Claude Skills 列表

Use this skill when building real-time, bidirectional streaming applications with the Gemini Live API.

Use this skill for generative video editing, text-to-video, image-referenced video generation, and first-frame-to-video transition animations using the official google-genai SDK.

Get your project to 100% ✪ AI-readiness, fast — the AI auto-detects your stack and only asks for what it can't know (your goal and the human "why"). Least typing, maximum context....

Advanced .faf (Foundational AI-context Format) specialist. IANA-registered format, MCP server config, championship scoring, bi-directional sync.

Text-to-speech and speech-to-text using fal.ai audio models

Generate images and videos using fal.ai AI models

Platform APIs for model management, pricing, and usage tracking

Generate workflow JSON files for chaining AI models

Use for file-based context management, dynamic context discovery, and reducing context window bloat. Offload context to files for just-in-time loading.

Guide to selecting and optimizing embedding models for vector search applications.

Build evaluation frameworks for agent systems. Use when testing agent performance systematically, validating context engineering choices, or measuring improvements over time.

Use when a user asks to mine or update a private, evidence-backed work profile from local Claude Code, Codex, Copilot CLI, or OpenCode sessions.

Estimate whether a document's prose was written by AI, with the linguistic tells and honest abstention on non-prose. Use when the user asks whether an essay, report, CV,...

Reference patterns (upstream reports, not independently verified here) for building AI agents that autonomously discover, evaluate, and acquire token listings for cryptocurrency...

Documentation and capabilities reference for Daily

Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory

Build applications that programmatically interact with GitHub Copilot. The SDK wraps the Copilot CLI via JSON-RPC, providing session management, custom tools, hooks, MCP server...

Design role-based agents, tasks, crews, and flows with CrewAI.

When agent sessions generate millions of tokens of conversation history, compression becomes mandatory. The naive approach is aggressive compression to minimize tokens per request.

Language models exhibit predictable degradation patterns as context length increases. Understanding these patterns is essential for diagnosing failures and designing resilient...