LLM 與 Agent

Work with ElevenLabs Conversational AI agents - initiate calls, retrieve transcripts, manage phone numbers, and analyze agent conversations. Use when building or testing voice AI applications.

Homeostatic sensor detecting requirements without implementation or test coverage. Scans for REQ-* keys in requirements docs and checks if they have corresponding code and tests. Use to find coverage gaps.

Use PROACTIVELY when enforcing TDD red-green-refactor, setting up test infrastructure, configuring coverage gates, or implementing the Testing Trophy model. Installs git hooks, npm scripts, and CLAUDE.md configuration to enforce test-first development. Supports coverage thresholds and test distribution analysis. Not for prototypes or projects without test requirements.

Discover and analyze Claude Code session logs from ~/.claude/projects, including finding the current session and extracting tool calls, user messages, and conversation history

Coordinate Tutopanda CLI and MCP to generate, edit, inspect, and preview documentary videos (video-audio-music blueprint with FinalVideo export). Use when users ask for Tutopanda to build, edit, or review movies inside Claude Code.

Share the current Claude Code session to claudereview.com for code review. Use this when the user wants to share their session, get a link to the conversation, or create a shareable review of the work done.

Universal test generation skill that works with any language or framework. Detects project conventions, generates unit/integration/API/validation tests, and evolves through learning. Use when user asks to "write tests", "create tests", "generate tests", "add test coverage", "test this function/class/component", or any testing-related request. Supports JavaScript, TypeScript, Python, PHP, Go, Java, Ruby, Rust, C#, and more.

Create, update, and maintain specialized AI agent prompts stored in XML and Markdown formats. This skill covers agent role definitions, capabilities, constraints, and best practices for agent prompt authoring. Use when creating new agent prompts, updating existing agents, understanding agent roles, or when users mention agent creation, agent prompts, or role-based AI systems.

Test creation and mocking (mockall, unit tests, integration tests, cargo test, AAA pattern). Use when writing tests, creating mocks, running cargo test, debugging test failures, asking about testing strategies, mockall usage, or test coverage.

Sleep science and Asleep sleep tracking knowledge. Use when working with sleep data, hypnograms, sleep stages, sleep insights, sleep metrics, or any sleepstar/agent-a/backend sleep-related code.

File-to-agent mapping and manifest generation for composite monorepo audits. Provides dynamic discovery of all config agents, generates structured audit manifests with priority-ordered spawn instructions, and handles library vs consumer repo exclusions. Use when performing root-level composite audits that scan repository for all config files and coordinate parallel agent execution across 26+ config domains.

Consult other AI models via GitHub Copilot CLI for second opinions, thorough analysis, or alternative perspectives. Supports Gemini 3 Pro Preview (gemini), Claude Opus 4.5 (opus), Claude Sonnet 4.5 (sonnet) and GPT-5.1-Codex-Max (codex). Use when user explicitly requests, when needing detailed analysis, when requiring additional help with an especially complex task, or when seeking alternative model perspectives.

Design, implement, and debug a custom ChatKit backend in Python that powers the ChatKit UI without Agent Builder, using the OpenAI Agents SDK (and optionally Gemini via an OpenAI-compatible endpoint). Use this Skill whenever the user wants to run ChatKit on their own backend, connect it to agents, or integrate ChatKit with a Python web framework (FastAPI, Django, etc.).

Use when executing implementation plans with independent tasks in the current session. Dispatches fresh subagent for each task with code review between tasks.

TacitChaos AI Agent Crew System - Pirate-themed orchestration with 23 officers and 90+ sailors

Skill providing design QA checklists and principles for visual review across lanes. Used by design-review agents to enforce hierarchy, spacing, color, and responsiveness.

Optimize content for AI search engines (ChatGPT, Perplexity, Google AI Overviews).Use when: (1) Auditing content for AI citability, (2) Writing content designed to becited by AI assistants, (3) Analyzing why content isn't being cited, (4) Adaptingexisting SEO content for answer engines. Spanish-language technical content focus.

Collaborative ideation and exploration before implementation. Triggers when creating features, building components, adding functionality, or starting creative work. Encourages brainstorming options, discussing trade-offs, and exploring possibilities together with the user before diving into code.

Generate project documentation including CONTENTS.md navigation files and AGENTS.md instructions. Use when creating documentation structure, project indexes, or AI agent configuration files.

Connect Claude Code with GitHub Issues for rapid problem resolution. This skill should be used when users need to manage, analyze, prioritize, and resolve GitHub issues automatically without manual intervention.