向量嵌入
向量检索与嵌入工作流
advanced-agentdb-vector-search-implementation
slurpyb
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, and hybrid search for distributed AI systems.
ark-embedding
jneless
skill of vole engine ark model platform embedding api
web-search-browser
coopergwrenn
Search the web, browse pages, take screenshots, scrape data, and automate web interactions. Use when the user asks to search the web, look something up, visit a website, take a screenshot, or scrape a page.
google-places
moldable-ai
Search and fetch place details via Google Places API (New) through aivault (no API key in skill runtime).
astkit-tooling
ClaudiuCeia
Use when a TypeScript/JavaScript task needs symbol navigation (nav declarations definition references), structural pattern search (search), structural rewrites (patch), or reference-based blast-radius estimation (code-rank). Prefer for compact, scoped repository analysis and migration work; do not use for runtime-path proofs, correctness guarantees, or replacing compiler/tests.
forvm
pompeii-labs
Connect to the collective intelligence network for AI agents. Share knowledge and query what others have learned.
american-airlines
CodeDraig
Book flights, manage AAdvantage miles, check flight status, and access American Airlines services
opencode-crane
AugustChaoTW
CRANE — Autonomous research assistant MCP server with 124 tools covering the full academic research lifecycle. Key trigger phrases: "paper trace" / "do paper trace" → trace_paper; "evaluate paper" / "score paper" → evaluate_paper_v2; "review paper" / "detect defects" → crane_review_full; "diagnose paper" / "diagnose section" → crane_diagnose; "submission check" / "投稿前檢查" → run_submission_check; "simulate submission" / "acceptance probability" → simulate_submission_outcome; "review pipeline" / "full review" → run_review_pipeline; "build index" / "scan paper" → build_paper_index; "semantic search" / "find similar" → semantic_search; "ask library" / "rag" → ask_library; "match journal" → match_journal_v2; "citation graph" → visualize_citations; "karpathy review" / "code review" → karpathy_review; "literature review" / "search papers" → run_pipeline(pipeline="literature-review"); "init project" / "setup" → run_pipeline(pipeline="full-setup"); "what can crane do" / "help" → crane_help(topic=...) or list_workflows().
linkup
trancong12102
Real-time web search and content retrieval via the Linkup API. Use when up-to-date information from the web, source-backed answers, or direct page content retrieval is required.
prompt-lookup
baotoq
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
content-strategy
Jackiexiao
（中文）When the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "content ideas," "blog strategy," "topic clusters," or "content planning." For writing individual pieces, see copywriting. For SEO-specific audits, see seo-audit.
exa
edxeth
Searches the web using Exa's neural embeddings-based search API. Use when needing real-time web information to answer questions, verify facts, debug issues, find code examples, research topics, or clear doubts with authoritative sources. Best for open-ended research, fact-checking, troubleshooting errors with web context, and getting AI answers with citations.
clawddocs
cgk-platform
Clawdbot documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all Clawdbot features
vault-propose-related
uhop
'Propose missing related: entries for vault notes by reviewing BGE-retrieval candidates. Use when the user says /vault propose-related, asks to densify cross-references in the vault, or wants to expand related: arrays without reading every note manually. Loads top-N nearest neighbours per source note (excluding existing related: and body wikilinks), reasons about which are genuine semantic matches, writes accepted proposals to a review note in the vault.'
Engram Conditional Memory (N-gram Hash Lookup + Offload/Prefetch)
sovr610
This skill should be used when the user asks to "implement engram memory", "add N-gram hash lookup", "implement tokenizer compression", "add engram layer", "implement CPU offload embeddings", "add async prefetch", "implement multi-head hashing", "add context-aware gating", "implement depthwise causal conv", "add engram encoder", "implement hash embedding retrieval", "add collision mitigation", "implement offloadable embedding", "add prefetch scheduler", "implement engram augmented layer", "add residual fusion", "implement RMSNorm gating", "add engram telemetry", "implement streaming N-gram cache", "add prime-sized hash tables", "implement tokenizer equivalence merging", or mentions engram memory, N-gram hashing, deterministic addressing, CPU offload + prefetch, tokenizer compression, context-aware gating, depthwise causal convolution, hash embedding, encoder-competition mode, layer-augmentation mode, or DeepSeek-style conditional memory in the cognitive pipeline.
idx-md
Keith-CY
AgentSkill for https://idx.md. Use the index to locate AI agent library topics and fetch HEAD/BODY markdown.
seekdb-docs
ofx-labs
Provide SeekDB official docs (built-in en-US/zh-CN content + menu maps). Use for docs lookup across SQL/SDK APIs, vector/hybrid search, deployment/ops, integrations (MCP/plugins), etc.
Mindflow
hrshitkunwar-tech
Collects saved content and bookmarks from social media platforms, organizes them using AI, and generates searchable mind maps for fast knowledge discovery and insight generation.
SKILL.md — Web Research
iamthetonyb
Never present speculation as fact
numpy-sorting
cuba6112
Sorting and searching algorithms including O(n) partitioning, binary search, and hierarchical multi-key sorting. Triggers: sort, argsort, partition, searchsorted, lexsort, nan sort order.
ace-search
PandAddKai
'Use when the task is read-only codebase discovery/search (查找/搜索/定位): find files, functions, classes, call sites, tests, or "where is X implemented" questions; prefer Augment Context Engine MCP (augment-context-engine) codebase retrieval over grep/rg.'
ecosystem-primer
Adrain11
"INVOKE FIRST for any LangChain / LangGraph / Deep Agents agent building project before consulting other skills or writing any agent code. Required starting point for up to date info on framework selection (LangChain vs LangGraph vs Deep Agents vs hybrid composition), agent patterns, install, environment setup, and which skill to load next."
llm-tldr
Tiberriver256
Summarize and navigate this repo with the llm-tldr CLI (tree/structure/context/semantic search). Use when you need LLM-ready summaries of files or symbols, fast codebase orientation, or behavior-based search before editing.
local-memory-search
blackbasilisk
Local, offline semantic search over OpenClaw memory files (MEMORY.md and memory/*.md) using Python embeddings + FAISS (no online LLM/API). Use when Dave asks for "memory search" without cloud billing, wants semantic recall across notes, or wants to share a reusable local-memory semantic search skill.