Discover and install skills to enhance your AI agent's capabilities.
| Name | Contains | Score |
|---|---|---|
strategic-compact affaan-m/everything-claude-code 建议在逻辑间隔处手动压缩上下文,以在任务阶段中保留上下文,而非任意的自动压缩。 | Skills | 78 2.27x Agent success vs baseline Impact 100% 2.27xAverage score across 6 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.3 |
citation-management K-Dense-AI/claude-scientific-skills Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing. | Skills | 77 1.84x Agent success vs baseline Impact 81% 1.84xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.0.1 |
dotnet-backend-patterns Dicklesworthstone/pi_agent_rust Master C#/.NET backend development patterns for building robust APIs, MCP servers, and enterprise applications. Covers async/await, dependency injection, Entity Framework Core, Dapper, configuration, caching, and testing with xUnit. Use when developing .NET backends, reviewing C# code, or designing API architectures. | Skills | 77 1.19x Agent success vs baseline Impact 85% 1.19xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.0.1 |
git-workflow NeverSight/skills_feed Enhanced git operations using lazygit, gh (GitHub CLI), and delta. Triggers on: stage changes, create PR, review PR, check issues, git diff, commit interactively, GitHub operations, rebase, stash, bisect. | Skills | 77 1.32x Agent success vs baseline Impact 93% 1.32xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
memory-leak-debugging ChromeDevTools/chrome-devtools-mcp Diagnoses and resolves memory leaks in JavaScript/Node.js applications. Use when a user reports high memory usage, OOM errors, or wants to analyze heapsnapshots or run memory leak detection tools like memlab. | Skills | 77 0.85x Agent success vs baseline Impact 56% 0.85xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
angular-ui-patterns sickn33/antigravity-awesome-skills Modern Angular UI patterns for loading states, error handling, and data display. Use when building UI components, handling async data, or managing component states. | Skills | 77 2.65x Agent success vs baseline Impact 85% 2.65xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
groq-reference-architecture jeremylongshore/claude-code-plugins-plus-skills Implement Groq reference architecture with model routing, streaming pipelines, and fallbacks. Use when designing new Groq integrations, reviewing project structure, or establishing architecture standards for Groq applications. Trigger with phrases like "groq architecture", "groq best practices", "groq project structure", "how to organize groq", "groq design". | Skills | 77 1.66x Agent success vs baseline Impact 93% 1.66xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
database-documentation-gen jeremylongshore/claude-code-plugins-plus-skills Process use when you need to work with database documentation. This skill provides automated documentation generation with comprehensive guidance and automation. Trigger with phrases like "generate docs", "document schema", or "create database documentation". | Skills | 77 1.08x Agent success vs baseline Impact 81% 1.08xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.2 |
nano-banana-prompts secondsky/claude-skills Generate optimized prompts for Gemini 2.5 Flash Image (Nano Banana). Use for image generation, crafting photo prompts, art styles, or multi-turn editing workflows with best practices. | Skills | 77 1.03x Agent success vs baseline Impact 97% 1.03xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
imaging-data-commons K-Dense-AI/claude-scientific-skills Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses. | Skills | 77 1.35x Agent success vs baseline Impact 73% 1.35xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.0.1 |
receiving-review shousper/claude-kit Enforces rigorous technical evaluation of code review feedback before implementation -- verifying suggestions against the codebase, pushing back when wrong, clarifying ambiguity, and avoiding performative agreement. Use when processing PR review comments, inline suggestions, change requests, reviewer feedback, or any list of code fixes to address. Applies to feedback from human partners and external reviewers alike. DO NOT TRIGGER when writing a review of someone else's code. | Skills | 77 1.21x Agent success vs baseline Impact 97% 1.21xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
angular-ui-patterns boisenoise/skills-collections Modern Angular UI patterns for loading states, error handling, and data display. Use when building UI components, handling async data, or managing component states. | Skills | 77 2.65x Agent success vs baseline Impact 85% 2.65xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
libfuzzer trailofbits/skills Coverage-guided fuzzer built into LLVM for C/C++ projects. Use for fuzzing C/C++ code that can be compiled with Clang. | Skills | 77 1.28x Agent success vs baseline Impact 96% 1.28xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.0.1 |
openhue trpc-group/trpc-agent-go Control Philips Hue lights and scenes via the OpenHue CLI. | Skills | 77 2.59x Agent success vs baseline Impact 96% 2.59xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
v0.2.1 Collection of agent skills for SLICC and Tessl-compatible runtimes — productivity, creative, document, and integration skills. Contains: aem AEM Edge Delivery Services (EDS) skill for reading, writing, previewing, and publishing EDS pages via the `aem` CLI. Use when the user asks about AEM Edge Delivery Services, EDS pages, Franklin, Helix, AEM EDS, edge delivery content, document-based authoring, or needs to list, get, put, preview, publish, or upload content in AEM EDS. Supports the full get→edit→put→preview→publish pipeline. ai-writing-detector Detect patterns of AI-generated writing in prose, creative writing, and technical documentation. Use when analyzing text for AI tells, checking if content reads like AI, reviewing drafts for machine-generated patterns, or auditing writing authenticity. Triggers on requests like "Does this read like AI?", "Check for AI patterns", "Analyze for AI writing", "Is this AI-generated?", "Detect LLM patterns". apple-music Interact with Apple Music — search the Apple Music catalog, manage Apple Music playlists, add and remove tracks from Apple Music playlists, and browse Apple Music library content. Use this skill whenever the user asks about Apple Music, wants to search for songs on Apple Music, manage their Apple Music playlists, or automate any Apple Music workflow. Activate for requests involving music search, playlist creation, playlist editing, track management, or any Apple Music library operations. bluebubbles Sends and receives iMessages via the BlueBubbles REST API. Use when the user wants to send a text message, iMessage, or SMS, read or search message history, find contacts, list conversations, or interact with their iPhone messages from the desktop. Capabilities include sending direct messages and group chats, querying message history, finding contacts by name, searching existing chat threads, distinguishing direct vs group conversations, and verifying message delivery. Requires a running BlueBubbles server. concur Interact with SAP Concur (Concur Expense / Travel) via its API — list expense reports, view report and line-item details, list available receipts and smart expenses, check approvals, and call any of 50+ Concur GraphQL operations directly. Use whenever the user mentions Concur, SAP Concur, Concur Expense, expense reports, expense submission, expense receipts, smart expenses, T&E (travel and expense), reimbursements at Adobe, or wants to automate, query, or extract data from Concur without clicking through https://us2.concursolutions.com. Activate on mentions of "concur", "expense report", "expense receipts", "submit expenses", "T&E", "reimbursement", "travel allowance", or related Adobe expense workflows. fluffyjaws Interact with Adobe FluffyJaws (Mr. FluffyJaws) — Adobe's internal AI assistant — via its public API. Use when the user mentions FluffyJaws, fj, FluffyPacks, the Adobe internal AI chatbot, the FluffyJaws CLI, fj-mcp, or wants to ask questions, stream chat completions, list/inspect FluffyPacks, list conversations, or talk to the FluffyJaws MCP endpoint without clicking through https://fluffyjaws.adobe.com. Activate on mentions of "fluffyjaws", "fluffy jaws", "fluffypack", "fluffypacks", "fj ask", "fj chat", "fj mcp", "ask FluffyJaws", "internal Adobe ChatGPT", or related Adobe internal AI workflows. github Interact with GitHub via gh.jsh — a lightweight GitHub CLI for SLICC agents. Use this skill for any GitHub task: listing or viewing pull requests, merging PRs, posting comments, checking out branches, viewing issues, inspecting workflow runs, listing releases, searching PRs, managing Actions variables, creating branches, pushing file content, archiving repos, or calling any GitHub API endpoint directly. Trigger on requests like "list open PRs", "check CI status", "merge this PR", "what issues are open", "show the latest release", "post a comment on PR #42", "set a repo variable", "archive this repo", "create a branch", "push this file", or any task involving a GitHub repository. gmail Interact with Gmail — read inbox, search messages, view full message bodies, send email, reply to threads, and produce aggregated inbox items for the monday dispatcher. Uses OAuth2 refresh token flow via GWS_* env vars. Triggers on requests involving Gmail, Google email, inbox, sending mail, checking unread messages, or monday inbox aggregation that includes Gmail data. icloud Interact with iCloud Calendar and Notes from a signed-in iCloud browser tab. Use when the user asks about their calendar, upcoming events, schedule, or wants to read/search their Apple Notes. Triggers on phrases like "what's on my calendar", "upcoming events", "my notes", "search notes", "read note", "iCloud calendar", "iCloud notes". linkedin Manage a LinkedIn company page — publish posts with consistent brand voice, grow engagement, respond to comments, analyze performance, preview profiles, and aggregate engagement for the monday dispatcher. Maintains a knowledge base of content ideas, audience insights, and brand guidelines. Use when the user wants to publish a LinkedIn post, draft LinkedIn content, check LinkedIn comments, respond to engagement, plan content strategy, review brand voice, view a LinkedIn profile, or manage a company page. Activate on mentions of LinkedIn, LinkedIn post, company page, social media, content calendar, engagement, brand voice, or audience growth. llm-wiki Build and maintain a persistent, interlinked markdown wiki knowledge base from raw sources. Use when the user wants to create a knowledge base, build a wiki, ingest articles or papers into a KB, query accumulated knowledge, organize research notes, or lint a wiki for broken links and orphan pages. Triggers on mentions of knowledge base, wiki, KB, ingest, research notes, or personal wiki. mixtape Create themed music playlists and mixtapes with curated song lists, descriptions, and cover art prompts. Use when the user asks to build a playlist, create a mixtape, curate songs around a theme, or wants music recommendations organized as a cohesive collection. Triggers on requests like "make me a playlist", "build a mixtape", "curate songs about...", "themed playlist for...". monday Aggregate and prioritize inbox items from multiple sources (Gmail, Slack, Teams, Outlook, GitHub, ServiceNow) into a single ranked list. Acts as a dispatcher: each source skill exposes a `[cmd] monday` sub-command that returns JSON items, and the `monday` command merges, deduplicates, optionally rates with an AI model (importance times urgency), and sorts them. Use when the user asks "what should I work on", "Monday morning triage", "what needs my attention", "show me my inbox", "rank my todos", "what's urgent across all my tools", or for weekly/daily triage across email, chat, tickets, and pull requests. oryx Interact with the ZSA Oryx keyboard configurator (oryx.zsa.io, configure.zsa.io) via its GraphQL API — list, inspect, edit, and compile layouts for ZSA Voyager, Moonlander, and ErgoDox EZ keyboards. Use when the user wants to automate ZSA / Oryx, dump a keyboard layout, edit layers or keys without clicking through the configurator UI, fork a revision, change layout privacy, set tags, trigger a firmware compile, download .bin / .zip firmware bundles, manage combos, or run any GraphQL query against the Oryx backend. Activate on mentions of zsa, oryx, voyager, moonlander, ergodox, keyboard layout, keymap, qmk, layer, combo, key code (KC_*), firmware compile, hex file, or related workflows. outlook Interact with Microsoft Outlook (Office 365) — read inbox, search mail, view calendar events, send email, and produce aggregated inbox items for the monday dispatcher. Uses the live Outlook browser session via MSAL token extraction from localStorage. Triggers on requests involving Outlook, email, inbox, calendar, meetings, sending mail, checking unread messages, or monday inbox aggregation that includes Outlook data. pdf Read, create, merge, split, rotate, and extract text from PDF files using SLICC's built-in pdftk and convert commands. No Python required. Use when the user asks to work with PDFs or .pdf files, needs to combine, merge, split, rotate, or extract text/pages from documents, wants to check page count or metadata, or needs to convert a PDF page to an image. pm-prd Interview a product manager until the bet is real, then capture it as a Product Requirements Document. Use when a PM asks to write a PRD, define requirements, scope an MVP, plan a roadmap, or draft a launch plan. Triggers on phrases like "write a PRD", "create a spec", "define requirements", "what should we build", "MVP for X", "roadmap for X", "GTM plan", "launch plan", "product spec", or "I need to document this feature". pptx2pdf Convert PPTX files to PDF, preserving slide backgrounds, text styles, colors, alignment, word-wrap, and embedded PNG/JPEG images. No external tools required — uses pdf-lib via esm.sh and the pre-loaded JSZip. Use when the user asks to convert a presentation to PDF, export slides as PDF, or download a PPTX as PDF. Triggers on phrases like "convert ppt to pdf", "export presentation as pdf", "turn this pptx into a pdf", "save slides as pdf". pptx Generates, reads, and edits PowerPoint files (.pptx). Handles full presentations with text, images, themes, and precise slide positioning. Use when the user asks to create, build, or generate a PowerPoint presentation, slide deck, or .pptx file; when they want to read, extract text from, or inspect an existing .pptx; when they need to edit, update, replace text in, or add slides to a PowerPoint file; or when they mention slides, ppt, slide deck export, or pptx output. Does not generate speaker notes or custom slide layouts. presentations Create slide presentations as standalone, responsive HTML documents. No frameworks — just bespoke HTML, CSS, and minimal JS for navigation and animations. Use when the user asks for slides, a slide deck, a slideshow, a presentation, a pitch deck, conference talk, keynote, lightning talk, or "make a deck about X". review Track review items (publish/comment/defer) and annotate documents with text highlighting via a sprinkle dashboard. Use when the user has content to review, approve, or annotate — pages pending publish, PRs needing signoff, documents to mark up. Triggers on requests like 'review queue', 'what's pending', 'annotate this doc', 'mark up this file', 'review dashboard', 'publish queue'. Distinct from code review tools: this skill manages a persistent UI queue with in-flight publish tracking and inline text selection annotations. save-the-cat Screenwriting assistant using Blake Snyder's Save the Cat! methodology. Helps with high-concept ideas, loglines, hero design, the 15-beat Beat Sheet (BS2), the Board, story genres, and diagnostics. Use when writing screenplays, developing movie structure, creating beat sheets, crafting loglines, building a board, or analyzing script structure. servicenow Interact with Adobe's ServiceNow instance — list and manage tickets/incidents, read and post comments, search the Knowledge Base. Use when the user mentions ServiceNow, tickets, incidents, KB articles, support requests, RITM, INC numbers, pagerduty replacement, on-call, or wants to check ticket status, leave comments, or find internal documentation. strudel-music Generate live-coded music patterns using the Strudel library (JavaScript port of TidalCycles). Use this skill whenever the user wants to create music, beats, melodies, rhythms, or sound patterns in the browser. Triggers on requests like "make some music", "create a beat", "generate a melody", "live code some audio", "play a pattern", "make a drum loop", "compose something", or any request involving Strudel, TidalCycles, or algorithmic music. Also use when the user asks to modify, remix, or explore existing musical patterns. suno Write song lyrics formatted for Suno AI V5.5 music generation and submit them via the `suno` CLI, which drives Suno through the user's own logged-in browser session on suno.com. Use when the user wants to create a song, write lyrics, compose music with AI, submit to Suno, list Suno personas, check Suno credits, or asks for help with Suno. Triggers on requests like "write me a song", "create lyrics about...", "help me with Suno", "compose a track", "song about...", "suno credits", "suno personas". swarm CLI access to Foursquare/Swarm check-in history, venue visits, and location search via the Foursquare v2 API. Use when the user mentions Foursquare, Swarm, check-ins, venues, venue history, places visited, top venues, location search, or wants stats about where they've been. Supports paginated check-in lookups, category filtering, nearby venue search, full venue detail (rating, hours, personal visit count), and overall check-in statistics with top 5 most-visited venues. teams Interact with Microsoft Teams via the Graph API — read messages, post to channels, search, read threads, look up users, view mentions/activity, and get channel info. Supports all teams and channels the user has access to, with auth via the live browser session. Use when the user wants to check Teams messages, post a Teams message, search Teams channels, read a thread, get user info, view mentions, or automate any Teams task. Triggers on mentions of Teams, channels, messages, threads, mentions, activity, or digest. wavespeed Generate images, videos, and speech using the WaveSpeed AI API via curl. Use when the user wants to generate images from text prompts, create videos from images, synthesize speech, or work with any WaveSpeed AI model. Triggers on requests like "generate an image of...", "create a video from this image", "make speech audio", "use wavespeed to...", "text to image", "image to video", "text to speech", or any mention of WaveSpeed AI, Flux, Wan 2.6, Seedream, or other WaveSpeed-hosted models. Also use this skill when the user asks to generate visual or audio content and no other generation API or skill is available — WaveSpeed can serve as the fallback generation platform. xai-grok Use Grok (xAI) models for chat, reasoning, image generation, web/X search, and function calling via the xAI API. Use this skill to call Grok, use xAI models, generate images with Aurora, do real-time web or X search through Grok, or build applications that integrate with xAI's API. | Skills | 77 Impact — Average score across 0 eval scenarios Securityby Risky Do not use without reviewing Reviewed: Version: 0.2.1 |
diagnose mattpocock/skills Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression. | Skills | 77 Impact — Average score across 0 eval scenarios Securityby Passed No known issues Reviewed: Version: b8be62f |
pathml K-Dense-AI/claude-scientific-skills Full-featured computational pathology toolkit. Use for advanced WSI analysis including multiplexed immunofluorescence (CODEX, Vectra), nucleus segmentation, tissue graph construction, and ML model training on pathology data. Supports 160+ slide formats. For simple tile extraction from H&E slides, histolab may be simpler. | Skills | 77 2.74x Agent success vs baseline Impact 96% 2.74xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
typespec-create-api-plugin github/awesome-copilot Generate a TypeSpec API plugin with REST operations, authentication, and Adaptive Cards for Microsoft 365 Copilot | Skills | 77 1.96x Agent success vs baseline Impact 100% 1.96xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.0.1 |
research docker/docs Research a documentation topic — locate affected files, understand the problem, identify what to change. Use when investigating an issue, a question, or a topic before writing a fix. Triggers on: "research issue 1234", "investigate what needs changing for #500", "what files are affected by #200", "where is X documented", "is our docs page about Y accurate", "look into how we document Z". | Skills | 77 Impact — Average score across 0 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: c0aa985 |
grill-with-docs belchman/claude-skills Stress-test a plan, design, or idea against the project's domain language (CONTEXT.md) and recorded decisions (docs/adr/). One question at a time, walks the decision tree, captures crystallized terminology and decisions inline. THIS IS THE DEFAULT GRILLING SKILL — use for any interrogation in a real project, even if CONTEXT.md or docs/adr/ don't exist yet (they get created lazily on first term resolution / first ADR-worthy decision). Triggers: /grill-with-docs, "grill me", "grill this", "interrogate this plan", "stress-test this design", "walk me through the decisions", "challenge this". Use grill-me ONLY for pure green-field thinking with no codebase at all — rare. | Skills | 77 Impact — Average score across 0 eval scenarios Securityby Passed No known issues Reviewed: Version: be88d6c |
Can't find what you're looking for? Evaluate a missing skill.