Scan to join WeChat grouppersonjakexiaoAPI key: unconfirmed
natural-language-postgres
Chat app that lets you ask questions in plain English and query your PostgreSQL database.
download7deployed_code—star1
Skill Directory
AI Skill Directory
Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
personjakexiaoAPI key: unconfirmed
ai-sdr-agent
Create an instant AI SDR (Sales Development Representative) agent for any website using HeyGen LiveAvatar. Use this when the user wants to create an AI sales rep, AI SDR, or AI avatar that can talk ab…
download7deployed_code—star0
personjakexiaoAPI key: unconfirmed
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
personjakexiaoAPI key: unconfirmed
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
personjakexiaoAPI key: unconfirmed
deepagents-hitl
Implement a manual approval workflow in Deep Agents, using the interruptOn parameter to manually intervene in sensitive tool operations.
download7deployed_code—star1
personjakexiaoAPI key: unconfirmed
langchain-chat-models
A guide to integrating chat models in LangChain, including OpenAI, Anthropic, Google, Azure, and Bedrock
download7deployed_code—star1
personjakexiaoAPI key: unconfirmed
langgraph-streaming
Stream real-time updates from LangGraph: Streaming modes (values, updates, messages, custom, debug) for reactive UX
download7deployed_code—star1
personjakexiaoAPI key: unconfirmed
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
personjakexiaoAPI key: unconfirmed
langchain-retrieval-agent
AI agent with retrieval tool for document Q&A using RAG and LangGraph.
download7deployed_code—star1
personjakexiaoAPI key: unconfirmed
day5-fetch-and-digest
AI Native Camp Day 5 content digestion skill creation. Create and utilize three skills: fetch-tweet, fetch-youtube, and content-digest. Use for requests related to 'Day 5', 'fetch', 'content skill', '…
download7deployed_code—star0
personjakexiaoAPI key: unconfirmed
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
personjakexiaoAPI key: unconfirmed
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
personjakexiaoAPI key: unconfirmed
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
personjakexiaoAPI key: unconfirmed
langchain-embeddings
A guide to integrating embedding models in LangChain, including OpenAI, Azure, and local embeddings
download7deployed_code—star1
personjakexiaoAPI key: unconfirmed
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
personjakexiaoAPI key: unconfirmed
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
personjakexiaoAPI key: unconfirmed
telegram-channel-reading
Reading and analysis of public Telegram channels. Upload before working with readTelegramChannel: channel analysis, channel comparison, content search, overview of the latest posts.
download7deployed_code—star0
personjakexiaoAPI key: unconfirmed
my-fetch-tweet
A skill that, when given an X/Twitter URL, fetches the original tweet and provides a summary-insight-full translation. Used for 'tweet translation', 'fetch tweet', 'X post' requests.
download7deployed_code—star0
personjakexiaoAPI key: unconfirmed
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
personjakexiaoAPI key: unconfirmed
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
personjakexiaoAPI key: unconfirmed
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
personjakexiaoAPI key: unconfirmed
langchain-models
Initialize and use LangChain chat models - includes provider selection (OpenAI, Anthropic, Google), model configuration, and invocation patterns
download7deployed_code—star1
personjakexiaoAPI key: unconfirmed
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
personjakexiaoAPI key: unconfirmed
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