Skills
98,639 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when exactly one of several properties should be present. Use when modeling mutually exclusive options. Use when building component props with alternative configurations. Use when designing API parameters that have variants.
Create and run LangWatch experiments for pre-deployment batch testing. Use when the user wants to test an agent against a dataset, compare prompts or models, benchmark quality, detect regressions, or add a CI quality gate. Do not use for production monitoring or guardrails.
Prevent duplicate agent actions, infinite retry loops, and unverified churn across all lifecycles. Reuses matching accepted evidence, enforces typed invalidations for changed work, gates deterministic local failures for local repair, and manages candidate promotion readiness with zero token overhead.
Prevent, detect, and repair AI coding slop and dirty engineering in repositories. Use for planning features, writing code, changing tests, reviewing pull requests, refactoring, hardening CI, debugging regressions, or auditing agent-generated changes. Enforces behavioral contracts, focused diffs, test integrity, repo conventions, security boundaries, and evidence-based completion.
Automatically configure and switch to domestic mirror sources to speed up package manager installs. Use this skill when the user installs packages/dependencies (e.g. npm install, pip install, yarn install, brew install, apt install, gem install, cargo install, go get), complains about slow downloads, install timeouts or network issues, or explicitly asks about domestic mirror sources.
Fetch and summarize Feishu group chat history. Use when the user asks to read, review, or summarize messages from a Feishu group chat. Triggers: "看群聊记录", "群里聊了啥", "帮我看看这个群", "群消息历史", "chat history", "what did the group discuss". NOT for: sending messages (use message tool), reading documents (use feishu-doc skill), or wiki operations (use feishu-wiki skill).
Generate structured developer handoff annotations for a Figma screen or component. Use when asked to write Figma annotations, create dev handoff notes, document a Figma design for developers, or write specs for a screen. Produces a complete annotation set covering interactions, states, spacing, accessibility, and edge cases.
Define component variants and states systematically for Figma. Use when asked to plan component variants, define states for a component, set up a Figma variant matrix, or work out what properties a component needs before building it. Produces a complete variant matrix with all properties, values, and combinations needed.
Turn financial model outputs into a clear written narrative. Use when asked to write a financial narrative, explain a financial model, summarise a P&L, or translate spreadsheet numbers into a board-ready story. Produces an executive narrative with key insights, drivers, and forward-looking commentary.
Search, scrape, and interact with the web via the Firecrawl CLI. Use this skill whenever the user wants to search the web, find articles, research a topic, look something up online, scrape a webpage, grab content from a URL, get data from a website, crawl documentation, download a site, or interact with pages that need clicks or logins. Also use when they say "fetch this page", "pull the content from", "get the page at https://", or reference external websites. This provides real-time web search with full page content and interact capabilities — beyond what Claude can do natively with built-in tools. Do NOT trigger for local file operations, git commands, deployments, or code editing tasks.
Builds NUI interfaces for FiveM using React 18 + TypeScript + Vite + Tailwind CSS v3 + Zustand. Use when the user mentions NUI, interface, UI, menu, HUD, panel, overlay, React, Vite, Tailwind, or any in-game interface for FiveM — regardless of the backend framework (vRP, QBCore, Qbox, ESX). Covers project structure, FiveM CEF restrictions, observe/Post hooks, VisibilityProvider, animations, dynamic config/theme, and performance rules.
Orchestrate the path from a raw research idea to a formal claim with a defensible proof design — drawing the hypothesis out of the idea, stating it as a precise theorem/claim, and designing (and auditing) the proof strategy. Use whenever the user says "help me turn this idea into a theorem", "I have a hunch, can we make it rigorous", "design a proof for this", "what would I need to prove this", "formalize this claim", "is this provable and how", or hands over an informal conjecture they want to develop into a formal result. This is a ROUTER that sequences existing singleton skills; it does not write the proof itself. Use flow-learn-new-topic or flow-deep-understanding when the goal is to understand existing work rather than formalize the user's own idea. Use gap-finder when the starting point is an existing paper's weakness rather than a fresh idea.
Data layer patterns for Flutter projects — DataSource interfaces and implementations, Repository, mapping DTOs to domain models, `fromJson` on freezed models, and reactive repositories built with `rxdart`'s `BehaviorSubject`. Triggered by phrases such as "create DataSource", "implement Repository", "repository", "local/remote data source", "BehaviorSubject", "stream repository", "DTO mapping", "fromJson".
How to set up get_it-based dependency injection in Flutter projects. Covers writing the `diSetup()` function, the registration order for DataSource/Repository/UseCase/ViewModel, choosing between singleton and factory, and the pattern of calling `getIt<T>()` in the Root widget. Be sure to use this skill when phrases such as "DI setup", "get_it", "registerSingleton", "registerFactory", "dependency injection", "register ViewModel", "diSetup", "getIt instance" come up.
Type-safe error handling patterns for Flutter projects — an `Error` marker interface, a freezed-based `Result<D, E>` sealed class, per-feature error enums, and handling success/failure with `switch` pattern matching. Triggered by phrases such as "Result wrapper", "error handling", "ResultSuccess", "ResultError", "NetworkError", "type-safe errors", "freezed sealed", "Result instead of exception".
Maintains showcase/flutter_test_app and intentcall web targets (Chrome, web codegen, WebMCP bootstrap, web-showcase, webmcp verify, Chrome DevTools MCP). Use when editing web/index.html, agent_manifest.json, intentcall_webmcp.generated.js, web platform sync, Chrome dogfood, WebMCP modelContext, or agent WebMCP list/execute.
Presentation layer patterns for Flutter projects — `ChangeNotifier`-based ViewModels, freezed `State` and sealed `Action`, separating Root/Screen widgets, observing with `ListenableBuilder`, and delivering one-off events through `StreamController`. Triggered by phrases such as "create ViewModel", "State/Action", "MVI", "ChangeNotifier", "separate Root and Screen", "onAction", "notifyListeners", "ListenableBuilder".
Flutter widget UI patterns — preferring StatelessWidget, `const` optimization, observing ViewModels with `ListenableBuilder`, `ListView.builder`/`IndexedStack`, reusing shared components, accessibility (Semantics), and handling dialogs and snack bars. Triggered by phrases such as "create widget", "create UI", "StatelessWidget", "ListView", "ListenableBuilder", "Scaffold", "snack bar", "dialog", "design token", "shared component".
Use for frontend architecture boundaries: code ownership, directory roles, file placement, import direction, UI/component extraction, API/data contracts, fetching/query, URL state, mappers/schemas/DTOs, hooks/stores, architecture docs, and tool enforcement. Also use before agent-initiated architecture-enforcement changes in lint, CI, import-boundary checks, or similar automation—even without a user request—and for small UI changes that may leak business rules or external data into lower-level code.
Create stunning, animation-rich HTML presentations from scratch, or generate them by converting PowerPoint files. Use when the user wants to build a presentation, convert PPT/PPTX to the web, or create slides for a talk or pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
Write tests that start with acceptance criteria, then add implementation tests for robustness. Use when writing unit tests (Vitest), end-to-end tests (Playwright), visual regression tests, or accessibility tests. Emphasizes user-centric testing, semantic locators, accessibility validation, and the balance between acceptance and implementation testing.
Audits existing game code against design principles — checks server-authority, schema conventions, auth security, payment safety, narrative coherence, and MVP scope drift. Extract the optional component name or path from the user's message (defaults to entire src/). Use after building components or before committing.
Use when the user needs to inspect Google Cloud (GCP) logs, metrics, and monitoring signals via gcloud for incident triage, debugging, or operational analysis. Supports Cloud Logging queries, Cloud Monitoring time-series reads, and environment checks for a target project.
AI-powered code vulnerability analysis and dependency scanning using Gemini CLI security extension patterns. Detects hardcoded secrets, injection attacks, weak cryptography, authentication flaws, and LLM prompt injection. Also scans dependencies against the OSV.dev vulnerability database.
This skill should be used when the user asks to "generate a video", "create a video", "animate an image", "text to video", "image to video", "make a video clip", "video from image", "bring this image to life", "subject-consistent video", "match character likeness in video", "interpolate between frames", or needs AI video generation using Veo 3.1. Handles prompt rewriting, style application, reference images for subject consistency, and Gemini Veo video generation API calls.
Use this skill when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.
End-to-end lead prospecting from Luma events. Searches Luma for events by topic and location, extracts all attendees/hosts, qualifies them against a qualification prompt, outputs results to a Google Sheet, and sends a Slack alert with top leads. Use this skill whenever someone wants to find qualified leads from events, prospect event attendees, or run an event-based lead gen workflow. Also triggers for "find people at events and qualify them" or "who's attending X events that matches our ICP."
CLI/Python toolkit for rapid bioinformatics queries. Preferred for quick BLAST searches. Access to 20+ databases: gene info (Ensembl/UniProt), AlphaFold, ARCHS4, Enrichr, OpenTargets, COSMIC, genome downloads. For advanced BLAST/batch processing, use biopython. For multi-database integration, use bioservices.
Use when the user asks to rewrite recent non-Conventional commit subjects, fix existing commit messages, or clean up commit history. Trigger on phrases like "rewrite commit history", "fix these commit messages", "커밋 메시지 다시 써줘", "/git-commit-rewrite", "$git-commit-rewrite", or whenever the user shows a non-Conventional `git log` and asks for help. For new commits use `git-commit`; for commit + push use `git-commit-push`.
Use when the user asks to merge the current branch into the dev branch (`dev`, falling back to `develop`) and delete the merged source branch unless the source is protected. Trigger on phrases like "merge to dev", "dev에 머지", "develop에 합쳐줘", "merge this into dev and delete it", "/git-merge-to-dev", or "$git-merge-to-dev". For `main` use `git-merge-to-main`; to bulk-clean already-merged branches use `git-branch-cleanup`.
Use when the user asks to merge the current branch into `main` and delete the merged source branch unless the source is protected. Trigger on phrases like "merge to main", "main에 머지", "main 브랜치에 합쳐줘", "merge this branch into main and delete it", "/git-merge-to-main", or "$git-merge-to-main". Refuses to force-delete or to operate on a dirty working tree. For `dev` use `git-merge-to-dev`; to bulk-clean already-merged branches use `git-branch-cleanup`.
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.