Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Provider-independent localization and dubbing production direction for AI agents producing translated videos, dubbed ads, social clips, explainers, avatar videos, documentaries, training media, and multi-market campaigns. Use when planning or reviewing subtitle-versus-dub strategy, translation adaptation, glossary/style-guide setup, casting or voice matching, lip-sync or phrase-sync direction, synthetic dubbing boundaries, captions/subtitles handoff, accessibility, platform delivery, client review, or localization QA.
Best practices for Flutter theming with Material 3, treating ThemeData as the single source of truth for colors, typography, component styles, and spacing. Use when creating, modifying, or reviewing ThemeData, ColorScheme, TextTheme, component themes, spacing systems, or light/dark mode support, and whenever widget code carries its own styling: a hardcoded Color, an inline TextStyle, raw padding or gap numbers, the same decoration repeated across widget instances, or a brightness/dark-mode conditional inside build, even when the request only says "review this widget", "cut the duplication", "stop repeating this", or "tidy this up".
Load this skill whenever the project uses Mermaid diagrams — flowcharts, sequence diagrams, class diagrams, Gantt charts, or any Mermaid-rendered visualization. Under no circumstances render a Mermaid diagram without an accessible title, description, and text-based alternative. Absolutely always add accTitle: and accDescr: (no %% prefix — that is the comment syntax and will be silently ignored) to every diagram.
Checks if a community pull request is ready for human review. Verifies CLA signature, PR title format, description completeness, test coverage, and cubic-dev-ai issues, then triages to the right Linear team or recommends a close. Use when given a PR number or branch name to review, or when the user says /community-pr-readiness-check, or asks to check if a PR is ready for review.
Authors a new Instance AI workflow or Agent eval case — written locally as JSON, calibrated against a real build, then pushed to the LangTracer suite CI runs — build cases, behaviour/process cases, credential cases, and seeded (mid-conversation) cases — with intent-driven expectations. Use when adding or changing an Instance AI eval, or debugging why one is flaky.
Guides work on `packages/frontend/editor-ui` experiments. Use when creating, extending, wiring, testing, reviewing, or retiring editor-ui experiments, PostHog feature flags, experiment key indexes, variants, stores/composables, persisted experiment state, or experiment telemetry.
Agent-callable Notion tools for searching pages and databases, reading and creating pages, querying data sources, appending content, and managing schemas. Use when the user mentions Notion or wants to find, read, create, or edit Notion content, even if they don't name Notion explicitly.
Optimizes Python library performance through profiling (cProfile, PyInstrument), memory analysis (memray, tracemalloc), benchmarking (pytest-benchmark), and optimization strategies. Use when analyzing performance bottlenecks, finding memory leaks, or setting up performance regression testing.
Deep analysis and expert reasoning. Use when the user asks for 'oracle', 'second opinion', architecture analysis, elusive bug debugging, impact assessment, security reasoning, refactoring strategy, or trade-off evaluation — problems that benefit from deep, independent reasoning. Do not use for simple factual questions, code generation, code review (use council-review), or tasks needing file modifications.
Read, search, and download emails and attachments from Microsoft Outlook via OAuth2. Use when the user asks to (1) check, read, or fetch emails or messages from Outlook, (2) search emails by keyword, sender, or subject, (3) download email attachments such as contracts, NDAs, or documents, (4) chain email content into other skills (e.g. "read the latest email from X and review the attached NDA"), or (5) any task involving Microsoft Outlook, Office 365, or Exchange email access.
Run, verify, reseed, and repair Paperclip isolated dev workspace services. Use when asked to start or fix a managed project/worktree service and prove health, login readiness, cloned data, runtime visibility, and correct port ownership.
Voice a papercut reel and time it to the picture. Three paths, local Qwen3-TTS, your own recording or another TTS, or a placeholder voice. Covers delivery rules, voice.json, captions and scene timing. Use for "set up the voice", "re-voice this", "time the script"
Migrate a Figma design into Penpot with high fidelity: Figma Auto Layout → Penpot flex/grid, Figma Variables → Penpot tokens, Figma component sets → Penpot variants, preserving hierarchy. Reads via the Figma MCP, writes via the Penpot MCP, through an intermediate representation (IR). Degrades to manually-pasted Figma data if the Figma MCP is absent. Triggers: 'migrate from Figma', 'import this Figma file into Penpot', 'move our Figma library to Penpot', 'recreate this Figma design in Penpot', 'Figma to Penpot'.
Profiles application performance under load using k6, Artillery, or JMeter to measure latency, throughput, and error rates. Use when planning load tests, stress tests, soak tests, benchmarking APIs, or identifying performance bottlenecks.
Use this skill when users need to find their unique marketing angle, differentiate from competitors, or transform their positioning. Activates for "find my angle," "how do I stand out," "why isn't this selling," "we sound like everyone else," or positioning strategy questions.
Guide product discovery conversations and produce standard PRD documents in Chinese. Use when the user describes a product idea, feature request, improvement request, vibe-coding project, MVP scope, or explicitly asks to write a PRD, product requirements document, 需求文档, 产品需求, or 功能规格. Enforce a staged workflow by diagnosing from user/business/technical perspectives, confirming page structure and navigation, outputting a concise concept PRD for alignment, freezing scope, then generating an implementation-ready PRD with flows, states, fields, copy, and exception handling.
Provider-independent production guidance for converting observed video into precise, objective, temporally ordered language. Use for shot descriptions, searchable metadata, dataset captions, reference logs, generation-prompt handoffs, and analysis across subject, scene, motion, spatial, and camera aspects; not for deciding what to shoot, accessibility captions, creative interpretation, or provider-specific video analysis APIs.
Create polished, audience-tailored presentations from outlines or documents, with support for Marp, reveal.js, Google Slides, and PPTX output formats. Use when the user requests presentation creation or provides relevant inputs for this workflow.
Give every sandbox, container, device, or tenant its own isolated ngrok endpoint, provisioned programmatically at runtime from a controlplane. Covers the per-workload resource set - service user, reserved address or domain, ACL-scoped authtoken, cloud endpoint forwarding to a private internal endpoint - plus the agent config that runs inside the workload, and teardown. Use when the user is building a platform that spins up isolated environments.
Turn a thesis, proposition, trend, question, or explainer topic into a citation-backed, image-rich, interactive website and deploy it with Vercel CLI. Use when the user asks to research a claim deeply, generate visuals, build a shareable web experience, publish a microsite, create an interactive story/report, or deploy a researched site to Vercel.
Use when reviewing PL/SQL - a changed procedure or package, a proposed file, or an object suspected of causing trouble. Combines the database's own correctness signals with the antipattern checklist, and reports findings anchored to line numbers.
Use when writing or modifying PL/SQL source - a procedure, function, package, trigger, or view - after impact is known and the spec is settled (open decisions go through pythia-spec first). The codebase's conventions already exist; copy them instead of inventing style, and anchor every type to the database's reality.
Diagnose and optimize existing slow SQL queries using execution plans, indexing strategies, query rewriting, and ORM tuning. Use when the user provides a query, performance symptom, or EXPLAIN plan; use sql-query-generation when creating a new query from requirements.
Produce text-to-speech with Alibaba/Qwen Qwen3-TTS through DashScope/Model Studio or open-weight Qwen3-TTS checkpoints. Use when an agent must choose Qwen3-TTS models, voices, realtime versus non-realtime synthesis, voice cloning, voice design, instruction/prosody controls, multilingual or dialect speech, audio artifact handling, regional routing, pricing/privacy/licensing constraints, or production QA for narration, characters, assistants, audiobooks, ads, localization, or voice-enabled media.
React component and hook testing patterns with Testing Library and Vitest. Use when writing tests for React components, custom hooks, or data fetching logic. Covers component rendering tests, user interaction simulation, async state testing, MSW for API mocking, hook testing with renderHook, accessibility assertions, and snapshot testing guidelines. Does NOT cover E2E tests (use e2e-testing) or TDD workflow enforcement (use tdd-workflow).
Recreate a website from a link — evidence-driven reconstruction with the awwwards MCP. Use when the user says "recreate this site", "clone this page", "rebuild <url>", or gives a URL and asks to build it. Produces a faithful hand-built implementation (HTML/CSS/JS + GSAP/Lenis as the reference demands), QA-verified against the live site, then optionally converted into a Vite/Astro/Next project.
Give Claude any viral reel (a link or a file) and it studies the whole thing—frame by frame plus the transcript—then breaks down exactly why it works: the hook, the beat structure, the pacing, and the on-screen visuals. Use when the user says “study this reel”, “break down this video”, “analyze this reel”, “why did this go viral”, “what’s the structure of this”, or pastes a reel/TikTok/Short link and wants to model it.
Provider-independent production workflow for assembling generated or sourced media into React/Remotion videos. Use when an agent must plan, build, render, review, variant-render, or hand off Remotion compositions with media custody, captions, audio, animation, accessibility, provenance, QA, and delivery requirements.
Assess and respond to pull request review comments through a status-gated workflow: collect comments, evaluate feedback, draft replies, write a verified local report, and optionally post exact approved replies to supported GitHub review-comment threads.
This skill should be used when the user asks to "review the security architecture", "check authentication patterns", "evaluate trust boundaries", "review encryption implementation", "assess authorization design", or needs to evaluate system designs for authentication, authorization, data protection, or cryptographic correctness.
Design, implement, test, and operate production Rust server-side HTTP services, including axum, Actix Web, routing, extractors, application state, error mapping, middleware order, timeouts, body limits, observability, graceful shutdown, and database boundaries. Use when users ask for Rust REST APIs, web handlers, middleware, server lifecycle, HTTP contracts, or production web-service architecture; hand security controls to rust-web-security.
Threat-model, implement, review, and test Rust web security, including authentication, object and tenant authorization, sessions, cookies, JWT and OIDC validation, CSRF, CORS, SSRF, input limits, secrets, cryptographic dependency boundaries, audit logging, and negative security tests. Use when users ask to secure or audit Rust web services, tokens, browser transport, multi-tenant access, secret handling, or security incident fixes.
Software Bill of Materials (SBOM) security analysis for vulnerability assessment and third-party risk management. Validates SBOMs from vendors or generates SBOMs for internal projects. Use this skill when: - User asks to analyze an SBOM file - User mentions “third-party risk” or “vendor security” - User needs to validate a supplier's SBOM - User wants to check SBOM for vulnerabilities - User asks about CycloneDX or SPDX formats
Use this skill to install and verify Compose HotSwan end to end so a developer goes from zero to working sub-second hot reload on a real device or emulator in one session. Covers the JetBrains IDE plugin install, the `com.github.skydoves.compose.hotswan.compiler` Gradle plugin wiring, the canonical `hotSwanCompiler { enabled = true; debugOnly = true }` DSL block, the HotSwan tool window flow, and the first save-to-reload verification. Trigger when the user mentions HotSwan, Compose hot reload, instant UI update, "save and see", "no rebuild", live edit on device, fast Compose iteration, or already has the JetBrains plugin installed and asks how to apply the Gradle compiler plugin.
Automate the EvenHub glasses simulator via its HTTP API. Use when testing or controlling the simulator programmatically — sending glasses input (up, down, click, double click), capturing screenshots, or reading browser console logs
Create, improve, and manage Droid skills. Use when the user wants to: - Create new skills from scratch or from session learnings - Improve existing skills based on user preferences - Analyze sessions to identify patterns worth codifying - Understand best practices for agentic skill design This is a meta-skill for self-improvement and continuous learning.
Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".
Generate, visually edit, and export beautiful HTML/CSS presentation decks with agents using slides-grab (NomaDamas, MIT) — the open-source Claude Design alternative and best harness + editor + linter for slides in Claude Code / Codex. One routing-first skill across Plan (agent drafts an outline), Design (each slide is a self-contained slide-XX.html), Edit (a pure-JS browser editor where you drag a bbox over any region and ask the agent to rewrite just that area, or hand-tweak text/size/bold), and Export (capture-or-print PDF, per-slide PNG incl. Instagram 1:1 card-news, plus experimental/unstable PPTX and Figma-importable PPTX). Picks an install path (npm package + npx skills add, or clone), a deck workspace (--slides-dir, multi-deck decks/<name>/), one of 35 bundled design styles, and the supported asset flow (local ./assets/<file> only — image via god-tibo-imagen/codex/nano-banana, fetch-video via yt-dlp, tldraw .tldr→SVG), validating with slides-grab validate before any export.
AI-powered comprehensive codebase documentation generator. Analyzes project structure, identifies architecture patterns, creates C4 model diagrams, and generates professional technical documentation. Use when users need to document codebases, understand software architecture, create technical specs, or generate developer guides. Supports all programming languages. Alternative to Litho/deepwiki-rs that uses Claude Code subscription without external API costs.
Manages Fabric Spark work, including notebook cell code with %%configure, %%sql, PySpark and notebookutils, named notebook runs, Livy sessions, triage of failed or OOM notebook and pipeline Spark runs, and the Materialized Lake View (MLV) lifecycle. Load it before writing MLV SQL, since CREATE MATERIALIZED LAKE VIEW and its CONSTRAINT clause are Fabric-only. KQL materialized views belong to eventhouse-cli.
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.
