Embeddings
Vector embeddings and similarity
recall
by rocky2431
Search and manage cross-session memory. Query past sessions by keyword, semantic similarity, or hybrid search. Save summaries and tags for future recall.
agently-task-dev
by okwinds
Use only when the user explicitly wants to build with the Agently framework (mentions Agently/agently/OpenAICompatible/TriggerFlow/ToolExtension/ChromaCollection, or says “用 Agently 做/用 agently 做”). Deliver runnable code plus regression tests validating schema/ensure_keys and streaming (delta/instant/streaming_parse), with optional tools (Search/Browse/MCP), TriggerFlow orchestration, KB (ChromaDB), and serviceization (SSE/WS/HTTP). Do not use for generic streaming/testing questions that are not about Agently, or for prompt-only writing without tests/structure.
vault-search
by Roasbeef
Semantic search and Dataview-style queries across the Obsidian vault. Use when searching for notes by meaning, finding related content, querying frontmatter metadata, or answering questions about vault contents. Trigger phrases include "search vault", "find notes about", "what do I have on", "related notes", "list tasks", "show positions".
slack
by i9wa4
Fetch Slack thread from URL using API directly (no MCP server needed). Use when: - User provides a Slack message URL - User says "read this slack thread" or "fetch slack thread" - User wants to see conversation context from Slack - User wants to search Slack messages - User wants to fetch channel history (e.g., Google Calendar DM)
earnings-financial-guidance
by OctagonAI
Extract and analyze financial guidance and forward-looking statements from earnings transcripts, including segment guidance, risk factors, and guidance vs. actuals comparison.
image-comparison-tool
by dkyazzentwatwa
Compare images with SSIM similarity scoring, pixel difference highlighting, and side-by-side visualization.
business-competitor-analysis
by kenneth-liao
Perform comprehensive competitor analysis for any business. Produces an executive-summary markdown report with target customer profile, market positioning, pricing/business model, product features, funding/company size, SWOT analysis, and competitive matrix. All findings are data-grounded. Use when the user asks to analyze competitors, understand competitive landscape, compare a business to alternatives, or perform market research.
youtube-data
by kenneth-liao
"Retrieve YouTube data using the YouTube Data API. Use when you need to search videos, get video/channel details, fetch transcripts, read comments, or discover trending/related content."
beepctl
by blqke
Use when sending messages, searching chats, or managing conversations across messaging platforms (Telegram, WhatsApp, Slack, iMessage, etc.) via Beeper Desktop API.
brave-search
by EthanAlgoX
Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.
deepThink
by LdotJdot
"通用问题诊断与深度分析 Skill。适用于代码、系统、业务、学习规划等需要严肃推理和可执行结论的任务。"
coding
by LdotJdot
"Local coding workflow: read/write/list_dir/exec，加上 Grep + SemanticSearch 的纯文本搜索（见 search skill）。Use when: editing code, building, refactoring, or exploring a codebase. Success = compile passes; user runs the program."
search
by LdotJdot
"高效纯文本 / 代码搜索：优先用 Grep 做精确 / 正则匹配，配合 SemanticSearch 做语义级定位。只针对工作区内的文本与代码文件。"
session-navigation
by Factory-AI
Navigate, search, and manage Droid sessions. Use when the user wants to: - List recent sessions - Search session history for specific topics or patterns - Resume a previous session - Get details about what was accomplished in a session - Find sessions by project, date, or content
ai-data-engineering
by ancoleman
Data pipelines, feature stores, and embedding generation for AI/ML systems. Use when building RAG pipelines, ML feature serving, or data transformations. Covers feature stores (Feast, Tecton), embedding pipelines, chunking strategies, orchestration (Dagster, Prefect, Airflow), dbt transformations, data versioning (LakeFS), and experiment tracking (MLflow, W&B).
getajob
by jackjin1997
AI-powered job search assistant. Scan job listings, track applications, maintain dream company lists, and generate tailored resumes and cover letters. Use when the user wants to find jobs, run a job scan, set up job search, track applications, or prepare application materials.
flightclaw
by jackculpan
Track flight prices using Google Flights data. Search flights, find cheapest dates, filter by airline/time/duration/price, track routes over time, and get alerts when prices drop. Also runs as an MCP server. Requires Python 3.10+ and the 'flights' and 'mcp' pip packages. Run setup.sh to install dependencies.
context7-cli
by Mic92
Fetch up-to-date library documentation from Context7. Use for getting code examples and API docs for any library.
db-cli
by Mic92
Search Deutsche Bahn train connections. Use for finding train routes, schedules, and travel times in Germany.
kagi-search
by Mic92
Search the web using Kagi. Use for web searches with Quick Answer AI summaries.
project-awareness
by gleanwork
Use when the user asks about project status, ownership, or context. Triggers on phrases like "status of X project", "who owns Y", "what's happening with Z", "project update", "where does the project stand", "what's the state of", "who's working on", or when needing quick project context without a full analysis.
gmaps-cli
by Mic92
Search for places and get directions using Google Maps. Use for finding locations, nearby places, and route planning.
implementing-search-filter
by ancoleman
Implements search and filter interfaces for both frontend (React/TypeScript) and backend (Python) with debouncing, query management, and database integration. Use when adding search functionality, building filter UIs, implementing faceted search, or optimizing search performance.
embedding-optimization
by ancoleman
Optimizing vector embeddings for RAG systems through model selection, chunking strategies, caching, and performance tuning. Use when building semantic search, RAG pipelines, or document retrieval systems that require cost-effective, high-quality embeddings.