Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Before finishing any reply to a question about how to use Claude or a Claude product, stop and check this skill. It recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: “how do I,” “how can I,” “getting started with,” “what can Claude do,” “teach me,” “learn to use”; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product—not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial—a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content
Inspect, run, and debug RevOS actions — the operations an integration performs per table row (sync a company to NetSuite, enrich a contact, push a deal to HubSpot) — and their runs, through the RevOS MCP server. Use this whenever something failed, did not sync, or came out wrong (“why didn't this deal reach NetSuite?”, “the sync is red”, “how many deals have a sync error?”, “what does this error mean?”), when the user wants to see which actions exist or what an action column did, wants an action run or re-run for some or all rows, or wants one record synced right now from an id or a link (“sync this deal”, “push this company now”) — even if they never say the word “action”. Read it before the first api_read or api_write on the `action-runs` resource. Syncing a source system into RevOS (“sync HubSpot”, “is our data up to date?”) is the `connections` skill.
Canonical guide to authoring Claude Code agent frontmatter and system prompts. PROACTIVELY activate for: (1) creating a new agent, (2) adding an agent to a plugin, (3) writing agent frontmatter, (4) designing a system prompt, (5) configuring <example> trigger blocks, (6) restricting tools, (7) setting model inherit, (8) migrating deprecated agent true flag, (9) fixing "agent never triggers", (10) ensuring skills have agent trigger coverage. Provides: agent templates, lean-orchestrator pattern, and validation checklist.
Plan and write conversion-grade Amazon A+ Content (formerly called Enhanced Brand Content, renamed in 2019), including Premium A+ tier modules (video, carousel, interactive hotspots, larger comparison chart, Q&A) and the Brand Story carousel that runs across the catalog. Selects the right module layout, writes persuasive module copy, designs the comparison chart, and produces designer-ready image briefs. Use when a user asks to create, plan, improve, or audit A+ Content, Enhanced Brand Content, Premium A+, brand story modules, comparison charts, interactive A+ modules, A+ video, or the visual section below the bullet points on an Amazon listing. Trigger phrases include "A+ content", "EBC", "enhanced brand content", "brand story module", "comparison chart", "below the fold", "premium A+", "brand story", "A+ video", "interactive modules", "premium content". Works with zero tools. the user describes the product and pastes any existing copy.
Optimize a listing for Amazon's AI shopping assistants (Rufus on the web, Alexa+ on devices, and the COSMO ranking layer behind them). Rewrites bullets as question answers, completes the Attributes section, models voice query anatomy, and reinforces with review-language. Use when a user asks about Rufus, Alexa+, AI shopping, AI-driven search, COSMO, conversational shopping, question-style queries, voice shopping, voice search, smart speaker discovery, or conversational query optimization. Trigger phrases. "Rufus", "Alexa+", "AI shopping", "AI search", "COSMO", "conversational query", "question answering", "voice shopping", "Alexa search", "voice query", "smart speaker", "conversational shopping". Works with zero tools.
Run a full competitor analysis for an Amazon product. Compares listings, pricing, images, reviews, ratings, and ad presence against direct competitors, finds the weaknesses to exploit and the strengths to neutralize, and outputs a prioritized attack plan. Use when a user asks to analyze competitors, compare their listing to a rival, find a competitor's weak spots, understand why a competitor outranks them, or plan how to beat a specific ASIN. Trigger phrases: "competitor analysis", "analyze my competition", "beat this competitor", "why is this ASIN ranking", "compare my listing". Works with zero tools. the user pastes competitor listing details and reviews.
Prepare an FBA shipment correctly so it is not rejected, delayed, or charged prep fees at the warehouse. Covers labeling, polybagging, suffocation warnings, bundle and set prep, expiration dating, box weight and dimension limits, and the shipment plan itself. Use when a user asks about FBA prep, shipping inventory to Amazon, labeling units, polybag requirements, prep requirements, a shipment that was rejected, or unplanned prep fees. Trigger phrases: "FBA prep", "ship to Amazon", "FBA labeling", "polybag", "shipment plan", "prep requirements", "shipment rejected". Works with zero tools.
Audit Amazon Payments report for fee errors. Finds incorrect FBA fulfillment fees (wrong size tier), missing referral fee credits on refunds, duplicate charges, and FBA storage discrepancies, and produces an FBA fee-discrepancy case packet per finding. Use when a user asks about Amazon fee errors, overcharged fees, wrong size tier, missing referral refunds, fee audit, or Payments report analysis. Trigger phrases: "fee audit", "overcharged", "wrong fee", "size tier error", "referral fee refund", "payments report", "FBA fee dispute". Works with zero tools. the user pastes Payments report rows.
Remove an Amazon listing hijacker step by step. Walks the test-buy script, evidence package, Brand Registry violation report, cease-and-desist template, and escalation to Amazon's Counterfeit Crimes Unit. Use when a user asks about a hijacker on their listing, an unauthorized seller, removing rogue sellers, counterfeit sellers, Brand Registry violation reports, or CCU. Trigger phrases: "hijacker", "unauthorized seller", "rogue seller", "counterfeit", "remove this seller", "report a violation", "CCU". Works with zero tools. The user describes the listing and the hijacker.
Plan Amazon FBA inventory end to end. Calculates reorder timing and quantity, safety stock, week-by-week days of cover, builds a 12-week PO schedule, applies ASIN-level restock limits and seasonal multipliers, watches the IPI score levers, and surfaces stranded and aged inventory. Use when a user asks about restocking, when to reorder, how much to order, running out of stock, the IPI score, restock limits, ASIN restock limit, days of cover, 90-day forecast, restock schedule, long-term storage fees, aged inventory, or stranded inventory. Trigger phrases. "inventory management", "when to reorder", "restock", "safety stock", "IPI score", "stockout", "aged inventory", "long-term storage", "reorder schedule", "forecast", "days of cover", "ASIN restock limit". Works with zero tools. the user provides sales rate and lead times.
Build a complete Amazon product launch plan. the 30-day runway from go-live to established rank. Sequences the pre-launch checklist, the review ramp, the ad and deal cadence, the price strategy, and the daily and weekly milestones that turn a new listing into a ranking product. Use when a user asks how to launch a product on Amazon, a launch plan, a launch strategy, a launch checklist, a product launch timeline, or how to rank a new product. Trigger phrases: "launch plan", "launch strategy", "how to launch", "product launch", "launch checklist", "launch runway", "rank a new product". Works with zero tools.
Recover a suppressed, blocked, or deactivated Amazon listing. Maps the suppression reason code to the specific fix path and produces the reinstatement message. Use when a user asks about a suppressed listing, a blocked listing, listing deactivated, pricing error suppression, image policy, restricted phrase, or missing required field. Trigger phrases: "suppressed listing", "blocked listing", "listing deactivated", "pricing error", "image suppression", "restricted phrase". Works with zero tools. the user pastes the suppression notice.
Brief and plan Amazon product photography. Builds the photographer brief for the main image and gallery, specifies lighting, angles, props, and styling per shot, and plans the lifestyle and infographic source shots. Use when a user asks about product photography, a photo shoot, photographer brief, lighting setup, studio shots, or how to get photos taken for a listing. Trigger phrases: "product photography", "photo shoot", "photographer brief", "lighting setup", "studio shots", "photograph my product". Works with zero tools. For image strategy and gallery order, pair with amz-listing-images.
Analyze true Amazon profitability per ASIN and across a portfolio. Goes beyond per-unit fees to include advertising, returns, storage, promotions, and hidden fees, and finds where the real money is made and lost. Use when a user asks about profitability, true net profit, which products make money, why profit is lower than expected, portfolio profit analysis, or hidden fees eating margin. Trigger phrases: "profit analysis", "true profit", "net margin", "which products are profitable", "where is my money going", "hidden fees". Works with zero tools. the user pastes revenue, fee, and cost figures.
Parses Amazon Search Term Reports (50K+ rows) into 4 actionable buckets: negative exacts, negative phrases, exact-match harvest, and hero scale terms. Produces a Bulk Operations upload-ready file in minutes instead of the eyeball approach that misses 60% of opportunities. Use when a user mentions STR, PPC bulksheet, or search term analysis. Trigger phrases: "search term report", "STR analysis", "PPC bulksheet", "negative keywords bulk upload", "harvest exact match". Works with zero tools.
Build an Amazon seasonal and Q4 plan. Works backward from peak demand dates to set inventory order timing, ad budget ramps, deal calendar, listing refresh, and the post-peak wind-down. Use when a user asks about seasonal planning, Q4 preparation, Prime Day prep, holiday selling, peak season inventory, or timing a seasonal product. Trigger phrases: "seasonal planning", "Q4 plan", "holiday prep", "prime day prep", "peak season", "seasonal product", "black friday". Works with zero tools.
Plan a Sponsored Brands Video ad. Writes the 30-second script, the hook, the on-screen text, the end-card CTA, and version variants for testing. Use when a user asks about Sponsored Brands Video, SBV, video ad script, video ad creative, or running video ads on Amazon. Trigger phrases: "sponsored brands video", "SBV", "video ad", "video script", "video ad creative". Works with zero tools.
Plan an Amazon Brand Store. designs the page structure, the navigation, the shoppable content, and the traffic plan so the Store works as a real branded destination, not a dead page. Use when a user asks about the Amazon Store, Brand Store, storefront design, store pages, shoppable images, or driving traffic to a store. Trigger phrases: "amazon store", "brand store", "storefront", "store design", "store pages", "shoppable images", "store traffic". Works with zero tools.
Internal sub-procedure (not a standalone entry point) — the shared footage-analysis pipeline that produces audio transcripts, contact sheets, and Sonnet-written summaries. Invoked end-to-end by the process-library and reprocess-with-contact-sheets skills; don't trigger it on its own.
Multi-agent collaborative Android-to-HarmonyOS code migration workflow (iterative). Triggered when the user needs to migrate an Android project to HarmonyOS. Provides: 1) Analyzer Agent scans the code structure 2) Planner Agent draws up the migration plan 3) Translator Agent performs the code conversion 4) **Validator Agent** uses the **ohos-app-build-debug** skill for compile verification, app packaging, and on-device verification of the first screen 5) Tester Agent verifies functionality (run after each module's migration is complete) 6) After all modules are migrated, the Feature Comparator Agent checks for missing functionality 7) UI Comparator Agent verifies UI consistency 8) Feedback of unfinished parts to the Planner Agent for continued iteration. Includes code analysis scripts, API mapping tables, component conversion patterns, and automated verification tools. Trigger keywords: migrate Android to HarmonyOS, Android migration, HarmonyOS migration, Java/Kotlin to ArkTS, Activity to Page, feature comparison, UI comparison.
Animate a tap-through onboarding or web funnel (quiz, survey, web2app flow) so the motion tells the flow's story — each page-to-page hand-off gets its own choreography tied to what the two pages say, the chosen answer physically becomes the progress it earns or the next page's hero, and everything stays fluid, physical and smooth on real phones. Built for flows shipped as Superwall surfaces (the superwall framework: pages, router transitions, layout chrome), with the engine mapped onto the router; the same direction applies to any tap-through web flow. Motion only; no new screens. Use when the user asks to \"animate the onboarding\", \"make the funnel feel premium\", \"add transitions between onboarding pages\", or when a flow's page transitions feel flat, generic, choppy, or cheap.
Use when authoring a feature specification (functional spec) — elaborating the features a PRD names into implementable, testable detail. Guides the METHOD, not the outline: tracing each feature to a PRD goal; specifying observable behavior (use-case flows, EARS); enumerating I/O, a state-transition table, and decision tables for combinatorial rules; covering edge cases + errors with their handling; writing testable Given/When/Then (or metric-threshold, for probabilistic/ML) acceptance criteria; applying a per-feature non-functional-requirement taxonomy keyed to the feature archetype (UI/API/data-ML/batch/integration/CLI); and amending an approved spec as a versioned, ripple-analyzed delta — to a bar an engineer can build and a tester can verify each feature from. Composes with a feature-spec template tool + a deep-research capability. Assumes the approved PRD as upstream input — never a blank page. Not for authoring the PRD, reviewing a finished feature spec, or engineering design docs (ADR/RFC).
This skill converts manual test cases into production-ready automated test scripts. It analyzes the existing automation framework, interprets manual test steps, and generates maintainable tests following automation best practices. Use this skill whenever the user wants to automate manual test cases, expand test coverage, or create end-to-end automated flows from existing test documentation.
Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via skill-creator + unslop, optionally pulling fresh evidence from recent threads
Exact-name Codex/OMX-compatible $autopilot front door for autonomous idea-to-verified-code work. Use when the user invokes $autopilot, autopilot, auto pilot, full-auto, or asks for an end-to-end build; route small focused edits to direct implementation and stricter spec-first loops to ooo or ralph.
Use when one validated cohort analysis must be repeated across many exposure/outcome pairs. Generates one R/Python script per combination from a single methodology template, changing only the variables, and aggregates the results into a summary matrix.
Use when defining `#[derive(Component)]`, declaring required components with `#[require(...)]`, writing observers with `On<E>` or lifecycle observers with `On<Add<T>>` (NOT `On<Add, T>`), choosing Table versus SparseSet storage, or registering `on_add`/`on_insert`/`on_discard`/`on_remove` hooks in Bevy 0.20
Ultra-compressed communication mode. Cuts token usage by about 75% by speaking like a caveman while preserving full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when the user says “caveman mode,” “talk like caveman,” “use caveman,” “less tokens,” “be brief,” or invokes /caveman. Also auto-triggers when token efficiency is requested.
Performs advanced CLI operations, structured data transformation, and Unix forensics with modern Rust-powered tools. Use when searching codebases with ripgrep, transforming JSON or YAML with jq, refactoring across files with sed and fd, debugging APIs with httpie, or navigating directories with zoxide.
Covers deploying Next.js apps (App Router and Pages Router) to Cloudflare Workers with the OpenNext adapter @opennextjs/cloudflare: scaffolding new projects via create-cloudflare, migrating existing apps, wrangler.jsonc and open-next.config.ts setup, the nodejs_compat flag and compatibility_date, the dual next dev plus opennextjs-cloudflare preview workflow, deployment, image optimization, caching, and bindings for D1, R2, KV and Workers AI. Use when running SSR, ISR, server components, server actions or middleware on Workers, moving a Next.js app from Vercel or AWS to Cloudflare, or hitting errors such as worker size limit exceeded (3 MiB free, 10 MiB paid), FinalizationRegistry is not defined, Cannot perform I/O on behalf of a different request, Turbopack chunk load failures, request-scoped database connection problems, or the CVE-2025-6087 SSRF vulnerability.
End-to-end cold email outreach orchestration. Handles goal alignment, lead selection from Supabase, sequence design, email generation (via email-drafting), campaign setup in the user's chosen outreach tool, and logging. Tool-agnostic — supports Smartlead (default), Instantly, Lemlist, Apollo, or manual CSV export.
When the user wants to write cold outbound emails, craft prospecting email copy, build follow-up sequences, or fix emails that aren't getting replies. Also use when the user says 'write a cold email,' 'prospecting email,' 'outbound email copy,' 'follow-up email,' 'outreach email,' 'sales email,' 'cold outreach,' 'email sequence,' 'write me an email to a prospect,' 'my emails aren't getting replies,' or 'help me fix my cold email.' For multi-channel sequence design, see outbound-sequence. For LinkedIn messaging, see linkedin-outreach. For account research before writing, see lead-research.
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.
