Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
This skill should be used when the user asks to "create a character", "update a character", "add a character", "build a family tree", "character relationships", "character timeline", "character arc", "character profile", or needs to manage characters in a story project.
The 20 principles of UX and animation, extended with Emil Kowalski's animation rules, Interface Craft's motion techniques and more laws of UX, as one procedure for building or reviewing how an interface moves, responds and gets people through a task. Use when adding or reviewing animation, transitions, gestures, micro-interactions, loading and optimistic states, feedback, targets, menus, forms, onboarding or multi-step flows. Triggers on: animate, motion, transition, easing, duration, spring, bounce, stagger, enter, exit, modal, drawer, popover, tooltip, toast, icon swap, press, hover, drag, rubber band, arc, anticipation, squash and stretch, follow-through, compound motion, storyboard, reduced motion, jank, feels slow, optimistic UI, hit area, Fitts's law, Hick's law, Miller's law, Doherty threshold, Postel's law, Jakob's law, proximity, similarity, Von Restorff, serial position, peak-end, Zeigarnik, goal gradient, Tesler's law, Parkinson's law, Occam's razor, Pareto, progressive disclosure, defaults, undo.
Use when a Power Apps mobile project needs dependency updates or an npm audit review. Checks the mobile-app plugin first, then updates the native host, other Microsoft packages, and all remaining direct npm packages in order with validation and rollback.
Vision-enabled verification gate with web search. Use when users want to (1) verify slides/reports/PDFs/images against authoritative online sources, (2) validate that citations actually exist and say what's claimed, (3) check charts/graphs/tables for accuracy, (4) audit AI-generated content in doc-only mode (no external knowledge). Two modes - search mode validates against web, doc-only mode ensures everything traces to provided documents. Supports content in any language.
AI-powered video production suite: editing, transcoding, captioning, analysis, creation, shortform pipeline, image/video generation, web screenshots, AI audio/video enhancement. Uses FFmpeg, Whisper, PySceneDetect, FLUX.2, Veo, Playwright, Real-ESRGAN, Demucs, and Remotion. GPU-accelerated with NVIDIA NVENC. Use when user says "video", "ffmpeg", "trim", "cut", "transcode", "caption", "export", "analyze", "download", "create video", "shorts", "tiktok clips", "generate image", "generate video", "screenshot", "upscale", "enhance", "denoise", "separate vocals", "face restore", "slow motion", "remove background", or "/video".
Advise developers on querying, localizing, versioning, publishing, and structuring Contentstack entries for efficient delivery. Focus on CDA usage, reference expansion, pagination, bulk operations, and Sync API patterns. Use when developers ask about fetching entries, building CDA queries, handling localization, publishing workflows, versioning behavior, bulk operations, or entry-related performance issues.
Scan C/C++ codebases for code quality issues including extra large files/functions and circular dependencies. Use when the user asks to check file sizes, find oversized functions, detect circular dependencies, analyze code complexity, find code smells, or identify maintainability issues in C/C++ code. Supports scanning individual files or entire directories with configurable thresholds.
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise. This skill should be used when code-quality checks pass but the code would benefit from structural cleanup — deduplication, branching simplification, naming improvements, or dead-code removal. Invoked as a subagent from /code-quality or directly via the Task tool.
Searches the live web via Nimble APIs to monitor competitors and produce a structured intelligence briefing. Runs parallel searches for news, product launches, hiring signals, and funding — then compares against previous findings to highlight only what's new. Use this skill when the user asks about competitors, competitive intelligence, or what rival companies are doing. Common triggers: "what are my competitors doing", "competitor update", "competitor news", "competitive landscape", "market intel", "what's new with [company]", "track [company]", "competitor briefing", "who's making moves", "competitive analysis", "losing deals to [company]", "battlecard". Also use before board meetings or strategy sessions when the user wants competitive context. Requires the Nimble CLI (nimble search, nimble extract) for live web data. Do NOT use for single-company deep dives (use company-deep-dive), meeting prep with attendees (use meeting-prep), or non-business queries.
Integrates Promptfoo and DeepTeam into CI/CD for automated, repeatable red-teaming of LLM apps against OWASP LLM Top 10, OWASP Agentic, and MITRE ATLAS presets, failing the build when jailbreak or injection vulnerabilities regress. Use for continuous adversarial testing in CI/CD, a merge-blocking security gate, or comparing model/prompt versions for compliance reporting.
Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in any language, with whichever verification tool fits. Use for /create-formal-verification-skill, “model-check this race”, “prove this invariant”, or when concurrency, retries, state machines, parsers, or unsafe code need more than tests.
Create and package React Router pull requests. Use when the user asks to create, open, prepare, or finish a PR for this repository, including branch/commit/push handoff, draft PR creation, PR body writing, and applying GitHub labels such as pkg:*, feat:*, docs, github-actions, or dependencies.
Guides correct usage of Crowdin CLI - the `crowdin` command that syncs localization files between a local project and Crowdin. Use whenever the user runs, scripts, or debugs `crowdin` commands, authorizes the CLI, creates or edits a crowdin.yml configuration, uploads sources, downloads translations, checks translation status, auto-translates a project, wires localization into CI/CD, or migrates scripts from CLI v4 to v5 - even if they just say "sync translations" or "push strings to Crowdin" without naming the CLI.
Create or analyze settings, scenes, world operations, and image direction in the literary cyberpunk mode of William Gibson's Sprawl fiction: dense, accreted urban systems; uneven high technology; corporate power; mediated culture; and human-scale survival inside global networks. Use for Gibson-informed creative work, setting design, or visual briefs, not for generic neon cyberpunk, faithful continuation of named canon, or imitation of Gibson's prose.
Monitor, inspect, and query saved Fabric Dataflows Gen2 with read-only CLI. List dataflows, decode mashup.pq/queryMetadata.json/.platform, inspect parameters, refresh status, job history, staging, and destinations, or run saved/ad-hoc read-only executeQuery requests and parse Arrow. Handle explicit requests to mutate through the Dataflows consumption or read-only path by refusing the write; offer `dataflows-authoring-cli` only after separate confirmation. For candidate M before persistence or connection configuration, use `dataflows-authoring-cli`. Triggers: "list dataflows", "inspect dataflow", "decode dataflow definition", "dataflow parameters", "refresh history", "last refresh status", "dataflow job history", "execute dataflow query", "executeQuery saved query", "executeQuery fetch rows", "ad-hoc dataflow query", "parse Arrow response", "Arrow IPC", "dataflow staging analysis", "use Dataflows consumption path to delete", "Dataflows read-only mutation refusal", "separate Dataflows authoring handoff".
Create, update, validate, or export DESIGN.md from an existing repository, website, or explicit design decisions. Not for finding a new style, implementing pages, or refactoring components. Extract evidence-based design rules, preserve established conventions, and report deviations.
The VS Code design philosophy — a shared Values→Principles→Moves vocabulary for reasoning about UI in design terms instead of raw pixels. Use when designing, building, reviewing, or giving feedback on any visual surface; when deciding a radius, spacing, type role, icon size, border, color, or motion; or when translating a "this feels off" observation into a concrete, principled fix.
When the user wants to create physical mail campaigns, dimensional mailers, handwritten notes, or gift sequences for B2B prospecting. Also use when the user says 'direct mail,' 'send a package,' 'dimensional mailer,' 'handwritten note,' 'physical mail campaign,' 'gift send,' 'ABM mailer,' 'executive gifting,' 'account-based direct mail,' 'send something to their office,' 'physical touch,' 'lumpy mail,' 'drop a package.' For email outreach, see cold-email. For multi-channel sequence design, see outbound-sequence. For account research, see lead-research. For persona targeting, see buyer-persona.
Expert embedded Rust development for ESP32 microcontrollers using no-std, Embassy async framework, and the ESP-RS ecosystem (esp-hal, esp-rtos, esp-radio). Use when building, debugging, flashing, or adding features to ESP32 projects. Covers sensor integration (ADC, GPIO, I2C, SPI), power management (deep sleep, RTC memory), WiFi networking, MQTT clients, display drivers, async task patterns, memory allocation, error handling, and dependency management. Ideal for LilyGO boards, Espressif chips (ESP32, ESP32-S3, ESP32-C3), and any no-std Xtensa/RISC-V embedded development.
ESPHome device configuration, firmware, and IoT product development. Covers ESP32, ESP32-S3, ESP32-C3, ESP32-C6, ESP32-H2, ESP32-P4, ESP8266, RP2040, RP2350, nRF52, LibreTiny, Shelly, Sonoff, Tuya, BLE proxy, Matter firmware, Thread, Zigbee, GPIO, sensor YAML, LVGL displays, LED strips, voice assistant hardware, device flashing, Arduino conversion, alarm_control_panel, lock, valve, media_player, microphone, speaker, audio DAC, event entities, datetime entities, Z-Wave proxy, MIPI DSI displays, and DLMS smart meters. Also covers designing new ESPHome-based products: hardware selection, component sourcing, PCB design (KiCad), enclosures, 3D printing, CE/FCC certification, BOM optimization, and manufacturing from prototype to production scale.
Discovers, searches, and installs skills from multiple AI agent skill marketplaces (400K+ skills) using the SkillKit CLI. Supports browsing official partner collections (Anthropic, Vercel, Supabase, Stripe, and more) and community repositories, searching by domain or technology, and installing specific skills from GitHub. Use when the user wants to find, browse, or install new agent skills, plugins, extensions, or add-ons; asks 'is there a skill for X' or 'find a skill for X'; wants to explore a skill store or marketplace; needs to extend agent capabilities in areas like React, testing, DevOps, security, or APIs; or says 'browse skills', 'search skill marketplace', 'install a skill', or 'what skills are available'.
Bring a blocked React Router community pull request across the finish line. Use when the user invokes `/finish-line` or `$finish-line`, provides a PR number or URL, and asks Codex to resolve merge blockers such as a missing change file, missing documentation, missing tests, or stale contributor follow-up. Handles evaluating the blocker and pushing small maintainer fixes onto a contributor PR branch when authorized.
Draw a floorplan of an app's codebase (one repo or several side by side), an interactive node-graph map where every subsystem, module, file and HTTP route has a human-readable name and a one-line description, connected by the imports and HTTP calls between them, at several zoom levels. It is saved as a self-contained floorplan/index.html in the codebase. Use whenever the user wants to visualize, map, diagram, document or get an architectural overview of a codebase, repo or monorepo, understand how their app works or is connected under the hood, onboard onto unfamiliar code, see how the frontend talks to the backend, or update an existing floorplan, even if they don't say "visualize".
Create, repair, or harden provider-neutral Flutter CI/CD pipelines, quality gates, caches, artifacts, secrets, and staged delivery. Use for GitHub Actions, GitLab CI, Codemagic, Bitrise, Xcode Cloud, or similar orchestration; route local artifact configuration to flutter-build-release and never publish without explicit authorization.
Review Flutter and Dart diffs, commits, pull requests, focused code scopes, or completed implementations for concrete defects and regression risks. Use for an explicit change review or bounded delivery review; report evidence without edits. Not for broad threat audits, performance diagnosis, or test authoring.
Trigger this skill when specific legal consequences need to be derived from confirmed legal facts, identified legal relationships, and matched legal norms (including but not limited to the type and scope of civil liability, calculation of damages, determination of criminal sentences, type and extent of administrative penalties, validity status of contracts, etc.). Typical trigger scenarios include: - The user asks "how much compensation can I get" or "what liability does the other party bear" - The user asks "how many years will this behavior get" or "how much is the fine" - The need to derive specific legal effects from the satisfaction of legal constituent elements - The need to calculate quantified results such as specific compensation amounts, sentence ranges, or penalty amounts - The need to reach a final legal consequence after comprehensively considering adjustment factors such as aggravation, mitigation, or exemption. This skill is the terminal link in the legal reasoning chain, converting abstract legal norms into concrete, actionable legal conclusions.
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.