Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Read metadata, DOM, screenshots, and structured page payloads from an attached Chrome or Chromium tab through the local Agent Browser Relay extension. Use when Codex needs relay preflight or troubleshooting, popup attach guidance, lease-scoped concurrent tab reads, or new background tab creation through the relay without direct browser automation.
Alibaba Cloud PAI Workspace Management Skill. Create, query, and list workspaces on the Platform for AI (PAI). Triggers: "create PAI workspace", "query PAI workspace", "list workspaces", "PAI workspace", "create workspace", "get workspace", "list workspaces", "AIWorkSpace CreateWorkspace", "AIWorkSpace GetWorkspace", "AIWorkSpace ListWorkspaces"
Edit videos with Alibaba Cloud ICE using URL or OSS inputs and cloud-rendered outputs. Use for Timeline editing, normal-template creation and rendering, multi-clip composition, titles, subtitles, transitions, audio mixing, translation or localization, and single-media intelligent-production jobs such as smart covers, erasure, caption extraction, matting, beauty, reframing, and audio processing. Also inspect templates and verify output URLs. Content analysis such as labels, highlight candidates, speaker attribution, and transcripts must be supplied upstream. Never use local ffmpeg to generate, convert, or extract media; it is limited to streamed audio analysis.
Use for fastboot operations, flashing partitions, bootloader unlocking, recovery mode, or partition management. Triggers on "fastboot", "flash boot.img", "unlock bootloader", "recovery mode", "TWRP", "Magisk", "partition", "sideload", "A/B slots". WARNING - These operations can brick devices if done incorrectly.
Validate that an Antithesis property catalog can actually catch bugs. For each safety property, inject one realistic mutant into the SUT, run it, and confirm the targeted property fires. Diagnoses survivors as a bad mutant, bad oracle, bad workload, or bad property, and routes fixes back to antithesis-workload or antithesis-research. Use once the harness is built and a baseline run is green.
Review architecture across 7 dimensions (structural, scalability, enterprise readiness, performance, security, ops, data) and provide scored reports. Triggers on: “review architecture,” “critique design,” “audit system,” “assess scalability,” “enterprise readiness,” or “technical due diligence.” Not for diagrams; use architecture-diagram. Not for interactively finding shallow modules or designing one module's interface and seam; use module-deepening.
Use this skill to run an end-to-end Jetpack Compose performance audit when the symptom is broad ("the app feels sluggish", "scroll is rough everywhere", "we're starting a perf sprint", "what should we fix first?"). Orchestrates the four-phase Measure → Diagnose → Fix → Verify loop by sequencing the 25 focused skills (release-mode setup, R8, Baseline Profiles, Compose Compiler reports, stability inference, Layout Inspector, `@TraceRecomposition`, stabilization, strong skipping, phase-deferral, derivedStateOf, lazy layouts, lazy prefetch, Modifier.Node, modifier ordering, flow collection, effects, CI gates, hot-reload) and produces a written audit report with Before/After Macrobenchmark numbers. Use when the developer wants a perf sprint kickoff, a pre-release perf gate, onboarding to a perf-troubled codebase, or a written deliverable. Use when the user mentions "audit", "perf review", "perf sprint", "where do I start", or has no specific symptom yet.
Expert knowledge for Azure Elastic SAN development, including troubleshooting, best practices, decision making, architecture and design patterns, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use when creating Elastic SAN volumes, iSCSI clients, AVS datastores, AKS storage, or clustered SQL/FCI workloads, and for other Azure Elastic SAN development tasks. Not for Azure Blob Storage (use azure-blob-storage), Azure Files (use azure-files), Azure NetApp Files (use azure-netapp-files), or Azure Managed Lustre (use azure-managed-lustre).
Expert knowledge for Azure IoT Central development, including troubleshooting, best practices, decision making, architecture and design patterns, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use when designing device templates, data exports, IoT Edge gateways, REST/CLI automation, or IoT Central migrations, and for other Azure IoT Central development tasks. Not for Azure IoT Hub (use azure-iot-hub), Azure IoT (use azure-iot), Azure IoT Edge (use azure-iot-edge), or Azure IoT Operations (use azure-iot-operations).
Expert knowledge for Azure Lighthouse development including decision making, security, configuration, integrations & coding patterns, and deployment. Use when configuring Lighthouse delegations, AOBO/PIM access, Arc/Sentinel integrations, policies/remediation, or Marketplace offers, and other Azure Lighthouse related development tasks. Not for Azure Arc (use azure-arc), Azure Managed Applications (use azure-managed-applications), Azure Resource Manager (use azure-resource-manager), Azure Role-based access control (use azure-rbac).
Expert knowledge for Azure Notification Hubs development, including troubleshooting, best practices, decision-making, architecture and design patterns, limits and quotas, security, configuration, integration and coding patterns, and deployment. Use when sending FCM/APNS/WNS pushes, using tags/templates, managing tiers, configuring IaC, or accessing Private Link, and for other Azure Notification Hubs development tasks. Not for Azure Event Hubs (use azure-event-hubs), Azure Service Bus (use azure-service-bus), Azure SignalR Service (use azure-signalr-service), or Azure Web PubSub (use azure-web-pubsub).
Expert knowledge for Azure AI Personalizer development, including troubleshooting, decision making, security, configuration, integrations, and coding patterns. Use when choosing single- vs. multi-slot setups, tuning policies or exploration, using apprentice mode, explainability, or local inference, and for other Azure AI Personalizer development tasks. Not for Azure AI Search (use azure-cognitive-search), Azure Machine Learning (use azure-machine-learning), Azure AI Metrics Advisor (use azure-metrics-advisor), or Azure AI Anomaly Detector (use azure-anomaly-detector).
Azure SQL Database optimization and platform-specific features. PROACTIVELY activate for: (1) Azure SQL Database optimization, (2) DTU vs vCore selection and right-sizing, (3) automatic tuning (force last good plan, create/drop index), (4) Hyperscale tier and read replicas, (5) Serverless tier and auto-pause, (6) Azure SQL performance monitoring (Query Performance Insight, Intelligent Insights), (7) elastic pools, (8) Always Encrypted with secure enclaves, (9) Managed Instance vs Azure SQL DB tradeoffs, (10) failover groups and geo-replication. Provides: tier-selection matrix, automatic-tuning enablement steps, Hyperscale architecture overview, monitoring queries, and elastic pool sizing guidance
Declare a skrub DataOps graph from the data source to the predictor after framing is locked. Stateless steps use `.skb.apply_func`. Stateful steps use `.skb.apply`. After the graph exists, attach the locked splitter and any non-default score. No fit, tune, persistence, or `skore.evaluate`. TRIGGER when writing or editing any link from data source to predictor (loaders, preprocessing, features, composition, the final estimator), including a pure-Python function on that path, a step added or reordered, a bare `sklearn.Pipeline` as the top-level, or a request to build a pipeline, classifier, or regressor. HOW TO USE: before the first declarative line and on every structural edit. Read the stops and emit Pre-flight before code. Confirm new names with `python -m skore_skills api get`.
Analyze SQA requirement inputs into five structured fields plus a display summary, and archive a Requirement to CawPlan QA Insights. Use when: the user explicitly asks to analyze requirements, structure requirement fields, produce a five-field draft with display summary and open-questions list, recommend a QA module-tree node, archive a Requirement, or update an existing Requirement in QA Insights — including an existing Test Suite Link/display_id, or a ticket link/ID together with requirement-analysis intent (e.g. "需求分析", "analyze this ticket", screenshots + ticket). Do not auto-select when the message is only a bare CawPlan issue URL with no requirement-analysis wording; prefer `cawplan-ticket-context` for coding-session ticket loading. NOT for: loading a ticket into the coding session only, writing or editing code, uploading AI daily reports, creating tickets, or generating test points.
Generate test-point coverage outlines from an archived CawPlan Requirement (its requirement Markdown), with an open-questions list, and batch-archive test points after SQA confirmation. Use when: an archived Requirement needs test points or a coverage outline; cold handoff (Test Suite Link, display_id, or id); hot handoff after A1 archive ("generate test points for this requirement"); incremental test-point supplements on an existing Requirement. NOT for: structuring or archiving Requirements (use `cawplan-requirement-analyze`); expanding test points into step-by-step cases or Excel (A3); viewing or editing archived test points or review in Test Suites (use the web UI); unarchived five-field drafts only (archive via A1 first).
Use the ClawdHub CLI to search, install, update, and publish agent skills from clawdhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawdhub CLI.
Deploy MISP, configure threat feeds (MISP community, freetext, TAXII, CSV), and use the PyMISP API to programmatically fetch, add, and search events and IOCs, building automated collection pipelines that aggregate indicators from community and commercial sources. Use when gathering, storing, or correlating IOCs and threat intelligence, or when scripting MISP ingestion via PyMISP.
Design and execute a social engineering penetration test combining OSINT-driven target profiling with phishing, vishing, smishing, and physical pretexting campaigns using tools like GoPhish, the Social Engineer Toolkit (SET), and Evilginx to measure human security resilience. Use when scoping or running an authorized human-attack-surface test and reporting results to identify security awareness training gaps.
Contract review skill that adds comment-based issue annotations without changing original text. Enforces a four-layer review (entity verification, basic, business, legal), writes structured comments (issue type, risk reason, revision suggestion) with risk level encoded via reviewer name, and generates a contract summary, consolidated opinion, and Mermaid business flowchart (with rendered image). Output language must follow the contract’s language
Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for /correct.
Data-story videos where an animated chart carries the argument - lines that draw as time passes, bars that grow, a big counter that ticks, axes that rescale when the data surprises, annotation pins on the key moments - rendered to MP4 at 9:16 or 16:9 with HyperFrames, SVG and GSAP. Use whenever someone wants to animate statistics, show a trend, growth or cost over time, compare numbers, break down a figure (salary, budget, benchmark), or turn a dataset or table into a short narrated video. Not for architecture or request flows (use system-diagram-animation) or text-only videos (use kinetic-typography).
Use this skill when conducting comprehensive research on any topic using the OpenAI Deep Research API. It automates prompt enhancement through interactive clarifying questions, saves research parameters, and executes deep research with web search capabilities. Use when the user asks for in-depth analysis, investigation, research summaries, or topic exploration.
Convert raw Kibana release notes tool output into Stack release notes (Elastic Observability or Elastic Security) using GitHub PR context and prior release notes. Use when drafting or editing Stack 9.x release notes from the Kibana release notes generator output.
Convert raw Markdown tool output into Elastic Cloud Serverless changelog format using GitHub PR context and prior Serverless release notes. Use when drafting or editing Serverless changelog entries from release notes generator output.
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. Use when Claude needs to work with professional documents (.docx files), including creating new documents, modifying content, working with tracked changes, or adding comments.
Use when the user wants to iterate on an existing generated Power Apps mobile app after /create-mobile-app: update Application Insights configuration, the plan, data model, native capabilities, design, screens, generated app code, and preview without restarting the full project flow. Natural-language triggers include 'the app already exists', 'edit my app', 'change this screen', and 'add a feature to this app'.
Design distinctive, on-brand emails — newsletters, campaigns, welcome series, promo, post-purchase, win-back, transactional, announcements. Use when the user wants to draft, write, compose, design, redesign, critique, polish, or improve an email; or send a campaign / blast / broadcast through any ESP (Nitrosend, Klaviyo, Mailchimp, ActiveCampaign, etc.). Produces a structured design brief and translates it into the sending tool's section format. Bakes in anti-slop principles: own a colour, restrained palettes, real imagery with sourced or prompted image slots, distinctive voice, no category-reflex aesthetics, no orphan whitespace, single column ≤600px, mobile-first, real footers (verified mission only, plus socials + address + unsubscribe). Asks at most three questions to fill brand gaps; otherwise infers from connected ESP account settings or a project brand file. Self-contained — no other skills required. Skip for pure strategy, deliverability, copy-only, or platform-selection questions.
Use this skill when the user asks to “learn ethical hacking,” “understand penetration testing lifecycle,” “perform reconnaissance,” “conduct security scanning,” “exploit vulnerabilities,” or “write penetration test reports.” It provides comprehensive ethical hacking methodology and techniques
Create FAIR-minded reproducibility bundles for materials simulations by collecting input/output file inventories, hashes, units, engine versions, structure identifiers, provenance, and NOMAD/OPTIMADE/Materials Project friendly metadata. Use before publishing, sharing, archiving, or handing simulation results to another agent
Manage Flare error tracking and performance monitoring using the flare CLI. Use when the user wants to list, triage, resolve, snooze, or debug errors; manage projects; create projects and retrieve API keys; check error counts; investigate slow routes, queries, jobs, or commands; view aggregated performance data and traces; or interact with flareapp.io from the command line.
Production-grade animation patterns for React and Next.js using Motion (formerly Framer Motion). Use this skill whenever the user asks to animate components, add transitions, create scroll-triggered effects, implement page transitions, layout animations, gesture interactions, or any kind of motion/animation in a React or Next.js project. Also trigger when code imports 'framer-motion', 'motion/react', or 'motion/react-client', or when the user mentions: animation, transition, fade-in, slide, parallax, scroll animation, exit animation, AnimatePresence, motion.div, spring, gesture, drag, hover animation, stagger, whileInView, or layout animation.
Coin comparison. Use this skill whenever the user asks to compare two or more coins. Trigger phrases include: compare, versus, vs, which is better, difference. MCP tools: info_marketsnapshot_get_market_snapshot, info_coin_get_coin_info per coin (or batch/search when available)
Use this skill to generate and measure Jetpack Compose Baseline Profiles end-to-end with the AGP 8.2+ Baseline Profile Generator module and the Macrobenchmark harness. Covers writing the `BaselineProfileRule` journey for cold startup plus first-scroll, generating `baseline-prof.txt`, verifying it shipped at `assets/dexopt/baseline.prof`, measuring with `MacrobenchmarkRule` under `CompilationMode.Partial(BaselineProfileMode.Require)`, and emitting accurate time-to-fully-drawn via `ReportDrawn` / `ReportDrawnWhen` / `ReportDrawnAfter` from `androidx.activity.compose`. Compose ships unbundled, so every Compose UI app benefits — cited gains around 30% faster startup and 40% smoother first-scroll. Use when the user mentions "baseline profile", "macrobenchmark", "slow cold startup", "first-scroll jank", "StartupTimingMetric", "FrameTimingMetric", "ReportDrawn", "TTFD", or preparing a release build for performance measurement.
Control a real iPhone connected to this Mac with the ghosthand CLI: screenshots and on-device OCR over USB, taps, swipes, scroll, keys and typing over Bluetooth, and files, photos, apps, battery and logs over USB. Use it to open apps, read messages, reply, fill forms, get photos or files off the iPhone, or do any task on the user's iPhone. ALWAYS load this skill when the user mentions ghosthand, their iPhone or phone, or asks to do something on a phone app (Messages, WhatsApp, Instagram, TikTok, Settings, App Store).
Use this skill when naming or renaming a GitHub repository, product, CLI, plugin, skill pack, framework, app, or public developer project. It reverse-engineers association-based open-source naming patterns and produces product name, repo slug, tagline, About description, topics, rejected names, and README hero copy.
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.