ghcp-dev-plugins

Analyzes code for bugs, security issues, performance problems, and readability improvements

Create new Agent Skills from prompts or by duplicating this template. Use when asked to create a skill, make a new skill, or scaffold a skill.

Intelligently reviews git diffs and creates well-structured commits, automatically splitting changes into multiple logical commits when needed

GitHub pull request tools — review PRs, resolve review comments, check thread status, and create PRs using the gh CLI

Runs ruff, mypy, and bandit on Python files to find and auto-fix lint violations, type errors, and security issues

Generates GitHub Actions workflows, diagnoses CI failures from run logs, and helps add pipeline steps

Generates changelogs from conventional commits, bumps semantic versions, and creates GitHub releases

Generates multi-stage Dockerfiles and docker-compose configurations, adds services like Postgres and Redis, and optimizes images for production

Generates RFCs and Architecture Decision Records from feature descriptions, maintaining consistent numbering and format

Decomposes feature descriptions and GitHub issues into ordered implementation subtasks with file-level scope and acceptance criteria

Manages Python dependencies — add, remove, audit for vulnerabilities, and detect unused packages

Generates markdown API documentation from FastAPI routes and DRF viewsets, and detects drift between code and existing docs

AI-powered wiki generator — creates structured documentation with dark-mode Mermaid diagrams, onboarding guides, and VitePress sites from any codebase

Lightweight adversarial code review with three parallel subagents (Advocate, Skeptic, Architect) that analyze independently before synthesis

Fully agentic software engineering pipeline — from ticket intake through spec design, TDD implementation, code review, and PR creation. Orchestrates multiple agents and skills across five stages.

Autonomous coding loops that keep Claude working until real completion criteria are met

Injects real-time, up-to-date library documentation into Claude's context for accurate code generation

Official Microsoft Playwright MCP server for direct browser control, debugging, and test automation

Sentry error tracking and performance monitoring - search issues, analyze errors, explore traces, and get AI-powered root cause analysis

Browser automation — writes and executes Playwright scripts for end-to-end testing and UI verification