Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Add knowledge retrieval (RAG) to AI agents using Twilio Enterprise Knowledge. Covers provisioning Knowledge Bases, uploading sources from web URLs, PDFs, and raw text, and running semantic search to retrieve relevant chunks at runtime. Use this skill to ground agent responses in your organization's actual approved content — FAQs, policies, product docs — rather than hallucinated answers.
Design or critique a product's typography — typeface selection and pairing, type scale, hierarchy, and readability settings (size, line length, line height, spacing, alignment). Trigger when choosing a typeface or font pairing, setting up a type scale, fixing typographic hierarchy, improving text readability, or reviewing a UI layout for typography issues.
Use Venice as a pay-per-call JSON-RPC proxy to 27 EVM, Starknet, and Solana networks. Covers the public GET /crypto/rpc/networks, POST /crypto/rpc/{network}, chain families and their explicit per-family method allowlists, the 1×/2×/4× method-tier pricing model (~$7e-7 per credit), the per-minute rate limit and per-user request serialization, idempotency keys for safe retries, single vs batch (≤100) requests, and the unsupported stateful/WebSocket methods (eth_subscribe, eth_newFilter, *Subscribe, etc.).
Generate 3 scroll-stopping hook variants for short-form video scripts (Reels, TikTok, YouTube, LinkedIn, X). Use when the user is writing a script for short-form video, asks for hook ideas, needs an opening line for a Reel/post, or pastes a script and wants alternative hooks. Pulls from a library of 100 hook formulas across 10 psychology triggers (curiosity, contrarian, authority, emotional, listicle, question, story, negation, specificity, confession).
Create and manage Volcengine cloud resources using the Volcengine CLI (`ve` command). Supports all Volcengine services including ECS, VPC, CLB, RDS, Redis, and more. Trigger this skill whenever the user asks to create, query, modify, or delete cloud resources on Volcengine, mentions the `ve` command, says "volcengine CLI", or describes infrastructure tasks such as "create an ECS instance", "set up a VPC", "list security groups", "allocate an EIP". Also trigger on Chinese prompts mentioning "火山引擎" or "火山" (e.g., "火山引擎上有哪些 ECS"、"查一下我火山的云服务器"、 "火山引擎创建一个 VPC"、"火山的 Redis 实例列一下"). Also trigger when the user encounters errors from `ve` commands and needs troubleshooting help. Also use for TOS bucket/object operations, tosutil (sometimes written tosutils), Ark CLI / arkcli model discovery, inference, generation, endpoints, fine-tuning, plans, or usage, and TLS (日志服务) / volclog log search, analysis, ingest, export, or LogCollector collection, through `ve tosutil`, `ve arkcli` and `ve volclog`.
Use when writing, reviewing, or debugging code that imports from "@vueuse/shared" (or its utilities re-exported by "@vueuse/core"). Provides the v15.0.0 API surface, debounce and throttle defaults, watch variants, state-sharing patterns, and v14 to v15 migration rules.
Search the web and scrape pages using the local tool stack: SearXNG (meta-search), Lightpanda (fast headless fetch), and Agent-Browser (full browser automation). This is your DEFAULT web skill — use it whenever you need to look something up, research a topic, fetch a webpage, extract content from a URL, check current information, find documentation, do competitive research, or answer any question that benefits from live web data. Triggers on any form of: search for, look up, google, find out, research, what's the latest on, fetch this page, scrape this site, check this URL, pull info from, web search, or any task where current web information would improve your answer. Even if the user doesn't explicitly ask you to search — if answering well requires current info you don't have, use this skill. NOT for interactive browser automation like form filling or clicking (use [[agent-browser]] or [[browser-use]]).
Expert workstream coordinator managing multiple concurrent tasks, tracking progress, detecting conflicts and stalls, analyzing dependencies, and ensuring smooth parallel execution. Activates when coordinating workstreams, tracking progress, checking status, or managing concurrent work.
Solves a high-frequency practical pain point: after accumulating a large amount of traffic for a site in Yakit History, how to fetch all unique paths by domain in one go, obtain the login Cookie, consolidate those paths into a reusable Payload dictionary, and then send requests and scan/Fuzz path by path with the login state. Covers db.QueryHTTPFlowsByKeyword to fetch History, URI deduplication, Cookie extraction, db.SavePayload/YieldPayload dictionary management, and poc.HTTP request sending with login state. Use when the user wants to "extract data from historical traffic to drive subsequent scanning".
Yakit native plugins (yak / mitm types) and the cli parameter system. Explains the difference between native plugins and hot patching, how cli.* becomes the parameter form on the Yakit execution page (String/Int/Bool/Urls/Ports/StringSlice dropdown/File etc. + setRequired/setDefault/setVerboseName/setCliGroup), and three good examples: a yak native plugin using cli to collect user input, a mitm native plugin passively scanning complex content and producing risk, and an interactive mitm + cli plugin loading external parameters (keyword dictionary/scope) to drive scanning. Use when the user asks "how to write a yak/mitm plugin with a parameter form, how to use cli, how to do passive scanning with a mitm plugin".
Usage and programming techniques for Yakit right-click plugins (codec plugins). Explains that a codec plugin only needs a handle(input) function, and with plugin type codec + the "use for packet right-click" switch (tag: allow-custom-context-menu-execute) it appears in the right-click menu of any HTTP editor; it also covers the special contract where input=flow id on History right-click (single/multiple selection) (the id can be used to look up the packet and extract all paths/parameter names of the host, with a yakit.SetProgress progress bar and db Yield channel), using cli parameters in codec plugins for dropdown selection (extract Path/parameter names/Cookie), doing "strange transformations" on a Web Fuzzer selection, and how to verify with the yak codec-plugin command. Use when the user asks "how to write a right-click plugin / how to use codec plugins / extracting data via History right-click / Web Fuzzer right-click transformation / codec with parameters". Right-click plugins are the fastest way to write small tools.
Yaklang database operations (db library). Use when the user needs to persist or query data in scripts/plugins: temporary SQLite table creation and CRUD (db.OpenTempSqliteDatabase / db.ScanResult / Exec), key-value storage for cross-script shared configuration (db.SetKey/GetKey/DelKey/SetKeyWithTTL), unified management of brute-force dictionaries (db.SavePayload/YieldPayload), and project-level configuration (db.SetProjectKey/GetProjectKey).
Yaklang toolchain and plugin verification guide. Explains how to run scripts with the yaklang source engine (go run common/yak/cmd/yak.go), and how the four hot patch/codec verification commands (yak hotpatch-mitm / hotpatch-global / hotpatch-webfuzzer / codec-plugin) verify your MITM / global / Web Fuzzer hot patches and right-click codec plugins using the same execution path as real gRPC; it also explains how to locate and debug MITM issues with the yaklang repository source code. Use when the user asks "how do I verify the plugin I wrote / how do I debug incorrect MITM behavior".
Use when a problem or issue needs explicit framing before deeper analysis begins — establishing the Problem statement, Current state, Desired state, Stakeholders, and Success criteria. This should trigger when an issue's Problem Framing point of view needs evaluation, or when a maintainer directly asks to frame a problem before root-cause analysis, design, or planning begins. Part of Plinth Toolkit
Create academic presentation slide decks and optionally demo videos from research papers. Use when the user asks to "make slides", "create a deck", "make a presentation", "demo video", "paper slides", "conference talk slides", or wants to turn a paper into a visual presentation. Covers slide generation, narration scripts, TTS audio, and video assembly.
Adds Work IQ (M365 Copilot Search) to a Power Apps code app via the Work IQ Copilot MCP connector (shared_a365copilotchatmcp), then wires up a production-ready McpSession wrapper for AI-powered, knowledge-grounded search and chat. Use when integrating Microsoft 365 Copilot search/chat. The CopilotChat tool searches internal Microsoft 365 content (documents, emails, chats, sites, files) across your organization — prefer workload-specific tools (SharePoint, OneDrive, Teams, Mail) when the workload is explicit; do not use it for general knowledge, news, public web, or external information.
Generate an AI Citations Report (GEO) for a domain — which AI-search prompts cite the site across Google AI Overview and ChatGPT, plus organic-traffic context and per-article citation coverage. Use when the user asks for an 'AI citations report', 'GEO citations report', or 'which AI prompts cite <domain>'.
Automatically collect and summarize daily AI industry news, trends, and hot topics from platforms like GitHub (trending repos), X/Twitter (AI influencers/hashtags), and AI news aggregators. Use this skill when the user asks for "today's AI news", "AI industry updates", "what's trending in AI", or wants a daily digest of AI developments.
Recommend and generate appropriate data visualization charts using the GPT-Vis library. Supports two output modes — (1) Syntax mode, which generates Syntax or JSON configurations, and (2) Code mode, which generates complete runnable code. Supports 26 chart types.
Build interactive, click-through architecture diagrams for software systems — a self-contained single HTML file with animated step-by-step flows, mode toggles (dev/prod, offline/online, v1/v2), dark/light theme, and a side panel with payload details, plus a companion markdown description. Use when the user wants to visualize or design a system: architecture diagram, service map, data flow, RAG/agentic flow, microservices topology, integration diagram, CI/CD or data/ETL pipeline, multi-agent system, or onboarding diagram — or to design a new service's flows before building. Natural-language triggers: 'I'm building X, what should the flow look like', 'pokaż jak działa system', 'diagram architektury', 'wizualizacja systemu', 'klikany diagram'. Do NOT use for static diagrams that belong inline (Mermaid/PlantUML), slide decks, or printable/PDF handouts — this produces interactive HTML for browser consumption.
Build fully customizable, agent-ready design systems with Astryx — Meta's production design system now open source. Ships 150+ React components built on StyleX with zero styling lock-in, component swizzling, brand theming, dark mode, and CLI tooling. Use when building component libraries, design systems, UI applications, design tokens, or when teams need consistent accessible components that AI agents can understand and extend. Triggers on: astryx, design system, component library, design tokens, react components, accessible components, astryx design, stylesheets, theme customization, component composition.
Build or review a seven-part brand strategy covering identity, audience, positioning, messaging, visual principles, channels and measurement. Use when creating a brand brief, defining positioning or revising brand messaging. Trigger with "create brand strategy", "build brand brief" or "brand messaging".
Bright Data's MCP server, the tool layer that gives an LLM agent live web access with no shell. Use when wiring Bright Data tools into an AI app or agent framework that picks its tools at run time, when connecting Claude, Cursor, or another MCP client to Bright Data, when choosing which MCP tools or groups to turn on, or when the user says MCP. Covers the Remote server hosted at mcp.brightdata.com and the Local self-hosted @brightdata/mcp package, and which tool each job should route to. Not for the agent doing the job itself from a shell, which is brightdata-cli. Not for fixed repeated code in an app, which is brightdata-sdk. Not for install or auth problems, which is agent-onboarding.
Expert on CI/CD pipelines, GitHub Actions first but the principles port to any forge. GENERATE mode builds a repo's pipelines through an interactive analyze-then-confirm conversation (never batch the questions). ADVISE mode reviews, hardens, debugs, and speeds up existing CI and answers best-practice and security questions. Use when setting up or generating CI/CD, adding a workflow, reviewing or hardening a pipeline, auditing supply-chain risk (pinned actions, cache poisoning, pull_request_target, token scope), speeding up CI (caching, path filters, job DAG, pinned tool binaries), or wiring Renovate to bump CI tool pins. Triggers include set up CI, generate a workflow, harden my pipeline, secure my Actions, is my CI safe, speed up CI, pin my actions
Use when the user wants to "make a video/clip", "generate a video from text", "animate this image/photo", "create a marketing reel / social video / teaser", "do a 3D / parallax move", "pan/zoom/orbit a shot", or mentions fal.ai, Kling, Veo or Seedance for video. Staged fal.ai workflow — brainstorm, draft cheaply, produce the final at quality. Three modes: text-to-video, animate (still to motion), camera-move (push-in/pan/orbit). Not for still images (image-studio), slide decks, or charts. Honesty discipline: never depict real identifiable subjects via text-to-video.
Evidence-based CBT and DBT intervention skills — guided thought records, opposite action, DEAR MAN roleplay, crisis skills with optional HRV biofeedback. Configurable therapeutic pushback. Triggers on "/cbt", "/dbt", "/thought-record", "/record", "/opposite", "/opposite-action", "I need to work through something", "help me with a thought", "cognitive distortion", "I'm spiraling", "can we do a thought record".
Write comprehensive commercial proposals for B2B technology consulting engagements. Integrate solution briefs, ROI/business cases, consulting pricing models (T&M, Fixed, Outcome-based, Retainer, Blended), team structure, governance, timeline, and terms. Output includes commercial-proposal.md and preliminary workplan-and-estimate.md, which feeds into the PM suite’s project-intake-and-charter skill. Use when creating proposals, writing SOWs, pricing engagements, or preparing commercial offers. Triggers on: proposal, commercial proposal, SOW, pricing, quote, engagement offer, commercial offer, statement of work.
Prepare the first working session with a contracted supplier against a fixed day budget: reads the agreed offer or contract, then builds a branded session workbook whose day-budget sheet totals against the contracted ceiling, an internal prep brief, a supplier agenda and a post-session note template. Use for kick-off or delivery-session prep with a supplier, or day-budget splits over a signed offer. Distinct from tor-procurement (writes the ToR), selection-toolkit (panel scoring), procurement-offer-review (one incoming offer), implementation-pack (donor grants IPPF receives), and meeting-notes mode 2 (1-1 prep).
Crypto Twitter intelligence and alpha research. Search X/Twitter for real-time crypto narratives, trending tokens, yield strategies, smart money signals, and protocol research. Features TweetRank (PageRank-inspired credibility scoring), multi-signal token detection, coordinated raid detection, and dynamic tool discovery for execution suggestions. Solana-first but covers all major chains.
Use when a user needs to export the same DaVinci Resolve edit for multiple platforms — YouTube (16:9), LinkedIn (square 1:1), Reels/Shorts/TikTok (9:16) — with correct dimensions, loudness, and optionally batch automation. Triggering symptoms include phrases like "export for YouTube and LinkedIn", "make a vertical version", "9:16 from my 16:9 edit", "render the same edit three times", "batch render", "generate captions", or any DaVinci Resolve Deliver/render question.
Use when an architecture/product decision should be recorded or past decisions need re-checking — an ADR-style decision journal for agents and teams. Create numbered decision records, track superseding chains, schedule periodic reviews, and search past decisions to avoid re-litigating settled questions.
Polish a Flutter app's screens — visual hierarchy, typography, color and contrast, spacing, section clarity. Reads a reference screen first to lock in the app's existing design tone, then drives the running app on an Android emulator via the `android-emulator` skill (screenshots, taps, swipes), makes targeted widget and `ThemeData` edits, and spawns an independent evaluator sub-agent to score design quality, originality, craft, and functionality. Use this skill whenever the user wants to improve, polish, refine, critique, audit, or tighten the visual design of a Flutter screen — even when they don't say "polish" (e.g. "make this look better", "fix the layout on settings", "tighten up the home screen", "this screen feels off", "review the UI", "design pass", "make it less generic", "feels too Material default"). Skip for non-Flutter UIs, feature work, or routing/functionality changes.
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.
