Published skills
notebooklm-research
A fully autonomous AI research agent that ingests sources into Google NotebookLM, runs deep web research, and synthesizes knowledge through cited Q&A and 9 downloadable artifact types.
super-helper
A helpful skill that does many things
greeting-helper
A simple skill that helps with greeting messages
check-environment
Verify development environment is ready
claude-md-check
Validate CLAUDE.md structure and completeness
claude-md-template
Generate CLAUDE.md template for current project
code-reviewer
Code review specialist for quality, security, and best practices
debugger
Debugging specialist for root cause analysis and problem resolution
doc-writer
Documentation specialist for README, API docs, and code comments
evolving-loop
Self-Evolving Development Loop - Dynamic skill generation with learning and evolution
evolving-status
View Self-Evolving Loop session status, history, and memory metrics
focus-problem
Problem analysis using Explore agents
getting-started
Guided 5-minute onboarding for Director Mode Lite
handoff-codex
Delegate tasks to Codex CLI to save Claude context
handoff-gemini
Delegate tasks to Gemini CLI to save Claude context
hooks-check
Validate hooks configuration and scripts
interop-router
Automatically routes tasks to external AI CLIs (Codex or Gemini) when more efficient. No manual commands needed - routing decisions are made automatically based on task type.
mcp-check
Validate MCP configuration and suggest improvements
plan
Create detailed execution plan with task breakdown
project-health-check
Complete project health audit (7 checks)
project-init
Expert-guided project setup with 6 phases
skill-check
Validate skill/command file format and structure
skill-template
Generate custom skill/command from template
skills
List all available skills (core + custom)
smart-commit
Conventional Commits with quality checks
test-first
Test-Driven Development (TDD Red-Green-Refactor)
test-runner
Test automation specialist for running tests and ensuring coverage
workflow
Complete 5-step development workflow
auto-loop
TDD-based autonomous development loop with checkpoint recovery and observability changelog
agent-template
Generate custom agent from template
agent-check
Validate custom agent file format and structure
agents
List all available agents (core + expert)
changelog-observer
Track development session events in a daily markdown changelog, including file changes, test results, and key decisions.
changelog
View and manage the runtime changelog for observability
hook-template
Generate hook script from template
semantic-compressor
Compress agents/skills with quality assurance loop. Iterative 5-phase process ensures understanding preserved. TRIGGERS: semantic-compressor, compress skill, optimize agent, reduce tokens, benchmark
Category alert