Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when the user asks to write, file, open, draft, refine, or split an implementation-ready Linear or GitHub ticket or issue. Drafts in chat unless asked to write it, and splits into linked subissues when real PR boundaries help. Never runs inside /task.
Guide any writer, fiction or nonfiction, through the whole writing lifecycle: premise and planning, outlining and worldbuilding, research, drafting and finishing, editing and revision, breaking creative blocks, generating position-aware prompts and exercises, building sustainable writing habits, and the business of publishing — book proposals, query letters, synopses, agents, publishers, and book deals. Do not use for formatting deliverables into document files (see word-document, pdf-document, epub), for technical or business documentation (see technical-documentation), or for pure grammar and spelling reference.
Create standalone beginner tutorial packages from a topic or supplied references, with adaptive research, course-style outline design, chapter visuals, and Markdown/DOCX/PDF/HTML exports. Use for textbook-like tutorials, course guides, teaching documents, or long beginner guides; not for quick answers, link summaries, pure diagrams, or file conversion.
Zod v4 reference for a TypeScript-first schema validation library. Schema definitions such as z.object / z.string / z.number / z.array / z.union / z.enum; parse, safeParse, z.infer (type inference), refine, transform, pipe, default, optional, nullable, z.compile (AOT), validate, z.toZod, error handling, Zod 4 migration, and Zod Mini (@zod/mini). createInsertSchema / createSelectSchema (drizzle-zod, schema generation from Drizzle tables) are covered by the separate drizzle skill.
Use when analyzing, selecting, validating, or communicating models for insurance, actuarial, financial-risk, or other consequential uncertain outcomes. Covers regression, generalized linear models, frequency-severity, panel and longitudinal data, survival, time series, credibility, reserving, tail risk, calibration, and model governance. Do not use for generic software forecasting, ordinary SaaS financial models, or credentialed actuarial, investment, legal, or regulatory advice without the relevant specialist review.
Assists legal staff of mainland China administrative agencies in making value judgments and interest balancing based on the basic principles of administrative law from a given administrative case, and in forming a reasoned discretionary conclusion.
Spawn parallel adversarial subagents that DRIVE THE REAL SYSTEM (not reason from source) to break new code before it ships — schemas, contracts, parsers, serializers, protocols, state machines, security/redaction, freeze guards. Use as a standard step on any nontrivial feature/task once the implementation is green and BEFORE the final convergence (dootsabha) review. Each agent gets one disjoint attack surface + a "try to break X" charter; every finding is independently reproduced before it is believed, then fixed with a regression test. Trigger phrases include "adversarial review", "try to break this", "find the bugs I missed", "harden before done", "attack this schema/parser/contract", and the shux feature-protocol adversarial step.
Query Alibaba Cloud DDoS Pro (ddoscoo) block/intercept reasons via SLS full logs and ddoscoo CLI. Analyzes detailed information about intercepted requests including CC protection rules, precise access control rules, region blocking, and IP blacklist policies. Use when users report being blocked by DDoS Pro, encounter block pages, or need to investigate and remediate DDoS protection rules. Trigger words: "DDoS block query", "blocked by DDoS Pro", "DDoS intercept", "ddoscoo intercept query", "CC block", "precise access control block", "高防拦截查询", "request blocked by anti-ddos"
Alibaba Cloud ICP Filing Success Data Query Skill. Use for querying ICP filing success information including entity, website, app details and risk alerts after successful filing. Triggers: "ICP filing query", "beian query", "filing information", "filing risk", "query filing success", "备案查询", "备案信息", "备案风险".
Use when designing custom voices with Alibaba Cloud Model Studio CosyVoice customization models, especially cosyvoice-v3.5-plus or cosyvoice-v3.5-flash, from a voice prompt plus preview text before using the returned voice_id in TTS.
Call Alibaba Cloud SLS from Python (alibabacloud_sls20201230): ListProject (list projects), ListLogStores (list log stores), GetLogsV2 (query logs). Suitable for scenarios such as "list projects", "list LogStores", "query SLS logs", and "search and analyze logs". See reference/*.yml for the API contract; see scripts/ for runnable examples; see scripts/requirements.txt for dependencies.
Diagnoses part lifecycle problems from system.part_log - part creation, merges, mutations, downloads, removals and moves. Use when there are too many parts or micro-batch inserts, merge backlog or slow merges, mutation storms from ALTER UPDATE or DELETE, unusual DownloadPart replication churn, unexpected RemovePart spikes, or Keeper znode growth tied to part activity.
This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a competitive product, tracking sentiment of recent Amazon reviews, extracting verified purchase reviews for quality assessment, summarizing user experiences from Amazon product pages, monitoring product performance through customer reviews, collecting reviewer profiles and links for market research, gathering review titles and descriptions for content analysis, scraping Amazon reviews without requiring a login.
Helps users migrate from Azure Cache for Redis (ACR/OSS) Basic, Standard, and Premium tiers to Azure Managed Redis (AMR). Provides SKU mapping, real-time pricing scripts, cache metrics assessment, automated migration via ARM REST APIs with DNS switching, and IaC template migration (ARM, Bicep, Terraform). Use when users ask about: Redis migration, ACR to AMR, OSS to AMR, automated migration, DNS switch migration, cache retirement deadline, ACR retirement date, SKU selection, AMR vs ACR features, feature compatibility, Redis module support, pricing comparison, cache upgrade, Basic/Standard/Premium tier migration, P1/P2/C3 cache migration, AMR SKU recommendation, migration rollback, migration validation, connection string changes, port changes, cache assessment and metrics, IaC template migration (ARM, Bicep, Terraform), or checking for amr-migration-skill updates. Do NOT use for: Enterprise (ACRE) tier migrations, creating new Redis caches, or general Redis performance tuning.
Build an animation from scratch, making the decisions in the order that determines whether it feels right — should it animate at all, what purpose, which tool, which properties, which curve and duration, how it interrupts, how it exits. Writes the implementation. Use when asked to animate something, add motion, make a component feel alive, or build a transition. For critiquing existing motion use review-animations; for auditing a whole codebase use improve-animations.
Expert in real-time game animation systems including skeletal animation, blend trees, state machines, inverse kinematics, root motion, procedural animation, and animation retargeting. Specializes in creating fluid, responsive character animation that balances visual quality with performance constraints. Use when "animation system, state machine, blend tree, skeletal animation, inverse kinematics, IK system, root motion, animation blending, character animation, animator controller, motion matching, animation retargeting, foot IK, look at IK, aim offset, animation montage, animation notify, additive animation, animation layers, procedural animation, animation, game-dev, character, state-machine, unity, unreal, godot, skeletal, rigging, motion" mentioned.
Deep anonymization sweep for double-blind paper submissions, plus clean de-anonymization for camera-ready. Use when a researcher says "anonymize my paper", "double-blind check", "blind this submission", "remove author names", "did I leak my identity" — or, after acceptance, "de-anonymize" / "restore authors for camera-ready". Sweeps the whole leak surface, \author/\affiliation/\email/\orcid/\thanks, acknowledgments and grant numbers, hyperref pdfauthor and compiled-PDF metadata, first-person self-citations (rewritten to third person), GitHub/dataset/homepage links vs anonymized mirrors, LaTeX comments, .bib annotations, home-directory paths, and supplementary material (.git dirs, notebooks, LICENSE/AUTHORS files). Bundles a stdlib-only scanner (scan_anonymization.py, check ids shared with preflight-check) and a reversible-edit workflow (toggle + manifest) so every change is cleanly undone at camera-ready. Advisory only; never submits anything.
Use this skill to review, tighten, draft, and rewrite prose so it does not read like generic LLM output, AI writing, bland marketing, or generic launch copy. Apply it when the user asks to make writing less generic/AI-sounding, tighten a talk intro, sharpen presentation/slide copy, or improve articles, wiki pages, README text, emails, posts, scripts, product/DevRel copy, launch copy, and other important writing with AI tropes, inflated significance language, generic cadence, weak flow, or marketing fog.
Apple app services. StoreKit 2 / CloudKit / WidgetKit / ActivityKit / User Notifications / Core Location / MapKit / HealthKit / Sign in with Apple. Product, Transaction, RequestReviewAction, CKRecord, CKUserIdentity, Widget, TimelineProvider, UNUserNotificationCenter, CLLocationManager, CLServiceSession, Map, MKGeocodingRequest, HKHealthStore, ASAuthorizationController, AuthorizationController.
GitHub Actions workflow templates for uploading builds and releasing to the App Store using the `asc` CLI. Use this skill when: (1) Setting up a CI/CD pipeline that uploads a signed IPA/PKG to App Store Connect (2) Automating App Store submission from GitHub Actions using `asc` (3) Adding TestFlight distribution steps (add beta group, update "What's New") (4) User asks "how do I release to the App Store from CI", "create a GitHub Actions workflow for App Store submission" (5) Wiring `asc builds upload`, `asc versions set-build`, `asc versions submit` into a pipeline (6) Adding a pre-submission readiness gate using `asc versions check-readiness`
Use when building ANY tvOS app - covers Focus Engine, Siri Remote input, storage constraints (no Document directory), no WebView, TVUIKit, TextField workarounds, AVPlayer tuning, Menu button state machines, and tvOS-specific gotchas that catch iOS developers
Use bdg CLI to drive and debug a real Chrome via Chrome DevTools Protocol - navigate, click, fill and submit forms, check what an action changed (navigation, new messages, pending requests), inspect elements without screenshots (box, layout, fonts, colors, a11y), read network requests and console errors, run JavaScript, and call any CDP method. Use this skill when you need to verify a UI change in a running app, debug a page, automate a browser flow, or scrape dynamic content.
Use when choosing Bevy 0.20's built-in renderer versus an API-only, headless, or external renderer; selecting forward or deferred PBR; writing render systems in `Core3d`/`Core3dSystems`; porting naga_oil shaders to WESL; opting into `ScreenSpaceTransmission` or `Tonemapping::Linear`; configuring 2D/3D render Cargo features; or deciding how physics crates such as `bevy_rapier3d` relate to rendering.
Point at something on the human's macOS screen with a big arrow and a sign ("Franz, click HERE"), and hand over values, secrets and questions on a floating cue card, using the bigarrow CLI. Use whenever the human has to look at, click, type into or choose a specific spot, button, field, window, tab or menu: show me where, point to it, which button, where do I click, zeig mir wo, guide me through this UI, the human must approve or sign something, or you need the human's hand and they may not be looking at the terminal; also to hand over credentials, a password, token, 2FA code, IBAN or command to paste, or to ask the human a question or a choice while they are away from the terminal. Mandatory when it is time-critical: a code that expires, a login or payment page that times out, a build waiting on the human.
Choose, configure, and use Blender MCP integrations for live scene control or deterministic asset evaluation. Use when connecting Codex or Claude Code to an open Blender instance, deciding between Blender Lab MCP and community Blender MCP servers, troubleshooting Blender MCP connectivity, or evaluating whether MCP tools improve a Blender modeling workflow.
Schedule, create, and manage social media posts via the Buffer GraphQL API. Use this skill when the user wants to post to social media through Buffer, schedule posts, create ideas, list channels, retrieve posts, or manage their Buffer queue. Triggers on: Buffer, schedule a post, publish to social media, Buffer API, social media queue, Buffer channels, create Buffer post, Buffer idea, or any mention of posting to LinkedIn/Twitter/Instagram/Facebook/Bluesky/Threads/Pinterest/Mastodon/YouTube/TikTok via Buffer.
Bun JavaScript runtime, bundler, and package manager. Covers Bun.serve() HTTP server, Bun.file() I/O, SQLite, password hashing, Bun.build() bundler, bun:test runner, and package management. Use when building with Bun APIs, running scripts with Bun, bundling code, managing packages with bun install/add, or writing tests with bun:test.
Manage Calendly scheduling via the v2 API. List event types, view scheduled events, check invitee details, manage availability schedules, cancel/reschedule events, create one-off links, and configure webhooks. Use when the user asks about their calendar, upcoming meetings, scheduling links, or availability.
Use when the user needs HTML Canvas, SVG graphics, data visualization, generative art, or interactive visual elements with D3.js or similar libraries. Triggers: user says "canvas", "SVG", "chart", "data visualization", "D3", "generative art", "animation", "interactive graphics", drawing on screen.
Migrates a Capacitor app from Capawesome Cloud live updates (@capawesome/capacitor-live-update, LiveUpdate.ready/sync/setNextBundle/reload, plugins.LiveUpdate config with appId, autoUpdateStrategy, defaultChannel, readyTimeout, publicKey, and @capawesome/cli bundle upload commands) to Capgo Updater (@capgo/capacitor-updater). Covers the package swap, config and API mapping, the notifyAppReady startup hook, deleting custom update glue, replacing CI upload commands, overlap with devices still on old binaries, verification, and Capgo positioning (native updater runtime, open source, cheaper at comparable scale, longer track record). Do not use for Ionic Appflow (ionic-appflow-migration), a fresh Capgo setup (capgo-live-updates), channel and rollout strategy after migration (capgo-release-workflows), or Capawesome plugins unrelated to live updates.
Always invoke before answering any request to create, compare, design, or review a user-facing map, even if the request is terse or underspecified. Covers publication maps, choropleths, map series and small multiples, comparable multi-date panels, proportional/bivariate/flow maps, raster rendering, and interactive web maps. Includes classification, color, legends, projections, accessibility, and large-data aggregation. Do not trigger for a temporary diagnostic plot inside another analysis.
Query or write generic CawPlan business metrics (subscriptions, CawPlan tickets, QA, workflow executions, tokens/credit, API usage, ...) via the metrics store, optionally charting the result. Use when the user asks to query, chart, or plot a business metric like subscription upgrades, ticket creation/status-change counts, QA test point/report counts, workflow success/failure rates, token consumption, or API usage over time; or asks to record/write/log a business metric event. NOT for: Support Ops sheet exports/backfills/reconciliation (use `cawplan-support-metrics`), a combined product health overview mixing metrics + feedback + critical issues (use `cawplan-product-insights`), device/app install metrics (that public endpoint has been retired), AI feedback categorization (`cawplan analytics get`), ticket creation, or critical issue lists.
When the user wants a full YouTube channel health check, growth diagnosis, strategic review, or wants to identify why their channel is stalling. Also use when the user says 'audit my channel,' 'channel review,' 'why is my channel not growing,' 'channel health check,' 'what's wrong with my channel,' 'growth blockers,' 'YouTube audit,' 'channel diagnosis,' 'strategic review.' For single video analysis, see video-analysis. For strategic repositioning, see channel-strategy.
Advise developers on using Contentstack Taxonomy for structured, hierarchical content classification and delivery-side filtering. Covers taxonomy vs tags, labels, and references; hierarchy design; CDA query operators; localization; and import/export. Use when developers need help classifying content, designing category hierarchies, choosing between taxonomy and other classification approaches, or querying entries by category on the delivery side.
Toolset for managing Alibaba Cloud Yunxiao Codeup code repositories. Use cases include: (1) repository operations — branch management, file operations, code diffs, merge request/MR management (2) organization management — department management, member lookup, role management (3) operating codeup repositories, branches, MRs, merge requests (4) querying Yunxiao organization members and department lists
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.