向量嵌入
向量检索与嵌入工作流
papertrail
jwmossmoz
Query and download logs from SolarWinds Observability (formerly Papertrail) using the paperctl CLI. Use when: (1) Downloading logs from Taskcluster workers or other systems (2) Searching for specific log entries across systems (3) Investigating CI failures by pulling worker logs (4) Listing available entities (hosts) in SolarWinds Observability Triggers: "papertrail", "pull logs", "worker logs", "download logs", "search logs"
doc-to-vector-dataset-generator
patricio0312rev
Converts documents into clean, chunked datasets suitable for embeddings and vector search. Produces chunked JSONL files with metadata, deduplication logic, and quality checks. Use when preparing "training data", "vector datasets", "document processing", or "embedding data".
spice-setup
spiceai
Get started with Spice.ai — install the runtime, initialize a project, run the runtime, and use the CLI. Use when setting up a new Spice project, installing Spice, running spice run, looking up CLI commands, API endpoints, deployment models, or creating a spicepod.yaml.
always-on-agent-architecture
curiositech
Architecture and systems design for building always-on AI agents with episodic memory. Covers the memory hierarchy (core/recall/archival), persistence layers, agent server infrastructure, vector stores, and framework selection. Provides concrete deployment patterns for agents that maintain identity and learn across sessions. Activate on: "always-on agent", "persistent agent architecture", "episodic memory system", "agent memory design", "long-running agent", "stateful agent", "agent that remembers", "MemGPT architecture", "Letta deployment", "/always-on-agent-architecture". NOT for: choosing what data to feed the agent (use always-on-agent-inputs), brainstorming applications (use always-on-agent-applications), safety and privacy concerns (use always-on-agent-safety), general agentic patterns (use agentic-patterns).
spice-search
spiceai
Search data using vector similarity, full-text keywords, or hybrid methods with Reciprocal Rank Fusion (RRF). Use when setting up embeddings for search, configuring full-text indexing, writing vector_search/text_search/rrf SQL queries, using the /v1/search HTTP API, or configuring vector engines like S3 Vectors.
ai-engineer
curiositech
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use PROACTIVELY for LLM features, chatbots, AI agents, or AI-powered applications.
agent-context-partitioner
curiositech
Algorithmic skill for designing evidence-backed partitions of LLM context or task DAGs across K agents. Covers two modes: (A) online/reactive spawning under context pressure, and (B) static pre-planned DAG execution with graph min-cut optimization. Encodes algorithms for sequence-stable clustering, dynamic K selection, token-budget-aware partitioning, and handoff protocol design. Use when designing multi-agent systems, deciding when and how many agents to spawn, or optimizing a task DAG for token efficiency. NOT for one bounded task that does not benefit from parallelism, runtime scheduling or authorization policy, or comparing vectors whose embedding-space identities are unknown or incompatible.
index-status
agentika-labs
Use this skill when the user asks to "check index status", "is the index healthy", "index diagnostics", "search index health", or mentions keywords related to verifying grepika search index state.
feishu-approval
alextangson
飞书审批流管理 Skill。获取审批定义、提交审批实例、添加评论、转办、撤回。当需要自动化提交审批或管理审批流程时使用此 Skill。
vector-db-setup
patricio0312rev
Sets up vector databases for semantic search including Pinecone, Chroma, pgvector, and Qdrant with embedding generation and similarity search. Use when users request "vector database", "semantic search", "embeddings storage", "Pinecone setup", or "similarity search".
spicepod-config
spiceai
Create and configure Spicepod manifests (spicepod.yaml). Use when asked to "create a spicepod", "configure spicepod.yaml", "set up a Spice app", "initialize Spice project", "configure caching", "set up observability", "build a data app", or "create an AI application with Spice".
iterative-retrieval
peopleforrester
Progressive context refinement pattern for subagents. Solves the problem of agents not knowing what context they need until they start working. Uses a 4-phase loop: DISPATCH, EVALUATE, REFINE, LOOP.
always-on-agent-inputs
curiositech
How to design contextual inputs for an always-on AI agent with episodic memory. Covers what data to feed the agent, how to structure observations and triggers, ambient context capture (screen, audio, calendar), context window budgeting, and retrieval strategies that keep the agent grounded in what's actually happening. Activate on: "what should the agent observe", "context inputs for agent", "ambient context capture", "agent triggers", "agent input design", "screenpipe integration", "context window budget", "what data to feed my agent", "/always-on-agent-inputs". NOT for: memory architecture and storage (use always-on-agent-architecture), application ideas (use always-on-agent-applications), safety concerns (use always-on-agent-safety).
searching-documents-with-google-drive
kjgarza
Search and download documents from Google Drive using rclone. Exports Google Docs as Markdown by default. Use when users ask to find files in Google Drive, download documents from Drive, export Google Docs, or sync Drive content locally. Triggers on requests mentioning Google Drive, gdrive, or document downloads from cloud storage.
paper-digest
iamseungpil
Generate shareable paper summaries for Discord/Slack/Twitter. Use when user provides arxiv paper(s) and wants a digestible summary to share. Triggers on phrases like "논문 요약", "paper summary", "share this paper", "디스코드에 공유", "summarize for sharing". Produces insight-centered single-paragraph summaries that explain WHY research matters, not just WHAT it does.
literature-review
kjgarza
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).
zotero-mcp-code
kerim
Search Zotero library using code execution for efficient multi-strategy searches without crash risks. Use this skill when the user needs comprehensive Zotero searches with automatic deduplication and ranking.
personal-material-search
alchaincyf
快速搜索用户的真实经历、观点和案例素材库（1800+条记录），为内容增加真实性和可信度。当用户提到"真实经历"、"个人案例"、"有根据"、"实际经验"、"素材库"、"找例子"时使用此技能。
annas-archive-ebooks
ratacat
Use when needing to look up book content, find a book by title/author, download an ebook, or reference material from a published book. Triggers on book lookups, ebook downloads, "find the book", "get the PDF/EPUB of". Downloads produce PDF/EPUB/MOBI files - use ebook-extractor skill to convert to text.
unifuncs-search
UniFuncs
使用 UniFuncs API 进行实时网络搜索，支持全球和中国地域，获取最新网络内容和新闻。当用户需要搜索、查找、联网获取信息时使用。
sec-edgar-skill
rebyteai-template
SEC EDGAR filing analysis using EdgarTools. Use when user asks about SEC filings, company financials, 10-K/10-Q analysis, insider trading, revenue trends, or financial comparisons. Triggers include "SEC filing", "10-K", "10-Q", "8-K", "EDGAR", "company financials", "revenue", "earnings", "insider trading", "financial statements". Do NOT use for real-time stock prices or market data (use market-data skill instead).
brave-search
ratacat
Use when user asks to search the web, look something up online, find current/recent/latest information, or needs cited answers. Triggers on "search", "look up", "find out about", "what is the current/latest", image searches, news lookups. NOT for searching code/files—only for web/internet searches.
debugging
ratacat
Systematic debugging that identifies root causes rather than treating symptoms. Uses sequential thinking for complex analysis, web search for research, and structured investigation to avoid circular reasoning and whack-a-mole fixes.
anipy-cli
Linaqruf
This skill should be used when the user asks to play, watch, stream, search, download, or binge anime; continue watching or check anime history; install, setup, configure, update, or fix anipy-cli; change video player or set anime quality; troubleshoot anime playback issues; or mentions anipy-cli by name. Triggers on "play anime", "watch frieren", "stream one piece dubbed", "download anime episodes", "binge naruto 1-10", "show anime history", "next episode", "continue watching", "change player to mpv", "set quality to 1080", "anipy-cli not working", "player not found", "anipy-cli", "anime from terminal".