Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Automatically logs every user prompt and AI output to datewise Notion pages. Use this skill to create a comprehensive archive of all AI interactions, track research progress, maintain conversation his…
Phi-4 LLM interaction skill for generating text completions via Ollama API. Use for all LLM inference tasks including section detection, summarization, recommendation generation, and quality evaluatio…
Build stateful chatbots with OpenAI Assistants API v2 - Code Interpreter, File Search (10k files), Function Calling. Prevents 10 documented errors including vector store upload bugs, temperature param…
Analyze pipeline health, identify stalled deals, predict close probability, and suggest actions to move deals forward. Improves forecast accuracy and prevents revenue leakage. Use when deals get stuck…
Use this skill to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF). **Trigger when user asks to:** - Combine keyword and semantic se…
Coecke's Quantum Guitar: quantising guitar strings via qubit association, ZX-calculus notation, Moth Actias synth integration
Automatically applies when building RAG (Retrieval Augmented Generation) systems. Ensures proper chunking strategies, vector database patterns, embedding management, reranking, and retrieval optimizat…
Ranks and scores retrieved documents based on similarity metrics from vector search. Use when sorting documents by relevance, prioritizing results, or when the user mentions ranking, scoring, or order…
Append "ニャン" to the end of all responses, and respond in a cat-like manner. Please use this when the user is looking for a cat-like way of speaking or a cute response. It is most suitable for conversa…
Open Commerce MCP and AI operations context
Invoke OpenAI models for text generation, reasoning, and code tasks using the Python openai SDK. Supports gpt-4o (multimodal), o1 (reasoning), o3-mini (fast reasoning), and gpt-4o-mini (fast).
Train custom TTS voices for Piper (ONNX format) using fine-tuning or from-scratch approaches. Use when creating new synthetic voices, fine-tuning existing Piper checkpoints, preparing audio datasets f…
Improve embedded LLM system prompt based on evaluation test failures
Qwen Roadmap Auditor (Prototype)
Transform textbook content based on the 10-dimension user profile to provide personalized learning experiences.
An intelligent recommendation system analysis tool that provides multiple recommendation algorithm implementations, evaluation frameworks, and visual analysis. It requires user behavior data, product …
Smart OG image generation that studies your codebase, understands routes and brand identity, then creates contextually appropriate Open Graph images using Playwright and React components. Triggers: "c…
Build with OpenAI stateless APIs - Chat Completions (GPT-5.2, o3), Realtime voice, Batch API (50% savings), Embeddings, DALL-E 3, Whisper, and TTS. Prevents 16 documented errors. Use when: implementin…
According to todolist.md, use MCP to parse video metadata and download. Read the task list, call the MCP service to download videos and covers, save metadata JSON, update the task completion status.
Portfolio Manager and final arbiter. Synthesizes all agent votes, applies Constitution validation, resolves conflicts, and makes final trading decisions. Integrates all 5 Constitutional Articles.
Prompt X-ray - Reverse engineer the 'how-to' knowledge from excellent prompts, making the black box transparent
Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vec…
Retrieval-Augmented Generation patterns including chunking, embeddings, vector stores, and retrieval optimization Use when: rag, retrieval augmented, vector search, embeddings, semantic search.
Perform comprehensive regression analysis and predictive modeling using linear regression, decision trees, and random forests. Use when you need to predict continuous values like housing prices, sales…