Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Cross-platform operating system automation and screen control toolkit. Use when users need screenshots, mouse/keyboard control, visual recognition, window management, browser automation, or desktop automation tasks. Supports macOS 12+ and Windows 10+. On macOS, uses AppleScript, pyautogui, and OpenCV. On Windows, uses pywinauto, pyautogui, and OpenCV (no Hammerspoon equivalent).
Triage and fix one microsoft/playwright-cli issue, or do a maintainer's task, unattended inside the Issue triage GitHub Actions workflow (.github/workflows/triage.yml), which a needs-triage, needs-triage-mac or needs-triage-win label starts, or a maintainer starts by hand with an issue, a task or both. Reproduces the issue on the runner, then leaves a verified fix proposal for the workflow to open as a draft PR, in this repo or in microsoft/playwright where the source of the CLI is, or an investigation note for it to post on the issue. Only for that workflow.
Translate ideas, feature requests, or vague concepts into specific, actionable dev briefs. Use this skill whenever the user has an idea they want to build, a feature to spec out, a bug to file, a project to scope, or needs to convert a half-formed idea into a clear implementation brief. Triggers on I want to add, we should build, can we make, what is the plan for, how do we implement, dev brief, feature spec, PRD, user story, acceptance criteria, scope this, prioritize. Also triggers when the user has a list of things they want to build and needs help converting them into well-formed tasks.
Write a promotional tweet for a published article. Takes a post URL (Substack, X Article, blog) and crafts a teaser tweet that opens the story and draws readers in — not a summary, but a hook that leads naturally into clicking the link. Use when user says "promote this post", "write a tweet for this article", "推广这篇文章", or provides a link and asks to write a promo tweet.
Master orchestrator for a full SEO audit suite powered by the Ahrefs MCP. Use this skill when running a comprehensive SEO audit, scoping a quarterly health check, doing pre-acquisition SEO due diligence, or post-migration verification. Triggers on full SEO audit, comprehensive SEO review, SEO health check, audit my site, SEO due diligence, audit suite, comprehensive audit, end-to-end SEO. Also triggers when a stakeholder wants the complete picture rather than a single-dimension audit
Maintain the existing May Shorts teaching compositions using their legacy face-mode, scene-overlay, and karaoke-caption patterns. Use only when working on those examples or explicitly requesting this legacy scaffold. For new reels, Shorts, or short advertisements, use short-form-edit.
Expert SurrealDB developer specializing in multi-model database design, graph relations, document storage, SurrealQL queries, row-level security, and real-time subscriptions. Use when building SurrealDB applications, designing graph schemas, implementing secure data access patterns, or optimizing query performance.
Guide for implementing Syncfusion Angular ListView components. Use this skill when building interactive lists with data binding, grouping, templates, selection, events, drag-and-drop, or virtualization features. This skill covers getting started, data binding, customization, selection, advanced features, specialized use cases, styling, and accessibility for building production-ready list interfaces.
TCGA/GDC cancer genomics analysis — cohort construction, clinical metadata retrieval, somatic mutation frequencies, survival analysis, and multi-omics integration. Use for TCGA-BRCA-style cohort studies, mutation prevalence by cancer type, survival-by-mutation analysis, and pan-cancer driver discovery. Always cancer-type-specific (don't use pan-cancer counts without cohort context)
Aggregates the top 10 trending topics across the web using hourly data from seven major platforms, including Douyin, Weibo, Bilibili, Kuaishou, Zhihu, Toutiao, and Baidu. Supports browsing trends from the past seven days. Does not support queries for specific topics.
Build production UI that reads as a deliberate choice for this project rather than an LLM default, audit shipped UI for the tells that give it away, or mock up a screen as an image before the build. Use when the user says "build this page", "make this UI not look AI-generated", "audit our UI", "make the frontend look good", "mock up this screen", "show me a few options for this screen", or "/uikit". Reads a project's DESIGN.md when one exists.
Automatically generates weekly KPI reports from multiple data sources, including Supabase analytics, CRM data, financial spreadsheets, and email metrics. Produces executive-ready reports with dashboards, trends, highlights, concerns, and action items.
Detect antibot vendors on one or more URLs without opening a browser session. Use when the user asks what antibot, bot protection, WAF, captcha, or challenge provider a site uses, or asks to check sites for Cloudflare, Akamai, DataDome, PerimeterX, Imperva/Incapsula, Kasada, reCAPTCHA, hCaptcha, Anubis, or Shape Security markers.
Create or extend a nao project's RULES.md. Owns the RULES.md template. Use when the user wants to generate the initial RULES.md from synced metadata (called by setup-context) or improve an existing RULES.md. Do not use for first-time scope setup (use setup-context) or diagnosing existing problems (use audit-context).
Xiaohongshu MCP Skill - Full automation solution with login fix. Features: (1) Login management, (2) Search, publish, interact, (3) Complete MCP protocol support (13 tools), (4) Comment strategy. Built-in Feishu notification, iflow integration. Triggers: xiaohongshu, rednote, 小红书 automation.
Use when you need Kafka messaging in Quarkus with SmallRye Reactive Messaging — including channel/topic design, build-time Jackson serialization, typed @Channel/@Incoming, ack/failure strategies, retries/DLQ, idempotency, Dev Services, and Testcontainers integration tests. This should trigger for requests such as Add Kafka in Quarkus; Review Reactive Messaging consumers; Improve failure handling for Quarkus Kafka; Configure Quarkus Reactive Messaging Kafka channels; Add Quarkus Kafka failure strategy or DLQ handling. Part of Plinth Toolkit
Use when you need MongoDB persistence in Quarkus — including Panache Mongo entities/repositories, document design, indexes, transactions where applicable, and error handling. This should trigger for requests such as Add MongoDB in Quarkus; Review Quarkus Mongo Panache design; Improve Mongo error handling in Quarkus services; Model MongoDB documents for a Quarkus service; Configure Quarkus MongoDB clients codecs or transactions. Part of Plinth Toolkit
Self-improvement system for agents. Invoke when the user runs /agent-brain followed by: improve (learn from this session), learn <something> (teach the agent something new), interview (proactively interview you to fill knowledge gaps), absorb <path> (adopt capabilities from another agent, skill, or full brain), dream (reflect on the full brain and surface growth opportunities), or validate (audit brain for structural issues)
Query and analyze Alibaba Cloud public network exposure, identify unnecessary exposed assets and ports, assess exposure risks, and generate remediation recommendations. Triggers when user mentions public network exposure, exposed assets, exposed ports, public IP security, port scan results, attack surface analysis, internet reachability, high-risk port detection. Also triggers when user asks about "which IPs/ports are exposed to the internet", "public asset inventory", "security baseline check", even without explicitly saying "exposure".
Retrieve analyst financial estimates including Revenue and EPS projections with low/high ranges and analyst coverage. Use when analyzing forward expectations, consensus estimates, valuation inputs, or comparing projections to historical performance.
Expert knowledge for Azure Cosmos DB development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using Cosmos DB SQL/Mongo/Cassandra APIs, change feed, multi-region HA, vector search, or Cosmos DB for PostgreSQL, and other Azure Cosmos DB related development tasks. Not for Azure DocumentDB (use azure-documentdb), Azure Table Storage (use azure-table-storage), Azure SQL Database (use azure-sql-database), Azure Blob Storage (use azure-blob-storage).
Use when user asks to search the web, look something up online, find current/recent/latest information, or needs cited answers. Triggers on "search", "look up", "find out about", "what is the current/latest", image searches, news lookups. NOT for searching code/files—only for web/internet searches.
First-time onboarding and scaffolding creator for cheat-on-content. A unified process: all users follow the same 5-stage cycle. The only difference is that users who have posted videos get one extra step during init: fetch existing videos to build historical context (so later cheat-seed can provide more relevant topics and a more accurate baseline). Triggers: “initialize” / “init” / “first time using” / “I’m a new user” / “setup cheat-on-content”. Must run in the user’s first session; other sub-skills automatically route here when .cheat-state.json does not exist.
Route explicit ClawTeam runtime requests into one honest operator packet before touching commands: manual-team, template-launch, monitor-recover, or profile-setup. Use when the user specifically wants ClawTeam's team/task/inbox/worktree/board workflow for parallel developer work, product/ops research, content operations, or game-production coordination. Not for generic multi-agent routing, board-only governance, or lightweight subtask fan-out when jeo, harness, task-planning, or built-in delegation already fit
Content distribution as a discipline. Owned channels (newsletter, blog, social), earned channels (PR, syndication, mentions), paid channels (boosted posts, syndication networks), and the channel-fit decisions that distinguish strategic distribution from spam-everywhere. Audience-channel matching, content-channel matching, distribution cadence. Triggers on content distribution, channel strategy for content, owned earned paid channels, content amplification, content promotion, audience-channel matching, content-channel matching, distribution cadence, syndication strategy, organic distribution. Also triggers when content is publishing but reach is low, when the team is distributing on every channel without strategy, or when the content program needs a distribution discipline rather than just publication.
Create comprehensive technical specs for SDK gaps, feature modules, or system centralization efforts. Use when writing specs, PRDs, gap analysis documents, or planning centralization of scattered functionality into a single module. Triggers on "create spec", "write spec", "gap spec", "centralize", "fill the gap".
Criticism and self-criticism: honestly, specifically, and factually review the work and process after completion, at a review checkpoint, when receiving criticism, or when the same mistake recurs; produce actionable improvements and address external criticism without defensiveness. Trigger signals include review, retrospective, audit, "帮我看看有没有问题", "你确定吗", "check this for problems", and "are you sure". Do not trigger at the start of a task or for a one-step lookup.
Detects prompt injection using regex signature matching, heuristic scoring for structural anomalies, and DeBERTa-based transformer classification. Flags direct injections (system-prompt overrides, role-play escapes) and indirect injections (encoded payloads, obfuscation) per OWASP LLM Top 10 (LLM01:2025). Use for input validation layers in chatbot/agent/RAG pipelines, or for retrospectively classifying injection attempts in logs or incident investigations.
Expert guide to Electron production builds, code signing, notarization, auto-updates, and release workflows. Use when building, packaging, or releasing Electron applications, configuring electron-builder, setting up CI/CD pipelines for desktop app distribution, or implementing auto-update mechanisms.
X++ code development lifecycle for Finance and Operations — scaffold models, author classes, custom services/APIs, and data entities, install matching SDKs, compile deployable packages, deploy packages, synchronize databases, and verify deployed artifacts. Use when the user explicitly requests creating, building, compiling, packaging, deploying, DB-syncing, or verifying X++ customizations, or an end-to-end ERP code change.
Use this skill when building agent evaluation systems: deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring, baseline comparison, and outcome measurement for agent pipelines
Architect a full-stack application on Eve Horizon — manifest-driven services, managed databases, build pipelines, deployment strategies, secrets, and observability. Use when designing a new app, planning a migration, or evaluating your architecture.
Search for and retrieve existing content and media (articles, blogs, news, FAQs, events, products, images, logos, icons, photos, graphics, banners, hero images, audio clips, videos, documents) from Salesforce CMS or other connected sources. Use this skill ANY TIME a user says "find", "search", "get", "fetch", "retrieve", "look up", "locate", "show me", "list", or "I need" followed by content or media words like "blog", "article", "news", "FAQ", "event", "product page", "image", "logo", "icon", "photo", "banner", "audio", "video", "document". Also use for requests that mix both, like "reuse existing assets" for a page. Routes each intent to the correct sub-workflow — structured content search or media search — and can run both in the same request. Does not apply when the request is to generate NEW content or images from scratch, define content type schemas, or apply brand guidelines.
A discipline for designing experiments (A/B tests, multivariate, holdouts) so the results actually answer the question you asked. Hypothesis writing, sample size, duration, segment analysis, running discipline, matching a result to a pre-committed decision rule, and the common failure modes that produce confidently wrong shipping decisions. Use this skill whenever the user is planning a test that has not run yet: framing a hypothesis, sizing the sample, setting duration, choosing guardrails, or deciding whether something is worth testing at all. Triggers on design an experiment, experiment plan, A/B test, split test, multivariate test, holdout, experiment hypothesis, sample size, minimum detectable effect, MDE, test duration, guardrail metric, no peeking, pre-committed decision rule, is this worth testing. Use `experimentation-analytics` instead when the test has already run and the question is how to read the result panel.
Guides exploration of $autocapture events captured by posthog-js to understand user interactions, find CSS selectors (especially data-attr attributes), evaluate selector uniqueness, query matching clicks ad-hoc, and create actions. Use when the user asks about autocapture data, wants to find what users are clicking, needs to build actions from click events, asks about elements_chain, wants to build a trend or funnel filtered by clicks or other autocapture interactions, asks which properties autocapture sends, or asks how to filter $autocapture events. Only applies to projects using posthog-js autocapture.
Original prompt for fact-checking. Use when the user wants to verify whether a claim, opinion, conclusion, data point, or plan holds up. Trigger phrases include fact-check, check this for me, is this true, verify this, is there a hallucination, is this data reliable, review this opinion, and fact check. Requires online verification; provide a five-level confidence rating and identify flaws in the reasoning chain.
Eight-layer pre-match football analysis. Takes a natural-language query, finds the match on FlashScore MCP, runs build_match_context.py to get normalized context in JSON, and produces a structured report using probabilistic language. Only for notstarted matches. Does not invent data or replace predictions with heuristic models.
Generate a CDS analytical model (star schema — cube + dimension + text views) on top of a RAP business object or a DDIC table. Use when asked to "create a star schema", "generate an analytical cube and dimensions", "make a RAP BO analytical", "build a CDS cube from a table", or "create an analytical model".
Think like Intel's legendary CEO. Apply Andy Grove's management operating system to maximize your team's output through leverage, OKRs, and systematic decision-making. Use when: **Scaling a team** when individual contribution isn't enough; **Performance management** to measure and improve output; **Meeting optimization** to make meetings productive; **Decision-making** in management contexts; **New manager transition** from individual contributor
Meta XR Core SDK (com.meta.xr.sdk.core) for Unity XR development. Use when setting up VR/MR projects, configuring OVRManager, adding OVRCameraRig, enabling passthrough, hand tracking, spatial anchors, boundaryless mode, controller input, Scene API, or any Meta VR feature. Covers OVRProjectSetup, AndroidManifest generation, and project configuration for Meta VR devices, driven against a live Editor with unity-cli.
Legacy interoperability skill for Storyboard and Interface Builder maintenance in iOS 26 / Swift 6.2 clinic codebases. Use only for migration or maintenance of existing storyboard screens; not for new SwiftUI clinic feature development. Triggers on Auto Layout, segues, size classes, IB accessibility, storyboard merge conflicts, and storyboard-to-SwiftUI migration tasks.
Mass line: Collect scattered input from everyone who holds ground truth (users, operators, codebase, logs, runtime results), synthesize it into a coherent plan, take it back for alignment and validation, and iterate. Trigger when inputs conflict, feedback must be consolidated, a plan needs sign-off from real users, or you sense you are designing in isolation; skip when there is a single complete source and the work is pure execution.
Extract formal spec and comprehensive test suites from existing MoonBit implementations. Use when asked to "extract spec from implementation", "generate tests from code", or "create spec-driven tests for existing package". Analyzes existing code to produce spec.mbt with `declare` keyword stubs and organized test files (valid/invalid).
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.