向量嵌入
向量检索与嵌入工作流
s2-geometry-spatial-indexing
copyleftdev
Index and query geospatial data using Google's S2 Geometry library. Emphasizes hierarchical cell decomposition, Hilbert curves for locality preservation, and efficient spatial operations on spherical geometry. Use when building location-based services, proximity search, geofencing, or any system that needs to efficiently query geographic data.
agent-memory
WHQ25
Long-term memory for AI coding agents via agmem CLI. Persist cross-project knowledge — bug fixes, library quirks, design decisions, user preferences — across sessions. Use when: (1) fixing a non-trivial bug worth remembering, (2) discovering undocumented library/API behavior, (3) making architecture decisions, (4) user corrects your approach or states a preference, (5) starting a new task and want to check for prior knowledge, (6) encountering an error that might have been seen before.
conversation-search
dhughes
Search indexed conversation history to find past conversations, locate when topics were discussed, or identify which project conversations occurred in. Use when user asks questions like "when did we discuss X?", "find conversations about Y", "in which project did we talk about Z?", or "show me conversations mentioning W". Works across all projects or within current project.
brainstorm
iulspop
Facilitates solution ideation with clear trade-offs and a final recommendation. Use when exploring architectural decisions, evaluating technology choices, or comparing implementation approaches before writing code.
keyword-based-llm-eval
shimo4228
"Use when evaluating LLM-generated structured output against expected results using keyword matching and F1 metrics."
droyd
droyd-ai
Crypto Trading Crypto Search Crypto Token Filter Virality Analysis Agent File Management Skill & File Discovery Agent Discovery Scheduled Tasks -- AI crypto trading wallet via natural language. Use when the user wants to execute AI research tasks, trade crypto autonomously, search crypto content/news, filter projects by market criteria, analyze social virality and mention velocity, manage trading positions, follow/unfollow agents, upload/read/search/delete agent files, search agent skills, create new agents, discover and rank agents, manage scheduled tasks, or interact with DROYD agents. Supports agent chat (research, trading, data analysis), content search (semantic/recent/auto), project discovery (by name/symbol/address/concept), project filtering (market cap, momentum, technical indicators, RSI), watchlist management (agent/swarm/combined), virality analysis (mention velocity, z-scores, trend signals), autonomous trading with stop losses, take profits, quant-based strategies, agent file operations (read/write/search/remove), skill discovery (search across agent/swarm/droyd/paid), agent creation with wallet provisioning, agent discovery (filter/rank agents by PnL, revenue, followers; lookup by ID/name/wallet/token), and scheduled task management (create/update/delete/get tasks with cron scheduling). Works with Solana (trading) and Ethereum, Base, Arbitrum for token filtering + research.
domain-name-generator
theepan
Generate short, pronounceable, catchy domain names for products, startups, or projects. Use when the user asks for domain name ideas, brand names, startup names, or wants help naming something with an available web domain.
conversation-history-setup
dhughes
Guide users through initial setup of conversation history indexing. Use when user asks about setting up conversation history, indexing past conversations, or when search returns no results and the database may be empty.
meyers-effective-cpp
copyleftdev
Write C++ code following Scott Meyers' Effective C++ principles. Emphasizes practical wisdom, specific guidelines with clear rationale, and avoiding common pitfalls. Use when writing production C++ code that must be correct, maintainable, and efficient.
skill-from-github
SebastiaanWouters
Create skills by learning from high-quality GitHub projects
google-search-serper
minilozio
Google Search powered by Serper.dev API — 9 search types: web, news, images, videos, places, shopping, scholar, patents, autocomplete. Returns Knowledge Graph, Answer Box, People Also Ask, and Related Searches. Use when asked to Google something, search the web for current info, find news, look up images, research academic papers, find local places, or when the user needs richer search results than basic web search. Also use when Brave Search results are insufficient or the user explicitly wants Google results.
creative-direction-council
antonioc-cl
Expert creative direction council with 6 advisors (Vignelli, Draplin, Bierut, Scher, Sagmeister, Carson) for visual identity, branding, and design systems.
openclaw-serper
nesdeq
Searches Google and extracts full page content from every result via trafilatura. Returns clean readable text, not just snippets. Use when the user needs web search, research, current events, news, factual lookups, product comparisons, technical documentation, or any question requiring up-to-date information from the internet.
x-research
skillhq
General-purpose X/Twitter research agent. Searches X for real-time perspectives, dev discussions, product feedback, cultural takes, breaking news, and expert opinions. Works like a web research agent but uses X as the source. Use when: (1) user says "x research", "search x for", "search twitter for", "what are people saying about", "what's twitter saying", "check x for", "x search", "/x-research", (2) user is working on something where recent X discourse would provide useful context (new library releases, API changes, product launches, cultural events, industry drama), (3) user wants to find what devs/experts/community thinks about a topic. NOT for: posting tweets, account management, or historical archive searches beyond 7 days.
ai-model-selector
jaymay549
"Use when selecting AI models, configuring API parameters, or implementing LLM calls. Covers OpenAI (GPT-5.2, GPT-5.1, GPT-4.1, o3), Anthropic (Claude 4.5), Google (Gemini 2.5/3), DeepSeek (V3.2, R1), and embedding models with specs, gotchas, and code templates."
atlassian-usage
dhughes
This skill should be used when the user asks to "search jira", "find tickets", "look up an issue", "search confluence", "find pages", "read a document", "create a ticket", "update an issue", "add a comment", mentions JQL, CQL, Atlassian, Jira issues, Confluence pages, or provides an Atlassian URL (*.atlassian.net). Provides guidance for using the atl CLI to interact with Atlassian products.
postgresql-table-design
dereknex
Design a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features
building-rag-systems
sumik5
Comprehensive RAG (Retrieval-Augmented Generation) system building guide covering data loading pipelines (11 source types including Word, PDF, CSV, audio, video, multimodal), data preparation (metadata enrichment, text quality enhancement, 5 chunking strategies from character to agentic), and full RAG architecture overview with Python. Use when building RAG applications, designing data ingestion pipelines, or implementing text chunking strategies. For Python language best practices, use developing-python instead. For LLMOps operational framework, use practicing-llmops. For JavaScript/LangChain.js RAG in web apps with Vercel AI SDK, see integrating-ai-web-apps.
weekly-report
SerendipityOneInc
Generate weekly work report from GitHub, Linear, and Lark data (周报生成 - 从 GitHub、Linear 和飞书数据自动生成周报)
md-book
terraphim
MD-Book documentation generator skill. Use when working with MD-Book, a modern mdbook replacement for generating HTML documentation from Markdown files. Supports syntax highlighting, live reload, Pagefind search, and Tera templates.
content-strategy
Jackiexiao
"Plan content strategy, topic selection, and publishing priorities for SaaS/software products."
seo-ai-search
johnpang1020
Expert SEO + AI search optimizer. Generates dynamic metadata, JSON-LD structured data (Schema.org), Open Graph / Twitter / Facebook tags, canonical URLs, hreflang, semantic markup guidance. Improves AI discoverability via entity linking, intent signals, context relevance, knowledge graph hints. Use when user asks for: SEOHead React component, AI-optimized content/structure, SPA crawlability, rich results, schema validation, or any SEO/AI-search task.
misc
SerendipityOneInc
Miscellaneous tools - train tickets (12306), flight info (Variflight), accommodation (Airbnb), and social media (Rednote/Xiaohongshu)
data-engineering-ai-ml
legout
"AI/ML data pipelines: embedding generation, vector databases, RAG patterns, LLM monitoring, and batch inference workflows."