on changed Python files — explains violations and auto-fixes with ruff check --fix. Use when asked to "lint", "fix lint", "check types", "type check", "run mypy", "run ruff", "python quality", or "lint python files".
Fetch active PR review threads from GitHub and resolve them by making code changes. Use when the user wants to address, fix, or resolve PR review comments automatically.
Run a four-agent review on a technical spec or implementation plan. Use when a spec or plan needs evaluation from maintainability, security, efficiency, and completeness perspectives. Spawns four reviewer agents that write structured comment files, then merges all comments into the document in a single conflict-free pass.
Generate a technical spec and implementation plan for a ticket. Use when you have parsed requirements and need a detailed design before implementation. Orchestrates codebase exploration, spec authoring, autonomous review-fix loops, implementation planning, and plan review-fix loops across multiple agents.
Run the full software engineering pipeline from ticket to PR. Use when starting a feature, fixing a bug from a ticket, or driving end-to-end development from a Jira, Linear, or GitHub issue. Accepts a ticket ID or URL as argument and orchestrates intake, spec design, TDD implementation, code review, and PR creation with approval gates at each stage.
Generates AGENTS.md files for repository folders — coding agent context files with build commands, testing instructions, code style, project structure, and boundaries. Only generates where AGENTS.md is missing.
Analyzes git commit history and generates structured changelogs categorized by change type. Use when the user asks about recent changes, wants a changelog, or needs to understand what changed in the repository.
Generates two complementary onboarding guides — a Principal-Level architectural deep-dive and a Zero-to-Hero contributor walkthrough. Use when the user wants onboarding documentation for a codebase.
Answers questions about a code repository using source file analysis. Use when the user asks a question about how something works, wants to understand a component, or needs help navigating the codebase.
Conducts multi-turn iterative deep research on specific topics within a codebase with zero tolerance for shallow analysis. Use when the user wants an in-depth investigation, needs to understand how something works across multiple files, or asks for comprehensive analysis of a specific system or pattern.
Generates GitHub Actions CI/CD workflows, diagnoses failing runs from logs, and adds pipeline steps. Use when asked to "set up ci", "create pipeline", "fix ci", "ci failing", "github actions", "add ci step", "diagnose build", or "workflow yaml".
Review code for bugs, security issues, performance problems, and readability improvements. Use when you need a code review on a file or directory.
One-shot adversarial review - three parallel subagents analyze independently, orchestrator synthesizes. No debate between agents. Fast and cost-effective.
Analyzes code repositories and generates hierarchical documentation structures with onboarding guides. Use when the user wants to create a wiki, generate documentation, map a codebase structure, or understand a project's architecture at a high level.
Generates rich technical documentation pages with dark-mode Mermaid diagrams, source code citations, and first-principles depth. Use when writing documentation, generating wiki pages, creating technical deep-dives, or documenting specific components or systems.
Packages generated wiki Markdown into a VitePress static site with dark theme, dark-mode Mermaid diagrams with click-to-zoom, and production build output. Use when the user wants to create a browsable website from generated wiki pages.
Generates multi-stage Dockerfiles and docker-compose.yml configurations, adds services like Postgres/Redis/Celery/Nginx, and checks for Docker anti-patterns. Use when asked to "dockerize", "create dockerfile", "docker compose", "add docker", "add redis", "add postgres", "docker init", "optimize docker", or "container setup".
Fetch and parse a ticket from Jira, Linear, or GitHub Issues. Use when starting work on a ticket, beginning a new feature, or when given a ticket ID or issue URL. Accepts a ticket ID or full URL as argument, auto-detects the ticketing system, and produces a structured requirements summary.
Decomposes feature descriptions or GitHub issues into ordered subtasks with file-level scope, acceptance criteria, and optional gh issue create. Use when asked to "break down task", "decompose feature", "create subtasks", "plan implementation", "break this into tasks", "task list", or "implementation plan".
Generates changelogs from conventional commits, bumps semantic versions in pyproject.toml or package.json, and publishes GitHub releases. Use when asked to "create release", "release notes", "changelog", "bump version", "semantic version", "tag release", "publish release", or "what changed since last release".