Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Reviews sales calls, extract coaching insights, and score against MEDDPICC/SPIN/Challenger. Use when a rep lost a deal and you want to understand why, call went sideways and need to debrief, not sure if rep is qualifying properly, need to pull action items from a recorded call, rep talking too much and not listening, or need to give structured feedback on a call. Do NOT use for deal-level risk analysis (use /sales-deal-inspect).
Scans container images, filesystems, and SBOMs for known CVEs with Anchore Grype, matching Syft-generated SBOM packages against NVD, GitHub Advisories, and OS-specific feeds with configurable severity thresholds and failure gates. Use when Grype or Syft is the chosen toolchain, when scanning an existing SBOM rather than an image, or when gating a build on severity. Keywords: Grype, Syft, SBOM, NVD, GitHub Advisory, --fail-on, severity threshold. Do not use when the toolchain is Trivy - use scanning-docker-images-with-trivy.
Designing scientific schematics, diagrams, and graphical abstracts. Covers tool selection (BioRender, Inkscape, Affinity, PowerPoint), design principles for pathway diagrams, mechanism schematics, experimental workflows, and journal graphical abstracts. Includes composition, icon sourcing, color for biological entities, and accessibility. Use when creating illustrative (not data-driven) scientific figures.
Autonomous web research agent — takes a research question, uses ScraperAPI to discover and scrape relevant sources, uploads content as file artifacts to the Anthropic Files API, then feeds everything to Claude for synthesis into a cited research report. All in one flow. Use when user asks: "research X for me and give me a cited report", "investigate Y online and summarize what you find", "do a deep dive on Z using real web sources", "find information about X across multiple websites and cite your sources", "run the scraperapi research agent on this topic". Produces a structured markdown report with inline citations and a numbered source list. Invoke whenever the user wants multi-source web research that requires scraping real pages, not just answering from memory. Note: Transmits user-supplied queries, URLs, and content to ScraperAPI; uploads scraped content to the Anthropic Files API.
Use to verify or create a Queue on a Salesforce org for a routable sObject (Case | Incident | MessagingSession | VoiceCall), discovered via its QueueSobject binding rather than by hardcoded name. Reuses whatever queue already routes the target sObject; with --create-if-missing it creates a Queue via the Metadata API (Group + QueueSobject) when none is bound and aligns its QueueRoutingConfigId to a caller-specified QRC. Returns created, reused, updated, or blocked. Triggers: verify or create a queue for Case/Incident/Messaging/Voice routing, align queue routing config, set up an Omni voice queue. Do not use to add users to the queue (service-omni-queue-members-assign) or for sObjects outside Case/Incident/MessagingSession/VoiceCall.
Use to deploy an Omni-Channel routing Flow for Case or VoiceCall and verify it routes work items to a queue or by skill. Supports the Case and VoiceCall steel thread with an autolaunched dryRun-gated variant and record-triggered QueueBased and SkillsBased variants. --trigger deploys a record-triggered variant; --routing-type SkillsBased evaluates WorkSkillRouting rules with a non-null skillOption; --runtime-proof checks routing evidence and, for SkillsBased, SkillRequirement rows. Triggers: deploy Omni routing flow for Case, deploy Omni routing flow for VoiceCall, wire VoiceCall routing, create a record-triggered Omni routing flow, verify a Case routing flow, deploy skills-based routing flow. Do not use for screen flows, platform-event-triggered flows, or Flow Tests.
Service worker lifecycle, caching strategies, background sync, push notifications, and static routing for progressive web apps. Covers Workbox v7.4 strategies (CacheFirst, NetworkFirst, StaleWhileRevalidate), workbox-precaching for app shells, Background Sync API with cross-browser fallbacks, Push API with VAPID keys, and the Service Worker Static Routing API (Chrome 123+). Use when registering service workers, implementing offline caching, configuring background sync, adding push notifications, optimizing fetch handling with static routes, or integrating service workers with local-first sync engines.
Diagnose and fix performance problems in Shiny for R apps — slow startup, sluggish interactions, long-running blocking operations, and apps that struggle beyond a handful of concurrent users. Use when a Shiny app is slow, hangs, recomputes too much, times out, or needs to support more users; when the user asks to "speed up", "optimize", or "make faster" an existing Shiny app; or when preparing a prototyped app for real-world traffic.
Pre-consultation diagnostic questionnaire for clients building websites with AI tools (Claude, Codex, Cursor, Bolt, v0, etc.) who have concerns about quality, design, or maintainability. Collects structured answers about their project, tools, pain points, and goals, then generates a consultation brief. Use when preparing for a website review consultation, when a client asks for a site audit, or when someone says their AI-built site has problems. Supports Russian and English — asks the client to choose language first.
Canonical guide to authoring SKILL.md files for Claude Code plugin skills. PROACTIVELY activate for: (1) creating a new skill, (2) adding a skill to a plugin, (3) writing SKILL.md frontmatter, (4) fixing skills that never trigger, (5) organizing core vs references vs examples, (6) improving weak skill descriptions, (7) progressive disclosure design, (8) splitting oversized SKILL.md files, (9) imperative body style, (10) zero-frontmatter SKILL.md files, (11) removing boilerplate from YAML descriptions. Provides: skill template, trigger checklist, size rules, and validation process.
SRT subtitle-driven HyperFrames + GSAP generation of Editorial-style videos. Use this skill when the user says "create an Editorial animation based on an SRT subtitle file" or says "make an Editorial video" and provides an SRT subtitle file
Institution ratings, consensus price targets, EPS/revenue forecasts, finance calendar, shareholder data, fund holders, insider trades (SEC Form 4), short interest, industry rankings, peer group analysis via the stock data provider. Frameworks: investment proposals, coverage initiation, stock research, competitive analysis, financial planning, and DeFi/on-chain analysis. Triggers: "机构评级", "目标价", "一致预期", "EPS预测", "内部人交易", "空头", "行业排名", "投资提案", "首次覆盖", "竞争格局", "财务规划", "DeFi收益", "链上数据", "機構評級", "目標價", "一致預期", "內部人交易", "空頭", "投資提案", "首次覆蓋", "競爭格局", "鏈上數據", "analyst rating", "price target", "consensus", "insider trades", "short interest", "coverage initiation", "DeFi yield", "on-chain", "earnings calendar", "finance calendar", "财报日历", "下周谁财报", "下周财报", "下周有哪些财报", "哪些财报", "谁财报", "FOMC", "非农", "股东", "谁持有", "股東", "基金持仓", "基金持倉", "機構評級", "目標價", "財務規劃"
Apply StyleKit visual styles and public assets when building, restyling, or reviewing UI. Use for named StyleKit styles, visual direction, mobile interface patterns, and component-library selection; preserve the target platform and existing product behavior.
Personalized audit that teaches advanced Superset features the user isn't using yet — automations, parallel agents, tasks, multi-host, terminals, custom commands, MCP. Use when the user wants to get more out of Superset, learn advanced Superset features, or 10x their Superset workflow.
Svelte 5 lifecycle, stores, context and testing skill. Use when the user needs to use onMount/onDestroy/tick lifecycle hooks in Svelte 5, manage state with writable/derived stores, share component-tree state with createContext, or write Vitest/Storybook/Playwright tests.
Trove collection and normalization for swain-design artifacts. Collects sources from the web, local files, and media (video/audio), normalizes them to markdown, and caches them in reusable troves. Use when researching a topic for a spike, ADR, vision, or any artifact that needs structured research. Also use to refresh stale troves or extend existing ones with new sources. Triggers on: 'research X', 'gather sources for', 'compile research on', 'search for sources about', 'refresh the trove', 'find existing research on X', or when swain-design needs research inputs for a spike or ADR.
Use this skill when a user asks how to generate, integrate, or implement a Word‑like document editor in Angular using Syncfusion. Trigger it for requests involving the Syncfusion Angular Document Editor, Angular‑based editor integration, document editing and formatting, comments and track changes, working with tables and images, managing headers and footers, applying document protection, and building end‑to‑end document workflows in Angular applications.
Tailwind CSS v4 usage guide and v3-to-v4 differences. This skill should be used when writing, reviewing, or refactoring any Tailwind CSS code in this repo. Triggers on tasks involving Tailwind classes, @theme blocks, CSS-first configuration, or cleanup of v3-era syntax.
Produces phased task boards from feature requests: dependency-mapped work items, parallelization flags, risk flags, edge cases, test matrices. Triggers on: "decompose this feature", "task breakdown with dependencies", "phased implementation plan", "work breakdown structure". NOT for discovering which decisions are still open, use decision-map. NOT for effort estimates, use estimate-calibrator.
Generate technical architecture diagrams, pipeline flows, layer/stack diagrams, and system illustrations as standalone HTML files. Uses a dark-mode design system with embedded CSS and inline SVG. Use when the user needs architecture diagrams, system illustrations, flow charts, or technical visualizations.
Use meitu-cli to edit and modify existing React/TSX/JSX source code, with multi-round iteration. Triggered when the user mentions changing code, modifying pages, adjusting styles, changing colors, adding buttons, deleting components, changing layouts, or editing the code from just now.
Add accessible animated AI loading and agent-status indicators with the React thinking-orbs library. Use when a chat, copilot, voice, search, generation, or tool-running interface needs a semantic working, searching, solving, listening, composing, or shaping state; when replacing a generic spinner with an AI activity orb; or when implementing the library's size, theme, speed, pause, reduced-motion, and canvas behavior.
Genome-ASSEMBLY discovery, QC, and replicon mapping for any organism (bacteria, archaea, fungi, and beyond) using NCBI Datasets. Resolves an organism name or taxid to assemblies, picks the reference/representative or best-quality assembly, pulls assembly QC metrics (total length, contig/scaffold N50, contig count, GC%, assembly level, RefSeq category), enumerates chromosomes and plasmids via per-replicon sequence reports, and compares candidate assemblies on quality. Use for "what genomes are available for [organism]", "assembly stats / N50 / GC content for [GCF_/GCA_ accession]", "how many plasmids does [strain] have", "compare assemblies for [species]", "find the reference genome for [taxon]", "is this assembly Complete Genome or just contigs". NOT for gene-level orthology/synteny (use tooluniverse-comparative-genomics), plant gene structure (use tooluniverse-plant-genomics), de novo assembly from raw reads (no tool exists), or taxonomy-only name/lineage lookups.
Find the real protein target(s) of a peptide from its sequence — peptide target deorphanization / off-target identification, for ANY target class (GPCR, ion channel, protease, cytokine/growth-factor receptor, enzyme, integrin), not only GPCRs. Use when a peptide has a phenotype but does not bind its hypothesized target, when a peptide binds a target in one species or assay but not another, or to screen candidate targets for an orphan peptide. A target-class router steers a multi-route keyless pipeline (PROSITE/ELM motif, BLAST homology, HGNC/InterPro/GPCRdb/GtoPdb target-family enumeration, OpenTargets phenotype anchor, EnsemblCompara/Alliance cross-species reconciliation) plus optional NVIDIA-NIM co-folding (Boltz2, AlphaFold2-Multimer, OpenFold3) for structural confirmation.
Build a complete typographic system -- modular or fluid type scale, line-height and tracking per size, weight roles, and vertical rhythm -- exported as tokens, Tailwind config, and CSS. Pairs with font-pairing-suggester (which picks the fonts; this builds the system they live in).
Extract a DDD-style ubiquitous language glossary from the current conversation, flag ambiguities, and propose canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when the user wants to define business terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model", "DDD", "glossaire" or "langage ubiquitaire".
Use this skill when running SEO audits, optimizing for AI search engines (AI Overviews, ChatGPT, Perplexity), generating schema markup, diagnosing traffic drops, fixing Core Web Vitals, managing site migrations, or building keyword strategies. Runs scored full-site audits (0-100 Health Score) across 21 modules including technical SEO, E-E-A-T, hreflang, and programmatic SEO. Three modes: Audit, Plan, Execute. NOT for PPC/Ads, social media management, or generic marketing strategy unrelated to organic search.
A comprehensive skill for integrating and using uCharts with UniApp projects. This skill focuses on UniApp-specific integration, configuration, and platform-specific considerations when using uCharts in UniApp applications. Use this skill whenever the user needs to integrate uCharts into UniApp projects, configure UniApp-specific settings, or handle platform differences.
Upgrade Datadog Browser SDK from v5 to v6. Use when encountering removed options like useCrossSiteSessionCookie, sendLogsAfterSessionExpiration, or when dropping IE11 support, or when a project references datadoghq-browser-agent.com CDN with /v5/ paths.
Design or critique an activity feed / stream — a scannable list of updates where what matters stands out and noise fades. Gates the feed-type choice (chronological vs. algorithmic/ranked) and levers like notification aggregation, follow recommendations, and per-entry controls, while applying the always-true core (curated entries, legible text, relative timestamps, no empty feed, visible refresh status). Trigger when the user asks to design or review an activity feed, news/social feed, activity stream, notifications feed, or timeline.
Design or critique an offboarding flow — canceling a subscription, unsubscribing, or deleting an account. Leads with the ethical stance (leaving must be easy and respectful — hiding the exit is a dark pattern), applies the always-true core (findable exit, preserve goodwill, prevent accidental destruction, explain consequences, ask feedback respectfully, offer genuine alternatives, close with a recovery path) and gates the retention levers (incentive offers, value reminders, confirmation friction, pause-vs-delete) with trade-offs so they don't tip into manipulation. Trigger when the user asks to design or review a cancel/unsubscribe/delete-account flow, a subscription cancellation, a churn/retention exit flow, or an account-deletion or deactivation experience.
Turn a video, tutorial, playlist, or course into an installed, evidence-grounded course Skill that can teach, give practice and feedback, apply demonstrated methods, and answer reference questions. Use when the user provides video sources and wants reusable learning or operational capability.
Use when the user wants to deploy a local directory or GitHub repository to Volcengine and needs the project analyzed, the app shape understood, and a ranked recommendation across ECS, VKE, and veFaaS before choosing an execution path. Also trigger when the user asks "what deploy mode should I use", "is this repo ready for Volcengine", or "check my repo before deploying". This skill prepares the decision; `volcengine-deploy` skill performs the chosen deployment, and `volcengine-iac` skill is used only when the user chooses Terraform/IaC or the task already has an IaC workflow.
Use when building, porting, or refactoring a Vue 3 feature that spans multiple components and layers: a page/view plus presentational components, composables, data access, a router route and shared utilities. Covers the view-orchestrates / components-present split, feature folders with a barrel (index.ts), data loading in composables, resetting shared state, router wiring and the build sequence. Triggers on building a new screen/view/feature, splitting a large `.vue` into smaller components, adding a data model/service, and wiring a router route. Single component's internals: `code-style`; Flux UI library: `flux-ui`.
A user-empowering data visualization Vue 3 components library (69 components) for eloquent data storytelling. ALWAYS use when writing code importing "vue-data-ui". Consult for component choice, config, theming, slots, tooltips, exports, SSR, debugging, or modifying vue-data-ui, vue data ui.
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.
