| # | Mod | Type | Stars | Scan | Tokens | Rating |
|---|---|---|---|---|---|---|
| 1 | markitdownK-Dense-AI/scientific-agent-skillsConverts heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server. | Skill | 55k | A | 62 | — |
| 2 | first-readerShubhamsaboo/awesome-llm-appsBeta readers for any draft, run by simulating how a real reader experiences it, moment by moment. A skim gate, a no-lookahead timed read producing an attention transcript with quit points, a recall test of what a reader remembers the next day, and a trust ledger of the implied author. Use when the user asks for a beta… | Skill | 143k | A | 174 | — |
| 3 | memory-triagemem0ai/mem0Persistent long-term memory protocol powered by mem0. Evaluate conversations for durable facts worth storing via memoryadd. Handles identity, preferences, decisions, configurations, rules, projects, and relationships. Loaded by the openclaw-mem0 plugin when skills mode is active. | Skill | 68k | A | 58 | — |
| 4 | deeptutor-cliHKUDS/DeepTutorConfigure, manage, and use DeepTutor through its CLI, including capabilities, knowledge bases, partners, memory, sessions, notebooks, providers, skills, and the server or Web app. | Skill | 44k | A | 42 | — |
| 5 | train-sentence-transformershuggingface/sentence-transformersTrain or fine-tune sentence-transformers models across SentenceTransformer (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), CrossEncoder (reranker, pair scoring for two-stage retrieval / pair classification), SparseEncoder… | Skill | 19k | A | 146 | — |
| 6 | graphifyGraphify-Labs/graphifyUse for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community… | Skill | 136k | B | 76 | — |
| 7 | surfsense-documentsMODSetter/SurfSenseMake or change a Word document (.docx), a PDF, a PowerPoint deck (.pptx) or an Excel workbook (.xlsx) by writing a Python script that surfsenserenderdocument runs, optionally starting from a source's own Word or PowerPoint file. Load it whenever the user asks for one of these, or for a change to one you made. | Skill | 17k | A | 80 | — |
| 8 | grpo-finetunepatchy631/ai-engineering-hubFine-tune a model with GRPO on Fireworks-managed GPUs from a plain-English task description and a dataset. Use this skill whenever the user wants to fine-tune, RL-tune, or GRPO-train a model on their own data — or says things like "train a model to extract/classify/score X", "fine-tune on this dataset", "set up a GRPO… | Skill | 38k | A | 122 | — |
| 9 | web-design-engineerConardLi/garden-skillsBuild or redesign polished browser-rendered visual artifacts with HTML/CSS/JavaScript/React: pages, dashboards, prototypes, slide decks, animations, UI mockups, and data visualizations. Use for visual front-end creation, design-system exploration, design critique, or explicit browser acceptance / QA of a web artifact.… | Skill | 13k | A | 96 | — |
| 10 | browserwing-executorMemTensor/MemOSControl browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations. | Skill | 12k | A | 42 | — |
| 11 | potpie-graphpotpie-ai/potpieUse when the task can read or write the project-memory graph through the potpie CLI: discover the contract with graph catalog, read named views with graph read, resolve entity identity with graph search-entities, create validated plans with graph propose, commit plans with graph commit --verify, inspect quality with… | Skill | 5.8k | A | 107 | — |
| 12 | autorag-setupMarker-Inc-Korea/AutoRAGInstall and configure AutoRAG, register its Lite MCP server for external agents, or repair its single search model, approved roots, indexes, datasources, and health checks without exposing credentials. Use when AutoRAG or MCP is missing, init/refresh/health fails, indexes are stale, or the user wants to add folders or… | Skill | 5.2k | A | 75 | — |
| 13 | tushare-dataagentscope-ai/ReMeA Chinese-language workflow for researching financial and market data through Tushare, a data service covering Chinese stocks and related economic information. It turns natural-language questions into steps for retrieving, cleaning, comparing, filtering, exporting, and briefly analysing data. | Skill | 3.7k | A | 122 | — |
| 14 | evalscopemodelscope/evalscopeLLM evaluation & inference performance testing via the evalscope CLI. Translates natural language requests into evalscope commands for: (1) Model accuracy evaluation — runs registered benchmarks against local checkpoints or API endpoints (OpenAI-compatible, Anthropic, LiteLLM); (2) Performance stress testing — TTFT… | Skill | 3.6k | A | 195 | — |
| 15 | memory-to-skillzilliztech/memsearchTurn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under… | Skill | 2.8k | A | 82 | — |
| 16 | remote-compute-modalUnicomAI/wanwuRun GPU jobs on the user's own Modal account via host.compute.create('byoc:modal', ...). Covers the create→submit→waitfornotification flow, the computeprovider kernel for env setup, image/volume resolution, and the two approval cards. Load once you've decided to dispatch to Modal. | Skill | 2.4k | A | 65 | — |
| 17 | deep-researchxerrors/YuxiA method for organising research that uses several sources and needs fact checking. It breaks a broad question into smaller investigations, checks important claims and combines the results into a cited report. | Skill | 7.5k | A | 69 | — |
| 18 | vss-generate-video-reportNVIDIA-AI-Blueprints/video-search-and-summarizationUse this skill when producing a VSS analysis report — Mode A per-clip VLM, Mode B incident-range via video-analytics, Mode C SOP compliance via the SOP tools. Not for standalone video summarization, real-time alerts or ad-hoc Q&A. | Skill | 2.0k | A | 61 | — |
| 19 | trigger.advanced-tasksagentset-ai/agentsetComprehensive rules to help you write advanced Trigger.dev tasks. | Cursor rule | 2.1k | A | 3,202 | — |
| 20 | nemotron-retrieval-recipesNVIDIA-NeMo/NemotronUse for Nemotron embed/rerank recipes, including Nemotron 3.5 multimodal SDG, tuning, evaluation, and deployment. Not for generic retrieval. | Skill | 2.2k | A | 42 | — |
| 21 | video-promptageerle/ruoyi-aiDirecting contract for editable shots and continuous performance segments. | Skill | 5.8k | A | 15 | — |
| 22 | pixelbrowseStarTrail-org/PixelRAGGive Claude eyes — screenshot any URL with pixelshot and read it visually. | Plugin | 10k | A | — | — |
| 23 | llmwikiatomicstrata/llm-wiki-compilerBuild and use a persistent, citation-traceable knowledge wiki from documents, research papers, notes, or project documentation. Use for llmwiki projects, retrieving reusable evidence for an agent task, or compiling a corpus for repeated questions. A one-off file read or live web search does not need a wiki. | Skill | 2.2k | A | 66 | — |
| 24 | moss-pikachuusemoss/mossBuild and maintain Moss Pikachu, a macOS menu bar semantic file search app using Moss Python SDK (PyPI moss>=1.6.0), FSEvents, SwiftUI, and Pikachu pet animations. Use when working on MossPikachu, mossworker.py, FileMonitor, SearchService, menu bar overlay, or Moss integration in this repository. | Skill | 800 | A | 80 | — |
| 25 | designer-perspectiveFuRongJun-1999/dsh-memoryA planning and decision-making skill that evaluates whether an action is justified, why it should be taken, and whether the available conditions are sufficient. It observes and recommends but does not perform operations or verify facts. | Skill | 490 | A | 230 | — |
| 26 | explain-paperraphaelmansuy/edgequakeUse EdgeQuake MCP tools as evidence — never invent document lists. | Skill | 2.3k | A | 0 | — |
| 27 | personal-document-searchLazyAGI/LazyMindUse when the user wants to find or ask questions about their local files, cloud documents, mail, or Agent conversation history across Local Files, Agent Conversations, Feishu, official Notion MCP, Google Drive, and Mail. Rewrite queries for each source, search independently in parallel, read evidence on demand, and… | Skill | 413 | A | 72 | — |
| 28 | project-rulesnuwax-ai/nuwaxA set of development rules for a React 18 frontend built with UmiJS, Ant Design, TypeScript, and related tools. The rules cover naming, components, styling, state, and performance. | Cursor rule | 897 | A | 11 | — |
| 29 | rag-index-decisionslyonzin/knowledge-ragAfter making a non-obvious architectural decision, solving a novel bug, agreeing on a coding standard, or reaching a conclusion worth remembering, index it back into the knowledge base so the next occurrence is one search away. Uses adddocument or addfromurl. Closes the feedback loop that makes a RAG-backed team… | Skill | 300 | A | 72 | — |
| 30 | memex-searchnicosuave/memexDiscover prior agent work across sessions, projects, providers, and machines. Use for historical investigations and analogous solutions, or as a fallback when native conversation and history tools cannot recover the needed evidence. | Skill | 288 | A | 42 | — |
| 31 | ragRailtownAI/railtracksBuild a RAG (retrieval-augmented generation) pipeline using railtracks. Use when the user wants to ingest documents into a vector store and retrieve relevant passages to answer questions. | Skill | 234 | A | 39 | — |
| 32 | starcat-ui-prototypestarcat-app/StarcatA design skill for creating macOS interface prototypes and visual designs for Starcat, a GitHub star-management and AI knowledge-organising app. It follows Apple’s Liquid Glass design language for macOS 26. | Skill | 211 | A | 85 | — |
| 33 | openviking-controlplanevolcengine/mcp-serverManage OpenViking collections (OV libraries) from the command line with ov-cp — list / create / get / update / usage / get the data-plane API key / delete, plus managing the users and account data spaces of an enterprise-tier library (list / create / register / update / delete), account-scoped users / API keys /… | Skill | 332 | A | 185 | — |
| 34 | alexaHybridAIOne/hybridclawExpose HybridClaw as a custom Alexa skill and prepare guarded Alexa smart-home/device control payloads without exposing Amazon credentials. | Skill | 159 | A | 27 | — |
| 35 | mengram-memoryalibaizhanov/mengramLong-term memory with 3 types (facts, events, workflows). Remember user preferences, past conversations, and learned procedures across sessions. Use when recalling what the user said before, saving important info, getting user context, or tracking completed workflows. | Skill | 204 | A | 53 | — |
| 36 | neurolink-guidejuspay/neurolinkGuide for using the NeuroLink SDK and CLI. Invoke when users ask how to use neurolink, integrate AI providers, add MCP tools, configure RAG, set up memory, deploy servers, or work with multimodal content. Covers SDK, CLI, providers, tools, and enterprise features. | Skill | 157 | A | 65 | — |
| 37 | gnogmickel/gnoSearch local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs… | Skill | 118 | A | 86 | — |
| 38 | haiku-ragggozad/haiku.ragSearch, read and analyze your haiku.rag knowledge base from Claude Code. | Plugin | 638 | A | — | — |
| 39 | migrate-from-ai-sdkDeuz-AI/Deuz-SDKUse when porting an app from the Vercel AI SDK (ai, @ai-sdk/) to @deuz-sdk/core. Triggers include "migrate from the AI SDK", "replace ai with @deuz-sdk/core", "we use streamText/generateText/useChat and want to switch", removing @ai-sdk/openai or @ai-sdk/anthropic, porting a toUIMessageStreamResponse route, converting… | Skill | 519 | A | 118 | — |
| 40 | bashopensolon/solon-aiA command-line agent for running Bash shell commands, terminal tasks, and Git operations. Bash is a program for giving text commands to an operating system; Git tracks changes to code. | Agent | 468 | A | 31 | — |
| 41 | bilibili-rag-localvia007/bilibili-ragA guide for querying a locally running service that stores and answers questions about saved Bilibili videos. Bilibili is a Chinese video platform, and RAG means retrieving relevant saved content before generating an answer. | Skill | 1.3k | A | 72 | — |
| 42 | rag-perfNVIDIA-AI-Blueprints/ragPerformance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / RAGAS scoring (use rag-eval) or for deploying / repairing services (use rag-blueprint). | Skill | 799 | A | 56 | — |
| 43 | karpathy-llm-wikiAstro-Han/karpathy-llm-wikiUse when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'. | Skill | 2.6k | A | 67 | ★ 5 |
| 44 | bili-noteRimagination/bili-noteA tool for turning Bilibili videos and posts into readable Markdown notes. Bilibili is a Chinese video and social-content platform; the tool can work with subtitles, article text, images, code, and selected comments. | Skill | 343 | A | 86 | — |
| 45 | forge-platformnihalashetty/ForgeUse when designing, building, debugging, or explaining Forge workflows, nodes, state, routing, middleware, tools, or knowledge - especially custom/complex shapes beyond the canned builders, AND for anything about deep agents, sub-agents, or supervisor patterns (how sub-agents are wired on the canvas), or… | Skill | 174 | A | 76 | — |
| 46 | graphify-windowssaeedkolivand/ai-job-hunter-appTurn any folder of files into a navigable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPHREPORT.md. | Skill | 62 | A | 75 | — |
| 47 | octocodeMuvon/octocodeAI-powered code indexer with semantic search and knowledge graphs. Runs locally from the @muvon/octocode npm package. | MCP server | 518 | A | — | — |
| 48 | veritasreasonbibinprathap/VeritasGraphFull-stack knowledge graph skills: semantic extraction, decision intelligence, context graphs, reasoning, explainability, ontology, provenance, deduplication, visualization, and multi-format export. | Plugin | 326 | A | — | — |
| 49 | lilbee-mcptobocop2/lilbeeSearch and manage the user's local lilbee knowledge base over MCP. Use whenever the user has indexed code, docs, PDFs, or web pages into lilbee and you need cited answers, or whenever they ask you to ingest content, swap models, or tune retrieval against their library. Every fact returned cites file and line.… | Skill | 66 | A | 95 | — |
| 50 | mcp-local-ragshinpr/mcp-local-ragEasy-to-setup local RAG server with minimal configuration. Runs locally from the mcp-local-rag npm package. Needs 8 environment variables to run. | MCP server | 425 | A | — | — |
| 51 | backlotbrekkylab/backlotEmulate an enterprise SaaS knowledge source over a corpus you supply, then wire a real client to it. | Plugin | 259 | A | — | ★ 5 |
| 52 | qdrantqdrant/skillsAgent skills for Qdrant vector search: scaling, performance optimization, search quality, monitoring, deployment, edge, model migration, multitenancy, version upgrades, and SDK usage. | Plugin | 264 | A | — | — |
| 53 | zettelforgeThreatRecall/zettelforgeZettelForge v2.0.0 — Production CTI agentic memory system. Hybrid TypeDB (STIX 2.1 ontology) + LanceDB (vector search). Zero external AI dependencies: fastembed for embeddings, llama-cpp-python for LLM. 75% accuracy on CTI queries, 18% on LOCOMO. Use when agents need persistent memory, threat intel retrieval, entity… | Skill | 66 | A | 97 | — |
| 54 | synaplanmetadist/synaplanSelf-hosted AI workspace: semantic RAG document search, long-term memory, and AI chat via MCP. Remote server at web.synaplan.com. | MCP server | 287 | A | — | — |
| 55 | apple-dev-docsBingoWon/apple-rag-mcpAnswer Apple platform questions from Apple's official developer documentation and WWDC session transcripts instead of guessing or web-searching. Use when the user asks about iOS, iPadOS, macOS, watchOS, tvOS, or visionOS; Swift, SwiftUI, UIKit, AppKit, StoreKit, SwiftData, RealityKit, or any Apple framework; an API's… | Skill | 121 | A | 123 | — |
| 56 | sweet-indexmrsladoje/sweet-searchUse when (re)indexing a Sweet Search project. Runs the full-profile indexer with GPU model prewarming (CoreML cascade on M3+, candle Metal on M1/M2, ORT CPU elsewhere), kills ORT CPU models during indexing to avoid memory contention, and rewarms them for query readiness on completion. Incremental runs under 20 files… | Skill | 50 | A | 83 | — |
| 57 | video_action_recognitionfdueblab/Micro-AgentTechnical guidance for recognizing human actions in video without training a new machine-learning model or using an LLM. It describes a pipeline that samples video frames, estimates body poses, measures movement, and assigns labels with rules. | Skill | 101 | A | 0 | — |
| 58 | omniseek-investigateBattam1111/omniseekDeep-investigation methodology for OmniSeek. Sweep in parallel with omniseekgather, judge the signals, zoom through walled sources, structure the evidence, and close with an explicit gap ledger. | Skill | 95 | A | 46 | — |
| 59 | basemindGoldziher/basemindFull AI context layer over MCP — tree-sitter code-map, document RAG (PDF/Office/HTML/email + OCR + reranker), shared agent memory, on-demand web crawl, git history + blame + per-symbol diff. 300+ languages, 10+ coding-agent harnesses, content-addressed Fjall + LanceDB. | Plugin | 113 | A | — | — |
| 60 | my-wikiNimaChu/my-wikiA skill for managing a local Markdown knowledge vault that stores captured webpages, PDFs, Office files, notes, images, folders, and ZIP files. It links preserved source material, called References, to durable topic pages, called Concepts. | Skill | 125 | A | 51 | — |
| 61 | zero-to-ai-ragPavanMudigonda/zero-to-aiMCP server "zero-to-ai-rag" as configured in PavanMudigonda/zero-to-ai. Runs scripts/rag_mcp_server.py with python. | MCP server | 155 | A | — | — |
| 62 | infranodusinfranodus/mcp-server-infranodusInfraNodus knowledge graphs and text network analysis: topics, content gaps, research questions, GraphRAG retrieval, SEO/GEO analysis, and structured memory for AI agents. | Plugin | 104 | A | — | — |
| 63 | local-rag-searchnkapila6/mcp-local-ragEfficiently perform web searches using the mcp-local-rag server with semantic similarity ranking. Use this skill when you need to search the web for current information, research topics across multiple sources, or gather context from the internet without using external APIs. This skill teaches effective use of… | Skill | 134 | A | 80 | — |
| 64 | ask-various-llmsNayjest/ai-microcoreMCP server "ask-various-llms", hosted remotely at 127.0.0.1, as configured in Nayjest/ai-microcore. | MCP server | 108 | A | — | — |
| 65 | weaviateweaviate/agent-skillsWeaviate plugin for Claude Coding. | Plugin | 104 | A | — | — |
| 66 | minirag-mcpsfrangulov/minirag-mcpLocal-first RAG MCP server: hybrid search over your documents, fully local. Runs locally from the minirag-mcp Python package. Needs 13 environment variables to run. | MCP server | 58 | A | — | — |
| 67 | pdfmuxNameetP/pdfmuxSelf-healing PDF extraction for RAG — #2 of 8 engines on opendataloader-bench (0.903). Flags pages it can't read instead of dropping them, and certifies any extractor's output for silent drops. Verify signed manifests offline, free. Per-page confidence, 7-tool MCP server, LangChain/LlamaIndex loaders. LlamaParse… | MCP server | 85 | A | — | — |
| 68 | convex-agentget-convex/agent-skillsAdd an AI agent / RAG backend (@convex-dev/agent) to the Convex app. | Skill | 64 | A | 25 | — |
| 69 | fine-tune-readinesszorost/AI-Engineering-LabDecide whether fine-tuning is justified versus prompting or RAG, and gate the training dataset before any LoRA/SFT/DPO run. Use when someone says 'let's fine-tune'. | Skill | 318 | A | 46 | — |
| 70 | mfs-ingestzilliztech/mfsRegister, update, or re-sync data sources for MFS so they become searchable — postgres / mysql / mongo / snowflake / bigquery, github / jira / linear / notion / hubspot / zendesk, slack / discord / gmail / feishu, s3 / gdrive / web / file. Use whenever the user wants to ADD a new data source to MFS, change an existing… | Skill | 157 | A | 196 | — |
| 71 | graph-engineeringcodejunkie99/graph-engineeringTeaches an agent graph engineering — both halves. Knowledge graphs (ontology design, entity/relation/event extraction, fusion, GraphRAG/memory serving; distilled and translated from Southeast University's graduate Knowledge Graph course, npubird/KnowledgeGraphCourse, 4.4K stars) and task graphs (agent orchestration … | Skill | 553 | A | 152 | — |
| 72 | setup-open-indexDrDroidLab/open-indexInstall and configure Open Index as the read/write context layer for a domain-specialized agent. Use when setting up a legal, marketing, customer support, sales, infrastructure, or other domain agent with Open Index over MCP. | Skill | 113 | A | 48 | — |
| 73 | okfy0dust/OKFyUse when a user wants an agent to use docs through OKFy, set up or verify an OKFy MCP docs source, convert docs websites or local Markdown into OKF bundles, generate activation proof, or answer from an existing OKFy bundle/workspace. | Skill | 75 | A | 54 | — |
| 74 | codealive-mcpCodeAlive-AI/codealive-mcpMCP server "codealive-mcp" as configured in CodeAlive-AI/codealive-mcp. Runs in Docker (ghcr.io/codealive-ai/codealive-mcp:3.0.3). Needs 1 environment variable to run. | MCP server | 90 | A | — | — |
| 75 | distill-kuralna-lab/distill-kuraMCP server "distill-kura" as configured in lna-lab/distill-kura. Runs locally from the distill-kura Python package. | MCP server | 54 | A | — | — |
| 76 | hybrid-memoryclawdbrunner/openclaw-graphiti-memoryHybrid memory strategy combining OpenClaw's built-in QMD vector memory with Graphiti temporal knowledge graph. Use for all memory recall requests. | Skill | 103 | A | 32 | — |
| 77 | pineconepinecone-io/pinecone-claude-code-pluginPinecone vector database integration. Streamline your Pinecone development with powerful tools for managing vector indexes, querying data, and rapid prototyping. Use slash commands like /quickstart to generate AGENTS.md files and initialize Python projects and /query to quickly explore indexes. Access the Pinecone MCP. | Plugin | 69 | A | — | — |
| 78 | pageindex-mcpVectifyAI/pageindex-mcpReasoning-based RAG system for chatting with long PDFs. Supports local and online files. Runs locally from the @pageindex/mcp npm package. | MCP server | 404 | A | — | — |
| 79 | context-enginemelonelish/context-engineTask-aware context compression for logs, RAG, and coding workflows. Runs locally from the melonelish-context-engine Python package. | MCP server | 326 | A | — | — |
| 80 | cocoindexcocoindex-io/cocoindex-claudeComprehensive toolkit for developing with the CocoIndex library. Use when users need to create data transformation pipelines (flows), write custom functions, or operate flows via CLI or API. Covers building ETL workflows for AI data processing, including embedding documents into vector databases, building knowledge… | Skill | 82 | A | 72 | — |
| 81 | claude-token-reducerMadhan230205/token-reducerOpen-source, local-first Claude Code plugin for token reduction, context compression, and cost optimization using hybrid RAG retrieval (BM25 + vector search), reranking, AST-aware chunking, and compact context packets. | Plugin | 52 | A | — | — |
| 82 | code-graph-rag-mcper77/code-graph-rag-mcpMulti-agent LiteRAG MCP server for advanced code graph analysis. Runs locally from the @er77/code-graph-rag-mcp npm package. | MCP server | 122 | A | — | — |
Want everything, not just what passes the gates? Browse the full category from any type hub, or search it. This shelf recomputes nightly from the measurements.