deepagents-implementation
Implements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, defining subagents, adding middleware, or setting up human-in-the-loop workflows.
senior-computer-vision
World-class computer vision skill for image/video processing, object detection, segmentation, and visual AI systems. Expertise in PyTorch, OpenCV, YOLO, SAM, diffusion models, and vision transformers. Includes 3D vision, video analysis, real-time processing, and production deployment. Use when building vision AI systems, implementing object detection, training custom vision models, or optimizing inference pipelines.
pal-mcp-server
AI orchestration and multi-model collaboration MCP server. Use when you need multi-model AI collaboration, code reviews, debugging assistance, planning, consensus building, or advanced reasoning across multiple AI providers (Gemini, OpenAI, Grok, Azure, Ollama, etc.).
claude-code-guide
Answer questions about Claude Code CLI, Claude Agent SDK, and Claude API. Use when asked about: - Claude Code features (hooks, skills, MCP servers, settings, IDE integrations, keyboard shortcuts) - Building custom agents with the Agent SDK - Claude API usage (tool use, vision, structured outputs, Anthropic SDK) Triggers: "Can Claude...", "Does Claude...", "How do I...", "claude code", "agent sdk", "anthropic api"
mcp-gateway
LiteLLM-RS MCP Gateway Architecture. Covers Model Context Protocol, JSON-RPC 2.0 implementation, multi-transport support (HTTP, SSE, WebSocket, Stdio), and permission system.
mc-waypoint
Labels a coordinate with a waypoint name for reasoning about spatial relationships. Use to mark important locations for navigation and planning
mc-training-capture
Enable or disable automatic training data capture (partial observation grid + optional ground truth).
pytorch-ml
Deep learning with PyTorch - model training, GPU acceleration, and data science workflows
chat-compactor
Generate structured session summaries optimized for future AI agent consumption. Use when (1) ending a coding/debugging session, (2) user says "compact", "summarize session", "save context", or "wrap up", (3) context window is getting long and continuity matters, (4) before switching tasks or taking a break. Produces machine-readable handoff documents that let the next session start fluently without re-explaining.
call-analysis
Analyzes sales call transcripts using the POWERFUL framework to extract insights and action items. Use this skill when reviewing call recordings, coaching reps, qualifying opportunities, or extracting deal intelligence from conversations.
prd-template
This skill should be used when the user asks to "create a PRD", "write requirements", "document a feature", "generate product spec", "define requirements", "write feature specifications", or when creating PRD documents from gathered requirements.
cold-call-scripts
Creates personalized cold call scripts using a proven 5-step framework. Use this skill when preparing for prospecting calls, coaching reps on call structure, or creating call templates for campaigns.
define-seo-strategy
Create a comprehensive SEO_STRATEGY.md covering both traditional SEO and Generative Engine Optimization (GEO) for AI platforms. Requires CUSTOMER.md to exist first. Includes platform-specific tactics for Google AI Overviews, ChatGPT, Perplexity, Claude, and Gemini with effort/impact prioritization.
craft-author-voice
Captures writing style/voice into AUTHOR_VOICE.md so AI can write like the user. Use when asked to match tone, write like me, replicate voice, or capture writing style for content generation.
optimize-prompt-token-efficiency
Iteratively optimizes prompts for token efficiency by maximizing information density - reduces verbosity, removes redundancy, tightens phrasing while preserving semantic content. Use when asked to compress, shorten, reduce tokens, tighten, maximize density, increase information density, or make a prompt more concise.
suno-upload
Upload a Suno prompt.md file to suno.com using Chrome automation with NO human intervention required. Parses the prompt file, navigates to Suno's Create interface, fills all form fields including sliders (lyrics, style, title, weirdness, style influence, vocal gender, exclude styles), and submits for song generation. Uses proven coordinate-based slider manipulation for reliable automation. Use this skill when the user asks to "upload to Suno", "create on Suno", "generate with Suno", "submit to Suno", or wants to automatically upload a generated prompt to the Suno website.
pandas-best-practices
Standards for efficient, readable, and performant data manipulation using Python's Pandas library.
summarize-experiment
Create a lightweight summary of experiment results from a completed (fine-tuned and evaluated) experiment. Use after run-experiment to capture key metrics from the experiment in textual form.
logseq-db-plugin-api
Essential knowledge for developing Logseq plugins for DB (database) graphs. Covers core APIs, event-driven updates with DB.onChanged, multi-layered tag detection, property value iteration, advanced query patterns (tag inheritance, or-join), and production-tested plugin architecture patterns. References production-validated code from logseq-checklist v1.0.0.
claude-agent-sdk-reference
Document for build custom AI agents with the Claude Agent SDK, include full SDK Reference and Example Codes.
skeleton-generate
Skills版エージェント骨格（CLAUDE.md, .codex/skills/, .codex/等）を生成し、初期設定を完了する。「スケルトン生成」「エージェント生成」「骨格作成」を依頼されたときに使用する。
