Scan to join WeChat grouppersonjakexiaoNo key required
my-history-insight
A skill to analyze past Claude Code session records to extract insights. Used for '히스토리 분석', '세션 분석', '내 작업 패턴 분석', 'history insight', /history-insight requests.
download7deployed_code—star0
Skill Directory
AI Skill Directory
Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
personjakexiaoNo key required
ml-experimentation
Conduct machine learning experiments from planning through evaluation and report writing. Use when running ML experiments, testing hypotheses, training models, or writing up results. Covers single-hyp…
download7deployed_code—star27
personjakexiaoNo key required
portfolio-analyzer
A comprehensive skill for analyzing, stress-testing, and optimizing a user's investment portfolio across risks, performance, and diversification.
download7deployed_code—star57
personjakexiaoNo key required
langchain-human-in-the-loop
Add human oversight to LangChain agents using HITL middleware - includes interrupts, approval workflows, edit/reject decisions, and checkpoints
download7deployed_code—star1
personjakexiaoNo key required
langchain-models
Initialize and use LangChain chat models - includes provider selection (OpenAI, Anthropic, Google), model configuration, and invocation patterns
download7deployed_code—star1
personjakexiaoNo key required
pomasa
Generate declarative multi-agent systems (MAS) using POMASA pattern language. Use when building agent pipelines, orchestrating multiple AI agents, or creating research automation workflows. Supports p…
download7deployed_code—star28
personjakexiaoNo key required
llm-training
Use when "training LLM", "finetuning", "RLHF", "distributed training", "DeepSpeed", "Accelerate", "PyTorch Lightning", "Ray Train", "TRL", "Unsloth", "LoRA training", "flash attention", "gradient chec…
download7deployed_code—star1
personjakexiaoNo key required
rag-frameworks
Use when "RAG", "retrieval augmented generation", "LangChain", "LlamaIndex", "sentence transformers", "embeddings", "document QA", "chatbot with documents", "semantic search"
download7deployed_code—star1
personjakexiaoNo key required
my-fetch-youtube
A skill that, upon receiving a YouTube URL, extracts subtitles, automatically corrects subtitle errors using web search, and then provides a summary-insights-full translation. Used for requests like '…
download7deployed_code—star0
personjakexiaoNo key required
youtube-ingestion
Ingest YouTube videos into the vault. Triggers when user pastes a YouTube URL (youtube.com/watch or youtu.be). Fetches transcript, creates transcript note and summary note. User may provide additional…
download7deployed_code—star27
personjakexiaoNo key required
deepagents-hitl
Implement a manual approval workflow in Deep Agents, using the interruptOn parameter to manually intervene in sensitive tool operations.
download7deployed_code—star1
personjakexiaoNo key required
langchain-chat-models
A guide to integrating chat models in LangChain, including OpenAI, Anthropic, Google, Azure, and Bedrock
download7deployed_code—star1
personjakexiaoNo key required
langgraph-streaming
Stream real-time updates from LangGraph: Streaming modes (values, updates, messages, custom, debug) for reactive UX
download7deployed_code—star1
personjakexiaoNo key required
email-generation
Generate cold outreach emails from a contact CSV and a self-contained prompt template. Campaign-agnostic — no hardcoded product or voice. The prompt template (from email-prompt-building skill) contain…
download7deployed_code—star63
personjakexiaoNo key required
huggingface-tokenizers
Use when "tokenizers", "HuggingFace tokenizer", "BPE", "WordPiece", or asking about "train tokenizer", "custom vocabulary", "tokenization", "subword", "fast tokenizer", "encode text"
download7deployed_code—star1
personjakexiaoNo key required
image-enhancement
Use when "improving image quality", "enhancing screenshots", "upscaling images", "sharpening photos", or asking about "image optimization", "screenshot quality", "resolution improvement"
download7deployed_code—star1
personjakexiaoNo key required
ai-native-product
This skill should be used when the user needs to build AI-native products with agency-control tradeoffs, calibration loops, and eval strategies. Use when building AI agents, LLM features, or products …
download7deployed_code—star12
personjakexiaoNo key required
manim-personal-style
Plan and implement Manim Community (ManimCE) animations: use when users want 3Blue1Brown-style explainer videos, need scene-by-scene planning, or ask for ManimCE code/visualizations. Must gather requi…
download7deployed_code—star1
personjakexiaoNo key required
deepagents-overview
Understanding the Deep Agents framework - what they are, how to create them using createDeepAgent, and the agent harness architecture, including built-in planning, file system, and sub-agent middlewar…
download7deployed_code—star1
personjakexiaoNo key required
langchain-embeddings
A guide to integrating embedding models in LangChain, including OpenAI, Azure, and local embeddings
download7deployed_code—star1
personjakexiaoNo key required
omni-ai-optimizer
Optimize your Omni Analytics model for Blobby, Omni's AI assistant — configure ai_context, ai_fields, sample_queries, and create AI-specific topic extensions. Use this skill whenever someone wants to …
download7deployed_code—star4
personjakexiaoNo key required
dspy-prompting
Use when "DSPy", "declarative prompting", "automatic prompt optimization", "Stanford NLP", or asking about "optimizing prompts", "prompt compilation", "modular LLM programming", "chain of thought", "f…
download7deployed_code—star1
personjakexiaoNo key required
nemo-evaluator
Use when evaluating LLMs, running benchmarks like MMLU/HumanEval/GSM8K, setting up evaluation pipelines, or asking about "NeMo Evaluator", "LLM benchmarking", "model evaluation", "MMLU", "HumanEval", …
download7deployed_code—star1
personjakexiaoNo key required
youtube-transcribe
Use when "youtube transcript", "extract subtitles", "video captions", "get transcript", "video to text"
download7deployed_code—star1