aka. Agent Skills
Discover skills for AI coding agents. Works with Claude Code, OpenAI Codex, Gemini CLI, Cursor, and more.
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Verify rough-draft phase alignment with design doc
Analyzes recent conversation history using chat tools to identify recurring workflow patterns and generate Custom Skills recommendations with statistical rigor. Use when users request workflow analysis, pattern identification, skill generation suggestions, or automation opportunities based on their AI usage patterns without requiring conversation exports.
Automatically validates Cloudflare Workers security patterns during development, ensuring proper secret management, CORS configuration, and input validation
Autonomous validation of Polar.sh billing integration. Checks webhook endpoints, signature verification, subscription middleware, and environment configuration.
Automatically validates Cloudflare Workers binding configuration, ensuring code references match wrangler.toml setup and TypeScript interfaces are accurate
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Process multimedia files with FFmpeg (video/audio encoding, conversion, streaming, filtering, hardware acceleration) and ImageMagick (image manipulation, format conversion, batch processing, effects, composition). Use when converting media formats, encoding videos with specific codecs (H.264, H.265, VP9), resizing/cropping images, extracting audio from video, applying filters and effects, optimizing file sizes, creating streaming manifests (HLS/DASH), generating thumbnails, batch processing images, creating composite images, or implementing media processing pipelines. Supports 100+ formats, hardware acceleration (NVENC, QSV), and complex filtergraphs.
Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.
Keycloak administration including realm management, client configuration, OAuth 2.0 setup, user management with custom attributes, role and group management, theme deployment, and token configuration. Activate for Keycloak Admin API operations, authentication setup, and identity provider configuration.
FastAPI best practices, Pydantic models, SQLAlchemy ORM, async patterns, dependency injection, and JWT authentication. Activate for FastAPI apps, async Python APIs, API design, and modern Python web services.
Generate and track E2E test checklists with clear user/Claude separation. Users do manual UI actions, Claude runs automated verifications (DB, API, logs). Launches a Docker webapp for testing with screenshot uploads. Use when completing features, requesting manual verification, or before merging.
Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.
Verification and drift detection for executing-plans
Expert-level Harness template types, runtime inputs, expression language, pipeline patterns (CI/CD, GitOps, Canary, Blue-Green), versioning, and step configurations
Convert all missing topic flags into stub topics flagged as incomplete
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
Use when designing interfaces, data visualizations, documentation, or any output where clarity and visual hierarchy matter - applies Swiss design principles of reduction, grid structure, hierarchy, and typography