Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
High-rigor interview coaching skill for job seekers. Use when someone wants structured prep, transcript analysis, practice drills, storybank management, or performance tracking. Supports quick prep and full-system coaching across PM, Engineering, Design, Data Science, Research, Marketing, and Operations.
Automate post-meeting follow-up: search Fireflies for a meeting transcript, generate a structured summary with key decisions, discussion points, action items, and next steps, then draft a professional follow-up email to all attendees via Gmail. Use this skill whenever the user mentions processing a meeting, creating meeting notes, sending a meeting recap, drafting a follow-up email after a call, summarizing a meeting, or anything related to post-meeting workflows — even if they don't use the word "meeting" explicitly (e.g., "recap my call with Acme", "send notes from the standup", "what happened in my sync with the design team and send it out").
Expert mobile game developer specializing in iOS and Android game optimization, touch input design, battery and thermal management, device fragmentation handling, and App Store/Play Store submission. Deep knowledge of mobile-specific constraints and best practices for shipping performant, player-friendly mobile games. Use when "mobile game, ios game, android game, touch input, mobile optimization, mobile performance, app store, play store, mobile battery, thermal throttling, mobile porting, tablet game, phone game, mobile monetization, mobile build, mobile, ios, android, touch, optimization, performance, battery, thermal, app-store, play-store, game-development, unity-mobile, godot-mobile, device-fragmentation" mentioned.
Track changes in northbound or foreign capital preferences, industry flows, and style shifts to help assess capital support, crowded trades, and potential reversal signals. For monitoring capital flows, assessing styles, and validating sectors in the A-share market.
Builds and tunes PostgreSQL retrieval with pgvector, full-text search, pg_trgm, hybrid fusion, ParadeDB BM25, and reranking. Use for search/RAG implementation, weak results, filtered ANN scans, non-English corpora, or retrieval evaluation. For general schema, RLS, and query tuning unrelated to retrieval, use Supabase's supabase-postgres-best-practices skill
Test willingness to pay before launch with proven pricing research methodologies. Combine Van Westendorp, Gabor-Granger, and behavioral techniques to find your optimal price point. Use when: testing willingness to pay after solution validation; setting initial pricing before launch; testing new price points for pricing changes; understanding price sensitivity by segment; pricing against alternatives for competitive positioning
Build terminal UIs with ratatui following 2026 Rust best practices. Use when: (1) Creating new TUI apps, (2) Adding widgets/layouts, (3) Keyboard navigation/state management, (4) Image integration via ratatui-image, (5) Async event handling, (6) Release optimization. Covers v0.30.0+ API, Elm Architecture, StatefulWidget, color-eyre.
Audit and generate answer-extractable content — verify each question heading is followed by a ~40–60 word direct answer, passages are self-contained (~134–167 words, with no unresolved anaphora), and lists, tables, definitions, and TL;DR blocks exist; draft answer-block and summary rewrites for the user to accept. Module M11. Feeds the AI Visibility score
Audit fact density and sourcing on a page — measure statistic/number density per passage, detect proprietary/original data, count outbound citations to authoritative sources, and flag claims made without a supporting stat or source. Module M12. Feeds the AI Visibility score. Advisory-only; never fabricates statistics or sources.
Audit and fix image and media accessibility for a page — detect missing, empty, duplicated, or keyword-stuffed alt text; check alt quality and length, missing width/height (CLS), legacy formats, and absent VideoObject schema; generate contextual alt text and dimensions. Module M9. Feeds both the Search SEO and AI Visibility scores
Audit a page's rendering strategy and JavaScript dependency — diff raw HTML against the rendered DOM to measure how much primary content, links, headings, and JSON-LD exist only after JS executes; classify CSR-only / SSR / SSG / ISR, and emit framework-specific guidance. Module M4. Feeds both the Search SEO and AI Visibility scores
Audit and generate Open Graph and Twitter/X social-card tags for a page — check og:title/description/url/type, og:image presence/size/reachability, and twitter:card/title/description/image, then inject complete card tags inferred from the page. Module M8. Feeds the Search SEO score
Fetch website traffic estimates (monthly visits, traffic sources, top countries, keywords, engagement, ranks) for any domain from SimilarWeb. Use when the user asks about a domain's traffic, monthly visits, traffic sources, audience countries, or wants to compare or benchmark sites against competitors.
Help users find suitable tools from the currently released PostPlus skill surface and provide public installation commands. Use this when the user asks which skill can do a task, which skill to install, or what the released skill surface covers.
Skill security auditing tool. Verifies the security of Claude Code skills by checking for malicious code, sensitive information leaks, dangerous operations, and more. Conducts a security assessment and generates a security report before installing or using new skills.
Model threats and review the security of applications, APIs, authentication, authorization, data, dependencies, secrets, and infrastructure. Use for changes involving trust boundaries, identity, external input, sensitive data, or security reviews; do not claim something is secure without evidence.
Implements Syncfusion .NET MAUI Picker (SfPicker) control. Use when working with picker controls, item pickers, selection pickers, multi-column pickers, or dialog pickers in .NET MAUI applications. This skill covers installation, configuration, modes (Default, Dialog, RelativeDialog), header/footer customization, column handling, data binding, events, and accessibility.
Enforces test doctrine where shape follows code, not the pyramid: pushes logic into Flutter-free packages tested with pure package:test and an injected Clock; asserts invariants with seeded fuzz tests against an independent oracle plus round-trip and rounding goldens; prefers bare-implements fakes over mocktail for code you own; tests the data layer against a real NativeDatabase.memory Drift engine, never a mocked DAO; drives Notifiers headlessly with ProviderContainer overrides; guards one end-to-end acceptance gate and a runtime invariant tripwire; floors coverage on unrecoverable-bug files, not a global percentage; and fixes the coverage-lies-upward gap. Use when writing tests under test/ or integration_test/, choosing unit vs widget vs integration, adding a fuzz or round-trip property, wiring a fake or ProviderContainer test, gating coverage, or triaging a flaky-suite failure.
Use tmux from the command line to run, drive, and monitor terminal programs as a coding agent (detached sessions, send-keys input injection, capture-pane output polling, formats, completion detection, and control mode). Use when a task needs long-running or interactive processes (builds, tests, servers, REPLs, watch modes, TUI apps) kept alive across turns or inspected live; skip when plain `cmd > log 2>&1 &` is enough.
Interpret hits from CRISPR-KO/CRISPRi/shRNA screens by integrating DepMap essentiality, gnomAD constraint scores, pathway context (Reactome, STRING), druggability (DGIdb), and clinical evidence (CIViC, COSMIC). Use for screen-hit prioritization, essentiality ranking, and turning a list of screen hits into a prioritized target shortlist.
Non-coding RNA analysis — miRNAs (miRBase, miRDB targets), lncRNAs (LNCipedia, RNAcentral), circRNAs, snoRNAs, and other ncRNA classes. Distinct mechanisms per class — miRNAs repress mRNA; lncRNAs scaffold/decoy/enhance. Use for ncRNA function prediction, miRNA-target prediction, lncRNA functional annotation, and ncRNA-disease association queries.
Meta-router for the tmux-agent-tools plugin. Invoke BEFORE choosing a wrapper or delegating any tmux-agent work — it decides inline vs worker, picks the right script, and points to the canonical capability table. Invoke it even if there is only a 1% chance it applies.
Create and edit videos using Google's Veo 2 and Veo 3 models. Supports Text-to-Video, Image-to-Video, Reference-to-Video, Inpainting, and Video Extension. Available parameters: prompt, image, mask, mode, duration, aspect-ratio. Always confirm parameters with the user or explicitly state defaults before running.
Operate a Vexdock server (self-hosted deployment platform) through its REST API with a bearer token. Use when asked to deploy, inspect, restart, run a command in, configure or clean up anything on a Vexdock host, or when VEXDOCK_URL and VEXDOCK_TOKEN are set in the environment.
Benchmark vLLM or OpenAI-compatible serving endpoints using vllm bench serve. Supports multiple datasets (random, sharegpt, sonnet, HF), backends (openai, openai-chat, vllm-pooling, embeddings), throughput/latency testing with request-rate control, and result saving. Use when benchmarking LLM serving performance, measuring TTFT/TPOT, or load testing inference APIs
Use when the user has an SRT (or transcript text) in one language and wants it translated to another, with punctuation-bounded re-segmentation so cues end at real sentence breaks. Simplified Chinese (zh-CN) and English (en) are first-class targets; other targets follow the same rules. Outputs a target-language SRT or bilingual SRT — no audio, no burn-in. Triggers — "翻译字幕", "翻成中文", "translate this SRT", "中英双语字幕", "把这个 SRT 翻译成 X", "bilingual subtitles"
Enforces accessibility as a correctness property authored into each widget: Semantics(button/label) or ExcludeSemantics on every node; a11y state read from MediaQuery, not app state; never MediaQuery.withClampedTextScaling / textScaleFactor / FittedBox / TextOverflow.ellipsis to fit a label; non-color redundant channels (icon+label+shape+text) for every state; contrast against composited backgrounds (4.5:1 body / 3:1 large); 44px single-tap targets; OrdinalSortKey traversal; and honoring boldText / reduce-motion. Use when adding a GestureDetector/InkWell or any tap target, adding an Icon or Image, reaching for withClampedTextScaling/FittedBox/ellipsis/textScaleFactor to make text fit, encoding state via color, sizing type, ordering focus traversal, or reviewing any View for screen-reader/switch/low-vision support.
Acton CLI workflow for TON smart contract development in Tolk: install/update, project bootstrap, Acton.toml configuration, build/compile/wrapper generation, tests with coverage/gas/fuzz/mutation/UI, scripts and deployment, wallets, verification, RPC inspection, libraries, lint/format/hooks, LSP/completions, and troubleshooting.
Integrate Base Builder Codes (ERC-8021) into web3 applications for onchain transaction attribution and referral fee earning. Use when a project needs to append a builder code or dataSuffix to transactions on Base L2, whether using Wagmi, Viem, Privy, ethers.js, or raw window.ethereum. Covers phrases like "add builder codes", "integrate builder codes", "earn referral fees on Base transactions", "append a builder code to my transactions", "transaction attribution", "Builder Code integration", or "attribute transactions to my app". Handles project analysis to detect frameworks, locating transaction call sites, and replacing them with attributed versions.
Alicloud OSS AI Content Awareness Skill. Use for enabling and querying OSS semantic search with AI-powered content understanding. Triggers: “OSS AI Content Awareness”, “OSS semantic search”, “OSS vector search”, “search by text”, “text-to-image search”, “text-to-video search”, “OSS MetaQuery”, “OSS data index”, “OSS AI内容感知”, “OSS语义检索”, “OSS向量检索”, “以文搜图”, “以文搜视频”, “OSS数据索引”
Expert knowledge for Azure AI Document Intelligence development including troubleshooting, best practices, decision making, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using AnalyzeDocument APIs, custom/classification/template models, batch analysis, containers, or v4.0 migration, and other Azure AI Document Intelligence related development tasks. Not for Azure AI Vision (use azure-ai-vision), Azure AI Custom Vision (use azure-custom-vision), Azure AI Search (use azure-cognitive-search), Azure AI Video Indexer (use azure-video-indexer).
Generate professional infographics with 21 layout types and 22 visual styles. Analyzes content, recommends layout×style combinations, and generates publication-ready infographics. Use when user asks to create "infographic", "信息图", "visual summary", "可视化", or "高密度信息大图".
Use when designing, writing, or reviewing PHP in Bitrix CMS or Bitrix24, including controllers, HTTP requests and responses, JSON payloads, routing, module loading, geolocation, URLs, outbound HTTP integrations, JWT, dates and time, configuration, logging, UUID generation, validation, dependency injection, persistent storage, caching, events, error handling, and operation results. Guides selection of Bitrix APIs and framework patterns.
Use this skill whenever the user wants to integrate BoldSign eSignature into their application. This includes sending documents for signature, setting up embedded signing or sending, configuring webhooks, working with templates, implementing Sender Identities for multi-tenant SaaS, choosing between OAuth and Sender Identities, handling rate limits, or generating stack-specific code in Node.js, TypeScript, Python, .NET/C#, or PHP. Also use this skill when the user asks about BoldSign best practices, common integration mistakes, sandbox vs live environment differences, or how to avoid pitfalls like polling instead of webhooks, skipping HMAC verification, or hitting rate limits. If the user mentions BoldSign, eSignature, document signing, or wants to automate a signing workflow, use this skill.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.