Synchronizes prompt files (agents, rules, commands) from the skill's prompts directory to both GitHub Copilot and OpenCode global configuration directories. Use when the user wants to update their...
Friendly onboarding when users ask about capabilities
Agentic memory system for writers - track characters, relationships, scenes, and themes
Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures,...
Enables GitHub repository operations (read/write/commit/PR) for Claude.ai chat environments. Use when users request GitHub commits, repository updates, DEVLOG persistence, or cross-session state...
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world...
Guide for authoring specialized AI agents. Use when creating, updating, or improving agents, choosing models, defining focus areas, configuring tools, or learning agent best practices.
|
Implement technical plans from thoughts/shared/plans with verification
Build AI agents with Pydantic AI (Python) and Claude SDK (Node.js)
Agentica server + Claude proxy setup - architecture, startup sequence, debugging
Create handoff document for transferring work to another session
Generate hierarchical AGENTS.md structures for codebases. Use when user asks to create AGENTS.md files, analyze codebase for AI agent documentation, set up AI-friendly project documentation, or...
Generate hierarchical AGENTS.md structures for codebases. Use when user asks to create AGENTS.md files, analyze codebase for AI agent documentation, set up AI-friendly project documentation, or...
Python coding standards and best practices for AI coding agents
Identify failure modes before they occur using structured risk analysis
>
>
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Use when completing tasks, implementing major features, or before merging to verify work meets requirements