Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Run upstream brand discovery covering audience research, competitive landscape, category dynamics, problem space, and positioning territory exploration. Use this skill at the very start of a brand or website project when the user needs to understand who they're for, who they compete with, what the audience actually needs, and where the brand could plausibly stand. Triggers on brand discovery, audience research, market research, competitive scan, category research, customer research, who is this for, who are we, positioning research, intake, kickoff. Also triggers when a creative brief is requested but the upstream inputs (audience, competitors, problem space) are not yet clear.
Add bot protection with Turnstile (CAPTCHA alternative). Use when protecting forms, securing login/signup, preventing spam, migrating from reCAPTCHA, integrating with React/Next.js/Hono, implementing E2E tests, or debugging CSP errors, token validation failures, Chrome/Edge first-load issues, multiple widget rendering bugs, timeout-or-duplicate errors, or error codes 100*/106010/300*/600*
Route Unity and Unreal frame-time complaints into one bottleneck-first profiling brief. Use when the main job is interpreting profiler screenshots, `stat unit` / `stat gpu` output, benchmark-route complaints, or Steam Deck / target-device review packets; choosing the smallest useful next capture; naming one primary bottleneck family; and deciding whether to stay with quick packets, move to an engine-native profiler, or escalate further. Route generic app/service tuning to `performance-optimization`, build/editor/package failures to `game-build-log-triage`, broader game-production coordination to `bmad-gds`, and mixed demo/community feedback to `game-demo-feedback-triage`.
Route Firebase AI feature work into either direct app/client Firebase AI Logic SDK integration or a server-owned Genkit workflow. Use when a web, mobile, backend, or full-stack feature needs model calls, typed outputs, reusable flows, tools, retrieval, prompt files, evals, observability, or deployment. Choose client-ai-logic, flow-foundation, tool-and-agent, retrieval-and-prompt, evaluation-and-observability, deployment-runtime, or comparison-or-fallback; route Firebase platform/operator work to `firebase-cli` and broad framework comparisons to `survey`.
Google Drive, Gmail, Calendar, and Docs operations via OAuth. Use this skill when uploading files to Drive, searching Drive folders, searching Gmail, finding calendar meetings, creating Google Docs, or managing folder structures. Triggers on Google Workspace operations, file uploads, email search, calendar search, or document creation.
Lark OKR: manage objectives and key results. View and edit OKR cycles, objectives, key results, alignment relationships, quantified metrics, and progress records. Use when users need to view or create OKRs, manage objectives and key results, or view alignment relationships. Does not handle: to-do task management (lark-task), scheduling/meetings (lark-calendar), performance reviews.
LLVM passes skill for writing compiler optimizations. Use when writing FunctionPass or ModulePass, registering PassPlugins, running with opt, using analysis utilities, or testing with llvm-lit. Activates on queries about LLVM pass, PassPlugin, opt -passes, DominatorTree, llvm-lit, or New Pass Manager.
Meta Media Buyer — publish, manage, and analyze Meta (Facebook/Instagram) ad campaigns via the Marketing API. Includes guided setup for first-time users. USE WHEN user says "meta ads", "facebook ads", "instagram ads", "publish ads", "create campaign", "launch campaign", "ad performance", "ROAS", "which ad is winning", "ad spend", "campaign metrics", "pause campaign", "resume campaign", "upload ad images", "ad set performance", "creative performance", "set up meta ads", "connect meta ads", "meta ads setup", or needs to publish, manage, or analyze paid Meta advertising campaigns.
Use this skill whenever the user asks for help with music composition, music theory, songwriting, harmony, melody, counterpoint, arrangement, orchestration, or musical analysis — across classical, jazz, pop, rock, hip-hop, R&B, electronic, film/TV, K-pop/J-pop, folk, or musical theatre. Triggers include explicit theory questions (“what scale fits over Cm7”, “explain ii-V-I”, “modulate from C to E♭”), craft questions (“write a chord progression for a melancholy bridge”, “make this melody more memorable”, “voice this chord on piano”), and vague creative problems that map to compositional techniques (“the chorus feels weak”, “this transition is awkward”, “my song sounds generic”). Use this skill even when the user describes the goal in non-technical terms — translating fuzzy creative problems into concrete compositional moves is exactly what this skill is for. Do NOT use for DAW operation, MIDI file generation, audio engineering, mixing/mastering, sound design, or notation software UI.
Use when the user reaches for a Code node, mentions writing JavaScript or Python in n8n, or any custom logic comes up in workflow design. Triggers on "Code node", "Code", "JavaScript", "Python", "custom logic", "transform data", "$input", "$json transformation", "loop in code", "write a function", or any time the obvious answer seems to be "just put it in code."
Prepares meeting agendas, internal pre-reads, and decision briefs using Notion context and relevant research. Use for meeting preparation, recurring meeting context, or updating meeting outcomes; use knowledge-capture for a standalone record of an existing discussion.
Turn a dense PDF (or one chapter or section) into a single-file interactive HTML page that is faster to understand than the original and fun to explore. Start with a 30-second summary, include hands-on scenes and guess-then-reveal interactions, cite every number with a link that opens the original sentence and page, illustrate it in a chosen art style, then self-audit against the source. Use whenever someone wants to make a PDF, paper, textbook chapter, annual report / 10-K, rulebook, manual, contract, novel chapter, or lecture notes easier to read, “come alive,” interactive, explorable, scrollytelling, or into a mini web app, interactive lesson, or courseware—even if they only say “this PDF is unreadable,” “help me get through this,” or mention a Gemini Canvas / Claude Artifacts-style “PDF to web app.” Chinese triggers: 把 PDF 做成网页、可交互网页、互动课件、可视化讲解、读不下去的 PDF、论文/教材/财报/规则书/名著变成能玩的页面、Canvas 那种 PDF 变网页
Peripheral driver methodology skill from MCU reference manuals. Use when reading register maps, timing diagrams, and writing drivers from vendor documentation. Activates on queries about reference manual, register map, peripheral init sequence, or datasheet-driven driver design.
Create investor pitch decks designed to stand alone without a presenter. Follows Sequoia/YC frameworks with traction-first structure and standalone readability. Use when creating a "pitch deck", "investor presentation", "fundraising deck", or any deck sent async to investors, partners, or stakeholders who won't have the presenter alongside.
Use when building Python 3.11+ applications requiring type safety, async programming, or robust error handling. Generates type-annotated Python code, configures mypy in strict mode, writes pytest test suites with fixtures and mocking, and validates code with black and ruff. Invoke for type hints, async/await patterns, dataclasses, dependency injection, logging configuration, and structured error handling
Wins back customers who have quietly stopped buying — finds those whose gap has stretched beyond their normal rhythm or who show churn signals, ranks them by the value of the relationship, drafts a win-back message for each customer in the owner's voice, and sends and logs only what the owner approves. Chains review-reputation, outreach-composer, and crm-autopilot, and keeps the rule that the first touch acknowledges the gap without pitching. Use whenever the owner is worried about customers drifting away, including phrasings like “who hasn't ordered in a while,” “win back my old customers,” “which customers have gone quiet,” “we lost some regulars,” “reach out to the people who stopped calling,” or “how do I get them back.” Reach for it when the owner names a customer they have not heard from, as readily as for a full win-back campaign.
Build, integrate, audit, or upgrade Stream Chat, Video, Feeds, and Moderation in React / Next.js web apps - the default skill for web work. Scaffold a new app, add Stream to an existing project, review an integration, upgrade an SDK major, or migrate from Sendbird. Covers team messaging, DMs, video conferencing, livestreaming, social feeds, AI assistants (including generative UI with A2UI / OpenUI), and apps built on Stream Agents (voice and text agents, @stream-io/stream-agents). Web React only - React Native uses stream-react-native.
Guide to implementing the Syncfusion Blazor Carousel component for image galleries, product showcases, and content sliders. Use when the user mentions carousels, image sliders, slideshows, content rotation, product galleries, rotating banners, slide transitions, or displaying multiple items in a cycling presentation
Implement Syncfusion Blazor Circular Gauge (SfCircularGauge) for radial data visualization. Use when creating speedometers, tachometers, KPI dashboards, or circular progress indicators. Covers needle pointers, gauge ranges, annotations, and circular metric visualization in Blazor applications
Run Vercel-specific deployment operations for linked web/fullstack projects: preview deploys, direct production deploys, staged deploy + promote flows, aliases/domains, environment-variable sync, and rollback response. Use when the request is specifically about operating a project on Vercel after the provider is already chosen—especially when someone needs a preview URL, stable alias, custom domain, env-scope fix, production cutover, or rollback on Vercel. Triggers on: Vercel deploy, Vercel preview URL, vercel promote, vercel alias, Vercel domain, Vercel env, Vercel rollback, and Vercel CLI deployment. Route provider-neutral release strategy to `deployment-automation`, CI/workflow authoring to `deployment-automation`, and local install/auth/bootstrap work to `system-environment-setup`.
Use when you need to design, review, or improve REST APIs with Quarkus REST (Jakarta REST) — including resource classes, HTTP methods, status codes, request/response DTOs, Bean Validation, exception mappers, optional runtime OpenAPI exposure (SmallRye), contract-first generation from OpenAPI, content negotiation, pagination, sorting and filtering, API versioning, idempotency (Idempotency-Key), optimistic concurrency (ETag / If-Match), HTTP caching (Cache-Control), API deprecation (Sunset / Deprecation headers), RFC 7807 Problem Details, ISO-8601 for time in contracts, and security-aware boundaries. This should trigger for requests such as Review or improve JAX-RS resources in a Quarkus project; Design HTTP APIs with validation and error handling on Quarkus; Add API versioning, idempotency, ETag concurrency, or deprecation headers; Implement pagination, sorting, or RFC 7807 Problem Details error responses; Improve Quarkus REST resources and exception mappers. Part of Plinth Toolkit
Systematic JavaScript/TypeScript performance audit and optimization using V8 profiling and runtime patterns. Use when (1) Users say 'optimize performance', 'audit performance', 'this is slow', 'reduce allocations', 'improve speed', 'check performance', (2) Analyzing code for performance anti-patterns (O(n²) complexity, excessive allocations, I/O blocking, template literal waste), (3) Optimizing functions regardless of current usage context - utilities, formatters, parsers are often called in hot paths even when they appear simple, (4) Fixing V8 deoptimization (monomorphic/polymorphic issues, inline caching). Audits ALL code for anti-patterns and reports findings with expected gains. Covers loops, caching, batching, memory locality, algorithmic complexity fixes with ❌/✅ patterns.
Score and tier a list of accounts (or your full book) against ICP fit and engagement signals to prioritize where to spend time. Use when the user asks to “tier my accounts”, “prioritize my book”, “which accounts should I focus on”, or “score these accounts”.
Use when the user runs /add-dictation or wants speech turned into text with Grok speech-to-text: a mic button that dictates into the composer, live captions, or transcribing recorded audio (files, uploads, URLs) with word timestamps, diarization, subtitles, meeting notes. STT, transcribe, transcription. For a voice agent that talks back use /add-voice.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Expert knowledge for Azure Blob Storage development, including troubleshooting, best practices, decision-making, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use when planning tiers/costs, lifecycle/versioning, SAS/RBAC auth, NFS/SFTP access, or SDK/BlobFuse integrations, and for other Azure Blob Storage development tasks. Not for Azure Files (use azure-files), Azure Queue Storage (use azure-queue-storage), Azure Table Storage (use azure-table-storage), or Azure NetApp Files (use azure-netapp-files).
DPDK skill for userspace packet I/O. Use when initializing EAL, configuring PMD drivers, using mbuf pools and rte_ring, setting up huge pages, RSS, or testpmd validation. Activates on queries about DPDK, EAL, rte_eth_rx_burst, hugepages, PMD, or testpmd
Email has the highest ROI of any marketing channel. $36 for every $1 spent. Yet most startups treat it as an afterthought - bulk blasts, no personalization, landing in spam folders. This skill covers transactional email that works, marketing automation that converts, deliverability that reaches inboxes, and the infrastructure decisions that scale. Use when: keywords, file_patterns, code_patterns.
Guides equity compensation planning for wealth management clients: RSU vesting and the supplemental-withholding gap, NSO and ISO exercise taxation, AMT on ISO spreads and the AMT credit, qualifying vs disqualifying dispositions, 83(b) elections for restricted stock, qualified Section 423 ESPPs, and managing concentrated employer stock (staged diversification, exchange funds, protective collars, charitable strategies, Rule 10b5-1 trading plans, Section 16 insider constraints). Use when the user asks about stock options, RSUs, ESPP purchases, or trading windows — e.g. 'my RSUs vested', 'should I exercise my ISOs', 'will I get an AMT hit', 'file an 83(b) election', 'disqualifying disposition', 'set up a 10b5-1 plan', 'I have too much company stock', or questions about selling employer shares as an executive or insider.
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
Send files, images, and audio messages via Feishu Lark API using the mandatory two-step process. Use when needing to send files, images, or voice messages to Feishu users or groups. This skill enforces the required workflow: first upload to get file_key, image_key, or audio_key, then send message with the key. Supports file API for documents, image API for pictures, and file API with audio type for voice messages.
Find feature flags that were soft-deleted in the active project within a recent time window. Use when the user asks "what flags were deleted in the last N days", "show me recently deleted feature flags", "who deleted flag X", "audit recent flag deletions", or anything similar. Handles the non-obvious gotcha that system.feature_flags exposes the deleted boolean but does not expose a deletion timestamp — the actual deleted-at time lives in the per-flag activity log and must be cross-referenced.
Reviews PRs against the live base with immutable objects and three-way merges. Use for PR review/merge readiness, main changed, closed-PR reconsideration, open-PR sweeps, review-led repair, or explicitly requested independent review of your own contribution. Not for GitHub CRUD (use github-ops), authoring/maintaining your PR (use github-contributor), or merging without fresh review.
Find and use real Hugeicons icon names in any framework—React, Vue, Svelte, SolidJS, Angular, React Native, and Flutter. Use whenever UI work needs icons—dashboards, sidebars, navigation, toolbars, buttons, menus, empty states—including in a project with no icon library installed yet and when the user has not mentioned icons. Also use whenever a project depends on @hugeicons/*, @hugeicons-pro/*, or the Flutter hugeicons package. Covers choosing the icon library, installation, rendering, props, and resolving names through the Hugeicons MCP server
Design Instagram carousel posts as self-contained HTML files in the user’s own brand. Runs a one-time brand setup on first use (name, handle, subtitle, photo, accent color, style preference). Four design styles: Bold Impact (dark premium), Tweet Post (minimal text), Clean Editorial (light/white), Product Showcase (soft gradient). Fixed 420x525px slides, Poppins font, progress bar, arrow indicators, white CTA slide, PNG + PDF export. Triggers: instagram carousel, carousel design, ig carousel, create carousel, design carousel, carousel post, make a carousel, instagram post design, carousel html, slide deck for instagram, visual carousel
Generate, validate, and fix KiCad 8/9 schematic files (.kicad_sch) programmatically. Use this skill whenever the user wants to create, modify, or fix KiCad schematics, generate netlists from circuit descriptions, fix ERC errors, or migrate schematics between KiCad versions. Triggers on: KiCad, schematic, .kicad_sch, ERC, electrical rules check, circuit design, PCB schematic, netlist generation, S-expression schematic, KiCad migration.
Use for marketing and paid-social creative: packaging design and mockups, product photoshoots, marketplace cards, static/UGC/video ads, campaign key visuals, ad storyboards, product launches, and Meta Ads. For generic media generation use krea-generate.
Upgrades a custom Workflow SDK World implementation from the v4 spec, or from a 5.0.0 beta, to the current v5 spec (spec version 8). Use when a package implements the `World` interface from `@workflow/world` and is moving to 5.x, or is on a 5.0.0 beta and the runtime reports `This Workflow runtime supports Worlds with spec version 6 through 8, but the configured World declares spec version N`; or when it shows event IDs that are ULIDs rather than slot positions, `Event id is not slot-numbered` at replay time, a `specVersion` the runtime refuses, `writeToStream` / `closeStream` / `readFromStream` as top-level World methods, `steps.get` or `events.listByCorrelationId` without a `runId`, a `'step'` queue kind or `__wkf_step_*` topics, a `preconditionGuard` capability, or a `createLocalWorld` / `createVercelWorld` factory
Operational arsenal for authorized external red-team and bug-bounty recon. Concrete probes, wordlists, regexes, dorks, curl one-liners for: subdomain enum, GraphQL/Swagger/REST discovery, identity fabric (Entra/Okta/ADFS/Google/SAML/M365 deep — Teams/SharePoint/OneDrive), cloud bucket enum (S3/GCS/Azure), CDN/WAF bypass, origin discovery, vendor fingerprinting (Citrix/F5/Pulse/Fortinet/PaloAlto/Cisco/VMware), CI/CD exposure, 48-pattern secret-scan catalog (AWS/GCP/GitHub/Stripe/Slack/Anthropic/OpenAI/Atlassian/DataDog/npm/PyPI), Postman workspaces, breach correlation (HudsonRock/HIBP/DeHashed/IntelX), TLS/JA3 audit, certificate transparency, JS endpoint extraction, package registry leaks, mobile/APK recon, sat imagery, sector-specific recon (healthcare DICOM, finance SWIFT, ICS/SCADA Modbus/BACnet). Detail content in 15 modular reference files, loaded on demand. Use for any authorized recon: scoping, asset discovery, attack-path mapping, secret triage, severity scoring.
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.