Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Convert prompts written for custom-coded web stacks such as React, Tailwind, Next.js, Vite, or plain HTML/CSS/JS into copy-paste-ready prompts for a Framer agent. Invoke this skill whenever the user says "convert prompt" (with or without a hyphen) or asks to rewrite, adapt, translate, or convert a code-oriented website, page, section, component, animation, or interaction prompt into native Framer platform instructions while preserving the original design intent, copy, layout, typography, color, motion, interactions, responsive behavior, and constraints.
Convex backend guidance for queries, mutations, actions, schema, validators, auth, components, agents, search, testing, production config, and client/server integration. Use whenever interacting with a Convex backend, including Convex functions, schema changes, HTTP endpoints, scheduling, storage, AI features, or framework integration.
Write or audit UI copy (buttons, labels, empty states, error messages, tooltips, form text) anywhere in the monorepo. Load it before shipping or reviewing any user-facing text — including when copy is incidental to the task, like a new feature that adds buttons, toasts, dialogs, or validation messages.
Automates creating new documents in the Feishu workspace. This skill should be used when the user asks to "create a Feishu doc", "create a new doc in Feishu", "open Feishu and create document", "create document in leiniao-ibg", or mentions creating documents in Feishu or Lark workspace.
Use this skill when authoring or extending an Unreal Engine toolset, a class of static, AI-callable functions registered with `ToolsetRegistry` and exposed through the unreal-mcp server. Trigger when the user wants to add, expose, or register a new tool method, create a new toolset, or extend an existing one such as `BlueprintTools`, `StaticMeshTools`, `ObjectTools`, `LevelTools`, or `MaterialTools`. Concrete triggers: 'add a tool to X', 'expose this via MCP', 'register a function so Claude/the agent can call it', 'wire this into the toolset registry', 'create a new toolset for Y', 'add a Python toolset', 'make this AI-callable'; adding a `static` method to a `*Tools.cpp/.h/.py` file; editing files under a `Toolsets/` folder; designing tool parameters, return types, or struct schemas for a toolset. SKIP for: invoking existing tools at runtime (use unreal-mcp instead), authoring an Agent Skill (use unreal-skill), generic refactors that happen to touch a toolset file but don't add or redesign a tool, or unrelated uses of the word 'toolset'.
Use when creating new opencode skills, modifying existing skills, or measuring skill performance. Triggers include requests to create a skill from scratch, edit or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Main entry point for docs. Triggers: writing/updating developer guides, user guides, API references; does not include docs-neat final cleanup. Do not use for new feature implementation (cs-feat), bug fixing / error diagnosis (cs-issue), breaking down large requirements (cs-epic), domain modeling, or ADR decision records (cs-domain).
Reviews DAST tool configurations against OWASP Top 10:2021 and OWASP Testing Guide v4.2. Auto-invoked when reviewing OWASP ZAP configurations, DAST CI/CD integration, scan policies, or authenticated scanning setups. Produces a DAST maturity assessment covering scan policy configuration, active vs passive scanning, API scanning, authentication handling, and results deduplication.
DAX (Data Analysis Expressions) mastery for Power BI semantic models. PROACTIVELY activate for: (1) writing DAX measures or calculated columns, (2) CALCULATE, FILTER, ALL, REMOVEFILTERS context-modification functions, (3) understanding filter context vs row context vs context transition, (4) time intelligence (SAMEPERIODLASTYEAR, DATEADD, YTD/MTD, TOTALYTD, DATESBETWEEN), (5) iterators (SUMX, AVERAGEX, FILTER), (6) variables (VAR/RETURN) and DAX optimization, (7) calculation groups, field parameters, and visual calculations, (8) WINDOW/INDEX/OFFSET/ORDERBY/PARTITIONBY/MATCHBY (window functions), (9) DAX user-defined functions (UDF), (10) DAX patterns for ratios, running totals, ranking. Provides: measure templates, time-intelligence patterns, optimization techniques (variables, FILTER vs CALCULATETABLE), context-transition explainers, and reference for window functions and calculation groups.
TanStack DB core concepts: createCollection with queryCollectionOptions, electricCollectionOptions, powerSyncCollectionOptions, rxdbCollectionOptions, trailBaseCollectionOptions, localOnlyCollectionOptions. Live queries via query builder (from, where, join, select, groupBy, orderBy, limit). Optimistic mutations with draft proxy (collection.insert, collection.update, collection.delete). createOptimisticAction, createTransaction, createPacedMutations. Entry point for all TanStack DB skills.
Instrument browser-based web applications with Datadog Browser RUM. Detect the application framework, router, package manager, bundler, entrypoint, credentials, and existing RUM setup; add or safely complete classic Browser RUM instrumentation for React, Next.js App or Pages Router, Angular, Vue, Nuxt, Svelte, vanilla JavaScript, SPAs, and iframe-hosted apps; avoid duplicate initialization; and verify the application still builds. Use when asked to add, set up, instrument, repair, or verify Datadog RUM, Browser Monitoring, Session Replay, or framework-specific Browser RUM plugins.
Define, review, or update SECURITY.md guidance for a repository or component. Use when the user wants to clarify what Codex Security should review, what is out of scope, which security properties must hold, or whether existing guidance still matches the code.
Downloads, installs, and relocates new agent skills to the global Antigravity shared directory (`~/.gemini/config/skills/`) to make them available across all tools. Use when the user requests to download, install, import, setup, or update new agent skills, or asks to relocate installed skills.
Use for every user-visible change in a GNOME app, new or existing, whether or not the request uses design vocabulary. Trigger on the repo rather than the wording — if it depends on gtk4/libadwaita (or is a GNOME-targeted Qt/PySide6 app), anything a user can see or interact with goes through this skill, including requests phrased purely as symptoms ("can I right-click to delete", "the window opens too small", "reordering doesn't work"). Covers choosing widgets, icons, dialogs, menus, sidebars, navigation, and empty states; interaction bugs in context menus, drag-and-drop reordering, window sizing, layout, duplicate affordances, and controls missing or inert at launch; and HIG review. Complements developing-gtk-apps, which owns architecture, threading, language syntax, and build/test plumbing.
Prove and counter-prove a statement using parallel agents to eliminate confirmation bias. Use when someone says “dialectic,” “prove/disprove,” “stress test this claim,” “is this really true,” “argue both sides,” or when a statement needs objective analysis from opposing viewpoints.
Integrate Didit Transaction Monitoring (KYT), crypto wallet screening, and the FATF / EU TFR Travel Rule. Use when the user wants to monitor transactions in real time, score transactions against AML/fraud rules, create, backtest, or install monitoring rules via API, list or read monitored transactions, screen crypto wallets or transaction hashes against blockchain analytics, generate a wallet-screening PDF, comply with the crypto Travel Rule (originator/beneficiary exchange with counterparty VASPs), verify self-hosted wallet ownership, register after-deposit (sunrise) transfers, mint SDK transaction tokens for client-side submission, or step up risky transactions with biometric re-verification using Didit. $0.02 per transaction.
Yamane Super Director Master — a directing and audiovisual skill designed by @山音, linked with "Yamane Super Screenwriter Master". Starting from the script, it completes director tone-setting, pacing planning, script fine-tuning, and storyboard breakdown, finally generating a standard nine-column storyboard table (xlsx). It analyzes the audiovisual theories of the world's top directors, includes a director-style template library for dozens of film genres, and supports cross-genre combinations. It covers storyboards in all formats, from concept super-short films to features. Be sure to use this skill when the user mentions storyboard, storyboard table, director, shot language, camera movement, composition, shot size, editing rhythm, audiovisual style, camera angle, director style, shooting plan, storyboard breakdown, storyboard, or any request involving turning a script into an executable shooting plan. Trigger it even if the user only says "help me break down the storyboard", "how should this scene be shot", or "give me a director's plan". Also trigger it when the user already has a script generated by the Screenwriter Master and wants to move into the directing stage.
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
When writing or reviewing code to eliminate duplicated knowledge and business logic. Use when the user says "this is duplicated," "we have this in two places," "single source of truth," "DRY this up," or "shotgun surgery." For premature abstraction concerns, see yagni.
Build event-driven pipelines that connect a zero-LLM mechanical layer to a duoduo brain job via session notify. Use when the user wants to monitor an external data source (feeds, prices, files, webhooks) and only wake an agent when something worth acting on actually arrives — keeping LLM costs at zero during idle periods. Also trigger for: 机械采集, 事件驱动, 按需唤醒, 数据监控, keepalive job, 外部触发, 只在有料时干活, 省 token.
Author agentic verification plans for Eve-compatible apps. Use when building structured test suites that verify app correctness AND Eve platform conformance — CLI parity, manifest conventions, SSO auth, managed migrations, fixture-driven ingestion, and agent efficiency.
FastAPI Python framework. Covers REST APIs, validation, dependencies, security. Use when building Python web APIs with FastAPI, configuring Pydantic models, implementing dependency injection, or setting up OAuth2/JWT authentication. Keywords: FastAPI, Pydantic, async, OAuth2, JWT, REST API.
Figma mastery and design-to-code: Auto Layout, component architecture, variable modes, Dev Mode handoff, Figma MCP server integration, Code Connect, and token pipelines. Use when working in Figma, converting designs to code, or setting up a design-to-code flywheel.
Unusual Capital Flows (资金异动): detects unusual capital-flow signals for a user-mentioned stock with `get_financial_unusual`, including 资金分布、买卖经纪商、资金流向、卖空数量、卖空比例 and their unusual changes. Use when the user asks about 资金动向、资金异动、净流入、净流出、主力行为、大单小单、谁在买谁在卖、买卖经纪商、卖空异动、卖空/做空/沽空、主力是否在进场或离场，or gives a broad 异动 request such as “英伟达异动”、“NVDA 异动”、“腾讯有没有异动/异常” without narrowing the dimension. For broad 异动 requests, use together with `futu-unusual-technical-signal-alerts` and `futu-unusual-derivatives-activity`. Before calling the CLI, first normalize the user-mentioned stock name, Chinese company name, English company name, or ticker into a standard symbol such as `US.TSLA` or `HK.00700`.
Publish any Freshworks Platform 3.0 custom app via MCP tools: fdk validate/pack, app-upload, and submit/update through openai-server. Pre-publish: confirm Developer JWT matches manifest product modules (Freshdesk support_* vs Freshservice service_*; multiproduct sequential). At publish time, ask new vs existing listing; for new listings, prompt for supportEmail before create_app_upload_url (required for submit_custom_app). list_custom_apps for updates so the developer selects appId, then MCP handover (submit_custom_app or add_app_version with uploadId). Use when the user wants to push an app to the Marketplace (test), check publish status, or list existing apps. Pair with fw-app-dev for manifest or module fixes. Works with Cursor, Claude Code, and any MCP-compliant client.
Invoke when the user wants feedback on a game design document, GDD review, design evaluation, or consistency check on an existing design. Triggers on: "review my GDD", "design feedback", "evaluate design", "design document review", "GDD critique". Do NOT invoke for brainstorming new ideas (use game-brainstorm) or balance tuning (use game-balance-check). Part of the AlterLab GameForge collection.
Reduce the size of compiled Go binaries and container images: linker flags, inlining budget, CGO and build tags, embedded assets, dependency weight, and measuring what actually costs bytes. Use when a binary or image is too large, when shrinking a CLI for distribution, or when auditing what a dependency adds to the build. Trigger examples: "binary is too big", "shrink the binary", "reduce image size", "strip symbols", "what is making my binary large", "ldflags -s -w". Not for: runtime speed and allocations (go-performance-review), CI setup (go-ci), release pipelines and signing (go-build-release), dependency CVEs (go-dependency-audit)
Scrape competitor ads from Google's Ads Transparency Center (Search, YouTube, Display, Gmail). Search by company name, domain, or advertiser ID. Returns ad creatives, formats, targeting regions, and campaign details. Use for competitive ad research and messaging analysis.
Convert operational incident and near-miss evidence into durable product, engineering, test, evaluation, and governance improvements with verified closure. Separate observed facts from causal hypotheses and unresolved uncertainty; map follow-up work across code, tests, skills, operations, product, and governance; track ownership, verification, and closure for every finding. Do not use to assign blame or produce a generic postmortem template; do not close learning because tickets were created — require evidence the intended change occurred.
Trigger this skill when general legal rules, adjudication rules, or legal principles need to be distilled and summarized from one or more specific cases, judgments, or fact patterns. Typical triggers include: the user asks to induce adjudication gist from a series of cases, distill a generalizable legal proposition from a single case, identify common legal rules across multiple fact patterns, build a summary of adjudication rules for similar-case retrieval, or summarize judicial application standards from practical precedents.
Plans a version-by-version Infrahub upgrade path and scores each release's breaking changes against the user's repository and instance, producing UPGRADE_PLAN.md. TRIGGER when: planning an Infrahub upgrade, asking what breaks between two versions, checking upgrade impact before a maintenance window, asked to "just run the upgrade", updating or extending an existing UPGRADE_PLAN.md after the target release or the repository moved, debugging a plan that missed a breaking change. DO NOT TRIGGER when: auditing a repo against best practices, querying live data, designing schemas, collecting diagnostics after a failed upgrade, switching between the Community and Enterprise editions. ALWAYS pass the user's request verbatim as args, versions, pasted schema, deployment, and edition included: this skill runs in a forked context and cannot see the parent conversation.
Interview prep. Use when the user uploads a résumé (PDF/image) and gives a vague target role direction (for example "AI application development" or "marketing internship"). Casts a wide net to find real interview experiences (main sources: Nowcoder + Xiaohongshu; supplementary sources: GitHub + general article pages), keeps only content from the past two years, deduplicates and sorts by frequency plus recency, and generates a personalized prep pack with project follow-up questions based on the user's résumé.
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.