Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
A Vue SFC best-practices guide for mini-program projects using weapp-vite, covering script setup, template-only SFCs, JSON macros, `definePageMeta`/layout, `defineModel`, `usingComponents`, built-in i18n Behavior, JSX/TSX script blocks, template directive compatibility, multi-platform SFCs, `.weapp-vite` type support files, and the managed `prepare` workflow.
Create a punchy highlight cut from a video with Adobe Quick Cut — for requests like “make a sizzle reel”, “make a highlight reel”, “quick cut this”, “cut the best parts”, “shorten this video”, “make a highlight clip”, or “summarize this video visually”. Works from the user's original request without follow-up questions and produces one highlight cut. Do NOT use it for exact-timestamp trims (“cut from 0:30 to 1:15”) or other deterministic edits — Quick Cut selects moments by relevance, not exact instructions; those need manual editing. Requires a video file (an upload or an already-referenced Creative Cloud asset).
Query AlertManager via curl using the v2 API. Use when listing active/silenced alerts, creating/managing silences, or checking alert inhibition state. Triggers on: alertmanager, silences, silence alerts, alert filters, alert inhibition, alertmanager API, create silence, delete silence.
Generates Angular 17+ standalone components, configures advanced routing with lazy loading and guards, implements NgRx state management, applies RxJS patterns, and optimizes bundle performance. Use when building Angular 17+ applications with standalone components or signals, setting up NgRx stores, establishing RxJS reactive patterns, performance tuning, or writing Angular tests for enterprise apps.
Builds carousels with @blossom-carousel/react in React and Next.js, covering BlossomCarousel setup, CSS scroll-snap layouts, BlossomPrev/BlossomNext/BlossomDots/BlossomDot controls, ref methods (prev, next, goTo), useBlossomNavigation for custom controls, and command and overscroll events. Use when a React or Next.js project imports @blossom-carousel/react or renders <BlossomCarousel>, or when the user wants a Blossom carousel, slider, or gallery in React or Next.js.
Diagnose whether the most important idea in an article, essay, post, memo, section, paragraph, or sentence appears where it best serves the reader. Use for BLUF checks, buried or misplaced ledes, slow or misleading openings, intro drift, competing main ideas, and requests to get to the point or find the real opening. Compare what the opening foregrounds with what the artifact actually delivers, judge whether any delay is earned, and recommend the smallest structural move. Diagnose by default; rewrite only when asked.
Security engineering that protects applications, data, and users from real-world threats. Use when “security, authentication, authorization, encryption, OWASP, vulnerability, XSS, SQL injection, CSRF, secrets, password, JWT, OAuth, permissions, audit, compliance” are mentioned.
Configures and runs Depot remote container builds using `depot build` and `depot bake`. Use when building Docker images, creating Dockerfiles with Depot, pushing images to registries, building multi-platform/multi-arch images (linux/amd64, linux/arm64), debugging container build failures, cancelling builds, configuring autoscaling, optimizing Dockerfile layer caching, using docker-bake.hcl or docker-compose builds, or migrating from `docker build` / `docker buildx build` to Depot. Also use when the user mentions depot build, depot bake, container builds, image builds, or asks about Depot's build cache, build parallelism, build autoscaling, or managing Depot Registry repositories, images, tokens, retention, and upstreams.
Framework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations including Navier-Stokes equations (2D/3D), shallow water equations, stratified flows, or when analyzing turbulence, vortex dynamics, or geophysical flows. Provides pseudospectral methods with FFT, HPC support, and comprehensive output analysis.
Use when building game systems, implementing Unity/Unreal Engine features, or optimizing game performance. Invoke to implement ECS architecture, configure physics systems and colliders, set up multiplayer networking with lag compensation, optimize frame rates to 60+ FPS targets, develop shaders, or apply game design patterns such as object pooling and state machines. Trigger keywords: Unity, Unreal Engine, game development, ECS architecture, game physics, multiplayer networking, game optimization, shader programming, game AI.
Generates service-specific configuration files for GitLab stack projects in the ./config directory, using .env as the primary configuration source. Creates nginx, PostgreSQL, Redis, and custom service configs with strict validation for secrets, paths, and Docker best practices. Use when setting up service configurations, creating config templates, or ensuring configs follow stack patterns.
Expert blueprint for idle/clicker games including big number handling (mantissa + exponent system), exponential growth curves (cost_growth_factor 1.15x), generator systems (auto-producers), offline progress calculation, prestige systems (reset for permanent multipliers), number formatting (K/M/B suffixes, scientific notation). Use for incremental games, idle games, or cookie clicker derivatives. Trigger keywords: idle_game, big_number, exponential_growth, generator_system, offline_progress, prestige_system, number_formatting.
Implements concurrent Go patterns using goroutines and channels, designs and builds microservices with gRPC or REST, optimizes Go application performance with pprof, and enforces idiomatic Go with generics, interfaces, and robust error handling. Use when building Go applications requiring concurrent programming, microservices architecture, or high-performance systems. Invoke for goroutines, channels, Go generics, gRPC integration, CLI tools, benchmarks, or table-driven testing.
Post team updates to Google Chat Spaces via webhook. Deployment notifications, bug fixes, feature announcements, questions. Reads config from .claude/settings.json, includes git context. Use when: "post to team", "notify team", after deployments, completing features, fixing bugs, asking team questions.
Translate Gremlin and TinkerPop-style traversals into direct HelixDB v3 Rust SDK requests. Use when the input contains Gremlin, TinkerPop, g.V, g.E, hasLabel, has, out, in, both, outE, inE, repeat, emit, dedup, valueMap, count, range, or limit. When the target is Helix Cloud, always use helix-mcp first.
Automatically generate an AI image on Higgsfield using Playwright browser automation. Use when the user has an image prompt and wants to generate it on Higgsfield Soul 2.0 or Nano Banana Pro. Triggers on requests like "generate image on higgsfield", "create image", "auto-generate image", "make the image on higgsfield", or any request to submit an image generation job. Requires Playwright MCP tools.
Use when the user asks to “create a hook,” “add a PreToolUse/PostToolUse/Stop hook,” “validate tool use,” “implement prompt-based hooks,” “use ${CLAUDE_PLUGIN_ROOT},” “set up event-driven automation,” “block dangerous commands,” or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks, focusing on the advanced prompt-based hooks API
Automatically organizes invoices and receipts for tax preparation by reading messy files, extracting key information, renaming them consistently, and sorting them into logical folders. Turns hours of manual bookkeeping into minutes of automated organization.
Build high-converting landing pages with proven structure, persuasive sections, and best practices. From hero to footer—every element optimized. Use when: Writing landing pages from scratch; Improving existing underperforming pages; Creating templates for repeatable page types; Structuring lead gen, sales, or product pages; Reviewing pages for conversion optimization
Create, get, edit, delete, list, validate, and consolidate all global configurations in a Mule project — connector configs, TLS Context, Object Store, Caching Strategy, Global Error Handler, API AutoDiscovery, Import Project Reference, properties files, global-property elements, and multi-environment setup. Use when the user asks to "add Salesforce config", "configure connector", "set up connection", "create TLS context", "set up object store", "add caching strategy", "create error handler", "set up autodiscovery", "import shared project", "create config.yaml", "set up environments", "add global property", "list global elements", "find usages", "validate config exists", "consolidate configs", or any request to manage global-level configuration in a Mule app. NEVER use MCP server tools — use only the bash scripts provided
Configuring fonts and glyphs for MapLibre GL JS and MapLibre Native — the style's `glyphs` URL, self-hosting or generating font PBFs, the GL JS local-font fallback (omitted `glyphs` or a failed glyph fetch), the `font-faces` property both SDKs read, and CJK, right-to-left, and Devanagari script handling. Use when text labels aren't rendering in the intended font, setting up a glyphs server, choosing between self-hosting and generating font PBFs, or handling non-Latin scripts
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.
Generate speech audio from text using OpenRouter's text-to-speech API. Use when the user asks to synthesize speech, narrate text, create a voiceover, generate an audiobook clip, read text aloud, convert text to an audio file, or mentions TTS, text-to-speech, or voice synthesis
Use when the user wants to talk through work with Pipa or their current agent in a live voice huddle: Pipa Huddle, Pipa voice session, talk this through, walking work session, plan this by voice, voice call with my agent, or discuss this out loud. Starts a voice huddle with agent context and optional handoff. Do not use for audio brief generation, generic TTS, video meetings, Zoom/Meet bots, or realtime voice coding/permission approval.
Use this skill when the user asks to create custom Remotion transitions, asks about “cool transitions,” “cinematic transitions,” “striped transitions,” “glitch transitions,” “custom TransitionPresentation,” or wants to build scene-to-scene transitions in Remotion beyond the built-in library. Also triggers for “how to make transitions in Remotion,” “custom transition,” “high-energy transitions,” “energy transitions,” “branded transitions.”
RESTful API design guidelines following the Richardson Maturity Model through to Level 3 (HATEOAS) for Ruby on Rails. This skill should be used when designing, building, reviewing, or refactoring REST APIs to ensure proper resource modeling, HTTP method semantics, hypermedia controls, content negotiation, and API evolvability. Triggers on tasks involving API controllers, serializers, routing, link relations, pagination, error handling, or HTTP caching in Rails.
Deploy a WHOLE redesigned site to AEM Edge Delivery Services — the full-site, bulk sibling of `deploy` (which ships one page). Use to roll out, bulk-deploy, or publish an entire migrated stardust site at once (“deploy all pages”, “full site deployment”, “deploy the whole/entire website to AEM”), not just a single page. Inventories the migrated tree (stardust/migrated/ + _meta.json) into a delivery ledger, dedups blocks, drives `deploy` per page, verifies, and tracks what's done and what's left. Supports archetypes-only mode — when only the template archetype pages are migrated, it deploys all block code immediately and registers the rest as content-pending.
Reverse-engineering specialist that extracts specifications from existing codebases. Use with legacy or undocumented systems, inherited projects, or old codebases without documentation. Invoke to map code dependencies, generate API documentation from source, identify undocumented business logic, understand what code does, or create architecture documentation from implementation. Trigger phrases: reverse engineer, old codebase, no docs, no documentation, figure out how this works, inherited project, legacy analysis, code archaeology, undocumented features.
Modelar, consultar, migrar e operar PostgreSQL com integridade, índices, concorrência, segurança, performance e recuperação. Use para schemas, SQL, EXPLAIN, locks, isolation, migrations, roles, backup ou tuning em Postgres; não use para bancos diferentes sem confirmar semântica.
External recon for software supply-chain attack surface — package-namespace squatting candidates, dependency-confusion vulnerabilities, GitHub Actions injection openings, container image registry exposure, SBOM mining, internal-package-name leakage, and CI/CD configuration exposure. Reconnaissance and identification ONLY — actual package publishing / typosquat attacks are EXTERNAL-OFFENSIVE and require explicit written sign-off because they can affect the entire npm/PyPI ecosystem. Use when the target has a public GitHub org, when their build artifacts/SBOMs are reachable, when their docker images are on Docker Hub/GHCR, or when you find internal package names in their JS bundles.
Generates and edits SVG logos, icons, and graphics. Use when creating SVG files, designing logos or icons, writing path data, optimizing SVGs, building icon systems, animating SVG elements, or modifying existing vector graphics. Covers path commands, shape primitives, styling, accessibility, gradients, masks, sprites, optimization, and animation (CSS keyframes, GPU acceleration, staggering, easing, SVG-specific techniques).
Tailwind CSS accessibility patterns, including WCAG 2.2 compliance, touch targets, focus management, and ARIA. Proactively activate for: (1) building accessible UI with Tailwind, (2) WCAG 2.2 compliance (Level A, AA, AAA), (3) focus rings and focus-visible styling, (4) minimum touch-target sizes (24x24/44x44), (5) color contrast and text legibility, (6) screen-reader-only utilities (sr-only, not-sr-only), (7) prefers-reduced-motion handling, (8) ARIA attribute styling (data-state, aria-* selectors), (9) keyboard navigation patterns, (10) accessible forms (label association, error announcements). Provides a WCAG 2.2 checklist, focus-management utilities, touch-target sizing recipes, sr-only patterns, and accessible component templates.
Test-driven development workflow for Noodle. Use when testing changes, writing tests, fixing bugs, creating fixtures, or running the test suite. Triggers: “test”, “write a test”, “fix this bug”, “add a fixture”, “run tests”, “TDD”, or any task involving verification of code changes
Integrate an external wallet (signer) into an IC dapp with @icp-sdk/signer—the relying-party side of the ICRC signer standards. Covers choosing a transport (popup via ICRC-29, top-level redirect via ICRC-167, or browser extension via ICRC-94), negotiating capabilities, managing permissions and the account lifecycle, and executing canister calls the user approves through SignerAgent (ICRC-49). Uses OISY as the worked example but applies to any ICRC-25 signer. Do NOT use for Internet Identity login (use the user-sign-in skill) or for implementing a wallet yourself. Use when the developer mentions wallet integration, OISY, @icp-sdk/signer, or approving a transaction in a wallet popup
General-purpose desktop web prototype. Single self-contained HTML file built by copying the seed `assets/template.html` and pasting section layouts from `references/layouts.md`. Default for any landing / marketing / docs / SaaS page when no more specific skill matches.
Review, critique, rewrite, or design product error messages and error-handling UX. Use when Codex is asked to improve validation errors, server failure messages, empty/failure states, toast/dialog copy, support escalation paths, or error-message inventories so users understand what happened, what was not affected, and what to do next.
Create viral X (Twitter) posts including short tweets, threads, and replies. Use when user wants to write X content, create posts, or mentions "create tweet", "write thread", "x-create", "写推文", "创作推文". Supports 5 post styles with customizable templates, plus a mandatory humanize pass to reduce AI-sounding phrasing. First-time users go through onboarding to set up profile.
Focuses on content trend analysis on Xiaohongshu, offering in-depth insights based on the top 50 popular posts from the past 7 days. Supports category searches across 24 verticals, discovery of unexpected viral hits, and daily subscription updates. Creators can explore popular Xiaohongshu content, analyze viral posts, track trends across fields, or find inspiration.
I Ching feng shui analysis for homes, based on Ni Haixia’s I Ching home feng shui teachings, emphasizing “name and position in accord” and “seniority and order.” Triggers: feng shui, home feng shui, residential analysis, orientation, office feng shui, boss’s position
Use when several agents share a repo: claim a task, see who works on it, reserve an id, sync the board, set up coordination. RU: возьми задачу, кто сейчас делает, зарезервируй id, обнови доску. Not for solo work or an unconfigured repo: 'no coordination' / «без координации».
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.