Agent Skills Hub

cc-skill-project-guidelines-example

A template skill for creating project-specific AI agent guidelines, defining architecture, file structures, and code patterns for deterministic development.

writing-agents

A framework for creating, testing, and managing autonomous AI subagents within project environments using Test-Driven Development principles.

moonbit-refactoring

Refactor MoonBit code for idiomatic style: minimize public APIs, implement methods, leverage pattern matching with views, and enforce high test coverage for maintainable MoonBit projects.

ui-mockup

Orchestrator for audio plugin WebView UI design, handling iterative mockup generation and production-ready scaffolding for JUCE-based instruments and effects.

context-compression

Optimize agent performance and token usage through advanced context compression, structured summarization, and task-oriented state management for long-running sessions.

otto

🛡️ GDPR & LGPD Privacy Guardian: Automated compliance scanner that detects PII exposure, insecure logging, and tracking violations in your codebase to prevent regulatory fines.

flow-nexus-swarm

Enterprise-grade multi-agent swarm orchestration, event-driven workflow automation, and intelligent agent coordination for Claude Code.

taskyou

An autonomous AI-powered task management system with Kanban boards, git worktree isolation, and pluggable executors like Claude Code, Gemini, and OpenAI Codex.

metacognition

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

auto-skill-generator

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

agent-canvas

Orchestrate visual communication by drawing diagrams, flowcharts, and annotations on a TLDraw canvas via CLI. Ideal for architectural planning, PR reviews, and logging agent output.

verification-before-completion

Enforces a strict evidence-before-assertion protocol for coding agents, requiring fresh command-line verification output before any claim of completion, success, or bug fixes.