Skills
98,067 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when a Backstage backend plugin or module needs a core service — logger, config, http router, database, scheduler, lifecycle, cache, urlReader, discovery, auth, httpAuth, or userInfo. Triggers on imports of coreServices.* refs from @backstage/backend-plugin-api or any deps map in a plugin/module register block.
Use when defining or authoring a Backstage backend plugin or module. Covers createBackendPlugin and createBackendModule from @backstage/backend-plugin-api, service registration via coreServices.* refs, and exposing extension points with createExtensionPoint. Triggers on imports from @backstage/backend-plugin-api or when writing src/plugin.ts, src/module.ts, src/index.ts in a backend package.
Use when a Backstage plugin needs to gate UI behind permissions (frontend) or authorize actions in route handlers (backend). Covers createPermission, the usePermission hook and RequirePermission component, the coreServices.permissions service for backend authorization, and resource permissions for per-instance checks. Triggers on phrases like "require permission", "gate this UI", "check authorization", or imports of @backstage/plugin-permission-common, @backstage/plugin-permission-react, or @backstage/plugin-permission-node.
Use when authoring UI for a Backstage frontend plugin. Covers the @backstage/ui (BUI) component library — layout, typography, forms, dialogs, menus, tables — plus styling via CSS modules with BUI design tokens, and Remix Icons. Triggers on imports of @backstage/ui or when creating any frontend component.
Use when working with concrete utility components in BK-CI, such as JWT, security authentication, expression parsing, thread pool loop utilities, and chain-of-responsibility implementations. Prefer this when the user wants to reuse these components directly rather than design framework-level practices.
Valaxy static blog framework built with Vue 3, Vite, and pnpm workspaces. Use when working with Valaxy projects: (1) creating or configuring Valaxy blog sites (site.config.ts, valaxy.config.ts), (2) writing blog posts with frontmatter, (3) developing Valaxy themes (valaxy-theme-*), (4) developing Valaxy addons (valaxy-addon-*), (5) customizing components/layouts/styles, (6) working with the Valaxy monorepo core framework, (7) debugging Valaxy builds or dev server, (8) deploying Valaxy sites. Triggers on: valaxy.config.ts, site.config.ts, theme.config.ts, defineValaxyConfig, defineSiteConfig, defineThemeConfig, defineTheme, defineAddon, valaxy-theme-*, valaxy-addon-*, pages/posts/, ValaxyMain, useSiteConfig, useFrontmatter, #valaxy/config.
Find similar vulnerabilities and bugs across codebases using pattern-based analysis. Use when hunting bug variants, building CodeQL/Semgrep queries, analyzing security vulnerabilities, or performing systematic code audits after finding an initial issue.
Velt Notifications implementation patterns and best practices for React, Next.js, and web applications. Use when adding in-app notifications, notification panels, email notifications via SendGrid, webhook integrations, user notification preference management, cross-organization notification feeds with enableCrossOrganization/disableCrossOrganization, or binding Notifications Panel / Notifications Tool wireframe slots with template variables (velt-data, velt-if, velt-class).
Integrate Redis-compatible Vercel KV for caching, session management, and rate limiting in Next.js applications. Powered by Upstash with strong consistency and TTL support. Use when implementing cache strategies, storing temporary data with expiration, building rate limiters, or troubleshooting missing environment variables, serialization errors, or rate limit issues.
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
Verifies a merged change took effect in production by revision ancestry and cohort sampling, and reports a bound over sampled requests rather than "fully deployed". Use when the user says "is it live in prod?", or when asked to confirm or report whether a merged change is live or deployed in production, before answering, even when the build-info, status, or deploy output is already in hand; also when gating on a deploy reaching the fleet, sequencing deploys, or verifying a one-time migration, backfill, or cleanup. Not for CI or build state.
Get exported video files ready to post, without touching a single slider. Upload your design assets, video clips (MP4, MOV, PNG, WebM, up to 500MB), say something like "convert my Figma design frames into a smooth product demo video with transitions", and download 1080p MP4 when it's done. Built for UI/UX designers, product teams who move fast and want to present Figma designs as videos without switching to a video editor.
Turn a 3-minute unedited screen recording into 1080p edited video files just by typing what you need. Whether it's automatically editing raw footage into polished videos or quick social content, drop your raw video footage and describe the result you want. No timeline dragging, no export settings — 1-2 minutes from upload to download.
generate text or images into ready-to-share videos with this skill. Works with MP4, MOV, PNG, JPG files up to 200MB. content creators use it for generating videos from text prompts or images without paying — processing takes 1-2 minutes on cloud GPUs and you get 1080p MP4 files.
Diagnose why an existing implementation differs from reference evidence using AE/SSIM, pixel, section, computed-style, and transition diffs. Use for post-implementation mismatch or repair guidance; not baseline capture or full clone generation.
Generate professional Chinese visual note cards (视觉笔记卡片/信息图) as single-page HTML infographics with automatic PNG export. Use this skill whenever the user asks to create a visual note, knowledge card, infographic, one-pager summary, visual summary, 知识卡片, 视觉笔记, 信息图, 一页纸总结, or any poster-style knowledge visualization. Also trigger when the user wants to summarize an article, blog post, book chapter, or concept into a structured visual card format, or when they reference an existing visual note and ask to create one in the same style. This skill produces both a self-contained HTML file and a high-quality PNG image, ready for sharing on social media or printing.
Use when the user is building on Web 3 Data Spaces (W3DS) or the MetaState prototype — building a post-platform, integrating an eVault, calling the eVault GraphQL API (createMetaEnvelope, updateMetaEnvelope, removeMetaEnvelope, bulkCreateMetaEnvelopes, uploadFile, bindingDocument*), wiring the Web3 Adapter, writing a webhook controller for /api/webhook, authoring mapping.json files, using the wallet-sdk, implementing the w3ds://auth or w3ds://sign flow, resolving W3IDs / eNames via the Registry, working with the Ontology service, proposing a new ontology, dealing with Binding Documents, dereferencing w3ds://file URIs, provisioning an eVault, syncing public keys, hosting a platform on GitW3 (the W3DS-aware Git forge — `.w3ds/platform.json`, platform eName, version eName, PPA certification, deployment records, porting an existing app, `w3ds-deployment-key.json`), or debugging local dev (Registry, Provisioner, eVault-core, Dev Sandbox, pnpm dev:core). Also use for any design decision about where data lives on a W3DS platform — adding a table, entity, model or field, deciding what to cache locally, or asking whether something belongs in the database or the eVault. Also use for company signing delegation — a company eVault with directors, titled roles, delegations and re-delegations, signing on behalf of a company, verifyDelegatedSignature / buildDelegatedSignRequest / buildGrantSignRequest. Also use when the user asks what an eVault, W3ID, eName, MetaEnvelope, Envelope, Ontology, Web3 Adapter, Awareness Protocol, or Awareness-as-a-Service is.
Walrus Memory (MemWal) — persistent, portable, encrypted memory for AI agents. Use when the user needs to give an AI agent persistent memory across sessions and apps, integrate the @mysten-incubation/memwal TypeScript SDK or Python memwal SDK, set up the Walrus Memory MCP server for Cursor/Claude/Codex, configure remember/recall/analyze/restore operations, manage memory spaces and namespaces, set up delegate keys and accounts, self-host the relayer, or use withMemWal AI middleware (Vercel AI SDK, LangChain, OpenAI SDK). Also use when the user asks about MemWal, Walrus Memory, agent memory, memory spaces, or the memwal-mcp package.
Use when creating designed PDFs from owned HTML/CSS templates with WeasyPrint. Covers invoice/report/proposal/brief/receipt/statement templates, render scripts, example galleries, font guidance, and QA checks for page size, warnings, overflow, extraction, and visual layout.
Generate web assets including favicons, app icons (PWA), and social media meta images (Open Graph) for Facebook, Twitter, WhatsApp, and LinkedIn. Use when users need icons, favicons, social sharing images, or Open Graph images from logos or text slogans. Handles image resizing, text-to-image generation, and provides proper HTML meta tags
Keyless, self-hostable multi-engine web search and clean-Markdown page reader for AI agents. Use it when the user asks to search the web, look something up online, find current or recent information, research a topic, fetch or read a URL, find academic papers or GitHub repositories, verify a claim against live sources, or configure and verify its NordVPN egress proxy. Fuses many keyless engines via the ddgs metasearch (plus a self-hosted SearXNG it can start itself), then extracts pages to clean Markdown, fenced as untrusted and paginated. Commands: init (bring it online), web-search (find pages), web-fetch (read a URL), web-open (page through a fetched document), arxiv (search papers), github (search repositories).
Turn de-anonymized website visitors into enriched, outreach-ready leads. The visitor identification itself runs in an external pixel/IP tool (RB2B, Warmly, Koala, Leadfeeder); this skill covers the ColdIQ marketplace tail — enriching and resolving identified visitors and timing outreach. Use when setting up website-visitor tracking, enriching identified visitors, scoring pricing/demo-page visits, or routing visitor signals to sequences. Triggers on "website visitors", "visitor tracking", "RB2B", "de-anonymize", "pixel identification", "IP to company", "Warmly", "Leadfeeder", "Koala", "visitor alerts", "who visited my site". Do NOT use for social post engagement (see signal-detection) or third-party intent data (see signal-detection).
Publish one or multiple Markdown articles to WeChat Official Account (公众号) draft box in a single API call. Supports multi-article combined drafts (main article + sub-articles), smart cover image selection with Unsplash auto-match + 12-image fallback rotation, custom styling (gold quote highlights, && section dividers, accent headings), inline image auto-upload to WeChat CDN, digest auto-extraction, and optional immediate publish. Activate when user wants to push Markdown files to WeChat MP, publish to 公众号草稿箱, schedule WeChat articles, or automate public account content delivery.
WeChat official account topic selection assistant — based on trending-list content breakdown + matching to the user's direction, intelligently generates viral topics. Supports fetching trending lists from multiple platforms, content breakdown analysis, direction-match scoring, and outputs 3 curated topics.
Turn the full transcript of a multi-person meeting (such as weekly meeting records exported from DingTalk/Feishu) into the body of a single person's weekly report email. Automatically extracts the specified member's (default 王鑫) "this week's work/this week's progress" and "next week's plan", drafts a "new technology/personal reflections" paragraph based on this week's work (including self-taught new technologies), and outputs a three-paragraph email body with a subject line, ready to copy and send. User invocation: /weekly-report [member name].
בונה אוטומטית סוכן וואטסאפ חכם בעברית עם Kapso (WhatsApp Business), Gemini (LLM + tools), ו-Maton (Google Calendar / Zoom / Gmail / כל אינטגרציה). פורס ל-Vercel, מגדיר webhooks, מסנכרן ENV — בלי שאתה צריך לגעת בקונסול. השתמש בסקיל בכל פעם שמישהו מבקש: "בנה לי בוט וואטסאפ", "סוכן וואטסאפ", "WhatsApp agent", "תקבע פגישות מהוואטסאפ", או רוצה לחבר Kapso + Gemini + Maton יחד.
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
Encyclopedic reference documentation for fictional worlds — wiki pages, character profiles, lore entries. Use when creating or updating reader-facing reference pages. Covers link discipline, citation conventions, and mermaid relationship diagrams. Distinct from the knowledge base, which is author/agent-facing knowledge.
Design and audit win-back, reactivation, churn recovery, cancellation follow-up, dormant-user, lapsed-subscriber, lifecycle offer, and re-engagement campaigns for SaaS, apps, games, marketplaces, and developer tools. Use when trying to recover churned users, reactivate dormant accounts, or build ethical promotion flows with segmentation, offers, messaging, and metrics.
Audit a fixed cohort of inactive WooCommerce pull requests against current trunk, linked issues, review history, repository labels, and representative user flows, then produce evidence-backed actions and a private checklist report. Use for stale or backlog PR cohort reviews, not ordinary single-PR code review.
Create or update a User Story. Use when you need to create, document, update, or standardize user stories. Activate when the user requests a new user story, describes a functional need, asks to refine requirements, structure features, or align existing stories with the project's conventions.
Implement already-specified work in code, of four types: (1) technical tasks (TK-XXX) under a user story; (2) maintenance tasks (WI-XXX) without a story — bugs, refactoring, technical debt, dependencies, operations; (3) test cases (TC-XXX) — automate the tests already documented by test-define; (4) features (FT-XXX) — automate the TCs of their acceptance criteria. Select the type according to the referenced artifact. Only implement work in State: Ready; it also accepts a bounded correction mode, delegated by quality-check, on any artifact of the branch (US-XXX, WI-XXX, FT-XXX, TC-XXX on a test/ branch, or an artifact external to the plugin), to fix a failing check or test. Always activate when the user asks to "implement", "develop", "execute tasks", "code", "automate the tests", "implement the test cases", "work on the TK/WI/TC/FT", or variants implying writing code from an already-drafted specification.
Close and integrate the work of a user story (US-XXX), a maintenance task (WI-XXX), or a test automation (test/ branch on a US-XXX, WI-XXX, or FT-XXX) by merging the branch into the branch it was created from, after verifying that progress.md has all work units in Done and that the closing quality gates pass (quality-check, code-review, and trace-validate). Activate when the user asks to close, deliver, merge, integrate, finish, or submit the work of a story, a WI, a feature, or the current branch.
WorkRally CLI (workrally) — a full-workflow AIGC comic-drama video creation toolkit for AI agents. Supports AI image generation, AI video generation, video prompt optimization, canvas audio/music generation, Hunyuan 3D model generation, AI audio generation, full CRUD for projects/series/scenes/shots, asset library, media asset management, infinite canvas, file upload/download, and more. Use when user asks to generate images, generate videos, generate audio, generate music, generate 3d, optimize video prompts, manage projects, series, shots, upload files, download assets, manage materials, or interact with WorkRally platform via command line.
Eight-stage document-writing host: clarify → analyze sources → explore → review → outline → execute writer → verify → retrospect. In-repo writer: tech-review-doc. External strong deps: humanizer, humanizer-zh. Auto mode never skips tech-review §1. Triggers — 「写文档」「写技术评审」「去AI痕迹」「人性化改写」「自动写文档」「write workflow」「humanize」. Do NOT use for code PDCA (solve-workflow), performance (perf-optimize-workflow), or marketing articles (article-writer).
Writes (generates or updates) AGENTS.md — a token-efficient context file for AI coding agents. Analyzes project stack, constraints, and commands. Produces AGENTS.md and agent-specific imports (CLAUDE.md, .cursorrules, GEMINI.md, etc.). Preserves curated sections on update. Also reviews an existing AGENTS.md read-only (runs the bundled critic; writes nothing). Use when: the user asks to create, update, or review AGENTS.md, CLAUDE.md, or agent context files; or to onboard an AI agent to a project.
ALWAYS LOAD THIS SKILL WHEN WRITING OR EDITING PYTHON CODE. Do not write or modify Python files directly — use this skill first. Core Python standards: basedpyright strict typing, Result-based error handling, async patterns, security, code style.
This skill should be used when a designer is picking up a Task issue to add design coverage. Triggers on phrases like "I want to design task #X", "help me add Figma references to this task", "create a component spec for this feature", "what UI states need design coverage", "scaffold the design reference section", "what components do I need for this task", "which Figma frames cover this ticket", "add design coverage to task #X", "does task #X have design coverage", or "link designs to this task". Handles exploring the design system, deriving UI states from Gherkin scenarios, and writing back a structured Design Reference into the issue.
This skill should be used when a developer is ready to implement a GitHub Task issue and needs to read the full spec hierarchy (Task + Feature + Epic), explore the codebase, produce a concrete Technical Approach with real file paths, and drive TDD implementation against Gherkin scenarios. Triggers on phrases like "implement task #42", "pick up task", "start working on this task", "build the task", "develop task #X", "code up the task", "write the tests for task #X", "start coding this ticket", "resume task #X", "continue task #X", or "I want to implement this ticket".
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.