Agent Skills Hub

metacognition

Enforces structured self-assessment checkpoints to validate approach, mitigate risks, and ensure quality before, during, and after task execution.

symbols

Token-efficient codebase navigation through intelligent symbol indexing, domain chunking, and architectural layer filtering. Reduce token usage by 60-95% when exploring or developing complex systems.

gemini-manager

Claude Code as an architect: delegate all coding and file edits to the Gemini CLI while maintaining control through planning, verification, and oversight.

handoff-pack

Generates structured Handoff Pack prompts for delegating scoped coding tasks to Gemini with clear instructions, acceptance criteria, and output requirements.

respond

Manually finalize and submit AI agent responses to Claude. Use when automatic synchronization fails or to manually curate findings.

auto-skill-generator

Research technical documentation and automatically generate ready-to-use software agent skills in markdown format.

reflect-appworld-failure

Analyze AppWorld task failures to extract specific API patterns and generate actionable playbook bullets with concrete code examples.

claude-code-skill

Control Claude Code via MCP protocol for autonomous development. Features persistent sessions, agent teams, precise execution planning, and advanced tool management for complex coding tasks.

context-management

Proactive context window management for AI agents via intelligent token monitoring, snapshot creation, and selective state rehydration to maintain continuity during long sessions.

qmd

Local hybrid search engine for markdown notes, documentation, and codebase knowledge bases to reduce token consumption and improve retrieval efficiency.

writing-skills

A Test-Driven Development (TDD) framework for writing agent skills, using pressure scenarios to ensure documentation guides agent behavior effectively.

crane

Expert assistant for writing high-quality, modern, and memory-safe C++ code for V8 FFI wrappers and native integrations.