Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Builds an editable .xlsx travel workbook (bookings, daily plan, options, prep, pack and buy lists, sources) from messy trip inputs such as PDFs, screenshots or booking notes. Not for prose itineraries, recommendation chat or calendar-only scheduling.
Analyze Taiwan-listed stocks using fundamental analysis including EPS, P/E ratio, dividend yield, and financial statement review. Use this skill when the user needs to evaluate a Taiwan stock, compare TWSE/TPEx-listed companies, assess valuation, or review earnings — even if they say 'should I buy this stock', 'analyze 台積電', 'is this stock overvalued', or 'compare these two Taiwan companies'.
Guides CockroachDB version upgrades with tier-appropriate procedures. Self-Hosted covers manual rolling binary replacement with finalization control. Advanced/BYOC covers Console-initiated major upgrades, maintenance windows for patches, and release channel selection. Standard and Basic upgrades are fully automatic with no customer action required. Use when planning, executing, or monitoring a version upgrade.
Validates hook, skill, and agent counts are consistent across CLAUDE.md, hooks.json, manifests, and source directories. Use when counts may be stale after adding or removing components, before releases, or when CLAUDE.md Project Overview looks wrong.
Increase how valuable an offer feels without increasing cost. Use when the offer is good but not converting, price feels too high, or users don't understand the value instantly. Upgrades naming, packaging, framing, value stacking, anchoring, and contrast to improve perceived value — outputs VALUE_PERCEPTION.md.
Add audio to existing videos with meitu-cli: add BGM, add narration dubbing, or BGM + narration in sequence. Triggered when the user mentions adding background music, adding BGM, changing background music, adding narration, adding dubbing, adding a voiceover commentary, adding voice-over, dubbing and music, or adding audio to a video.
Use meitu-cli to increase video frame rate and interpolate frames (e.g. 24fps → 60fps), making motion in low-frame-rate videos smoother. Triggers when the user mentions frame interpolation, adding frames, raising the frame rate, upconverting the frame rate, 60 frames, 120 frames, smoothness, insufficient frame rate, or video stuttering.
Use meitu-cli to concatenate multiple video clips in sequence, supporting plain concatenation that keeps the original audio or concatenation + background music (automatic lookup / custom music URL). Triggered when the user says concatenate videos, merge videos, video compilation, or concatenate with music.
Deploy a local project directory or Git repository to Volcengine as a running, reachable cloud service. USE WHEN: deploy to Volcengine, deploy to 火山引擎/火山, deploy this repo/project, publish current code, launch the app, run it in the cloud, expose it as a service, deploy to ECS/VKE/veFaaS, run on ECS, push to VKE, deploy as serverless/FaaS, or the user wants the agent to choose a Volcengine hosting target. If the user only asks which Volcengine deployment target to choose, use `volcengine-prepare` skill first. Not for creating a single standalone resource — use `volcengine-cli` skill for that.
Apply when creating or modifying manifest.json, service.json, or node/package.json in a VTEX IO app. Covers builders (node, react, graphql, admin, pixel, messages, store), policy declarations, dependencies, peerDependencies, and app lifecycle management. Use for scaffolding new VTEX IO apps, configuring builders, or fixing deployment failures related to app structure and naming conventions.
Use when compile time or startup time is the problem in code that uses Warp: a request to improve, optimize, or cut compile times; an app that is slow to start or stalls at the first wp.launch; seconds of compiling before real work begins; JIT modules recompiling on every run or every CI job. Only applies when the code being optimized uses Warp kernels. Not for steady-state kernel runtime, memory, correctness, building Warp itself from source, or nvcc/C++ build times.
Diagnose weapp-tailwindcss and `weapp-tw` CLI issues with styles not being generated, JS/template classes not being transformed, classNameSet, @source/cssEntries, source candidates, rpx, pseudo-class/custom variant, component isolation, Rspack, minification, watch/HMR, and multi-platform output for H5/Web/App/uni-app x. Use for debugging, troubleshooting, CLI output failures, classes not working, broken hot reload, wrong output, or runtime compatibility; not for new project configuration, custom API design, or Lynx-specific integration.
A deep dive into how yak scripts interact with the Yakit UI. Explains how yakit.* library functions drive interface rendering through the gRPC ExecResult stream: yakit.Info/Warn/Error/Success log output, yakit.SetProgress progress bars, yakit.NewTable/EnableTable/TableData tables (static vs dynamic), yakit.NewLineGraph/NewBarGraph/NewPieGraph/NewWordCloud charts, yakit.StatusCard status cards, yakit.EnableWebsiteTrees website trees, yakit.EnableText/TextTabData text tabs, the unified yakit.Output channel, and the full path from the frontend consuming ExecResult via useHoldGRPCStream to rendering the UI. Use when the user asks "how do I make Yakit show a table/chart/progress bar/card from a script" or "where does yakit.Info output go".
Download live chat transcripts from YouTube videos. Use when the user asks for live chat, chat messages, or chat replay from a YouTube video and provides a YouTube URL (youtube.com/watch?v=, youtu.be/, or similar). Works with live streams and past streams that have chat replay enabled.
Creates a 3D cartoon “what if” explainer short (9:16) in the style of Zack D. Films-type videos, entirely in code with three.js. It features procedural cartoon people, props, and effects, a blue studio sky, slow-motion impacts, a red force-ripple overlay, quick whip cuts, and 1 to 3 word captions timed to the voiceover. Use when the user runs /zach-d-films or asks for a 3D cartoon explainer, a “could X stop Y” or “what if” short with characters and props.
Answer questions about evaluating GenAI / AI tools and products using the AI Evaluation Playbook (eval.playbook.org.ai; The Agency Fund with CGD and IDinsight, 2026) — the 4-level framework (Model / Product / User / Impact), Minimum Viable Evaluations, golden datasets, LLM-as-judge, engagement funnels, guardrail metrics, level linkages. Use when Ane asks how to evaluate an AI tool, chatbot or GenAI product, "how do I know this AI is working", "what should we measure for this AI tool", "where do I start with AI evals", or an MA/partner AI tool proposal needs an evaluation appraisal. NOT for programme or MEL evaluation design (/ann, /grill-mel, indicator-designer, evidence-synthesis own that lane) and NOT for AI used by evaluators as a working tool (wiki page ai-mel-framework governs that).
Use when the user needs an end-to-end article illustration workflow in this repository that preserves Type x Style planning, loads article-illustration preferences, recommends Alibaba Cloud image backends, and produces a Markdown article with inserted local image references.
Triage an Amazon Account Health Rating (AHR) screenshot or text dump. Identifies which violations and metrics are pulling the rating down, prioritizes by point weight, and outputs a remediation order. Use when a user asks about Account Health, AHR, account health rating dropping, violations to address, or stabilizing a yellow or red account. Trigger phrases: "account health", "AHR", "violations", "policy strikes", "account at risk". Works with zero tools. the user pastes the AHR snapshot.
Mine the Customer Questions tab of a listing for unanswered buyer intent. Generates branded answers to publish, then feeds the recurring question themes back into bullets, A+ content, and backend keywords. Use when a user asks about Customer Questions section, Q&A tab, unanswered questions, or using questions for SEO. Trigger phrases: "Customer Questions", "Q&A tab", "unanswered questions", "questions on my listing". Works with zero tools. the user pastes the questions.
Build a complete Amazon keyword set for a product and sort it into a usable map. generates seed keywords, expands by intent, classifies by funnel stage and relevance, and assigns each keyword a placement (title, bullets, backend, PPC). Use when a user asks for keyword research, keyword ideas, what keywords to target, long-tail keywords, search terms to rank for, or how to map keywords to a listing. Trigger phrases: "keyword research", "keyword ideas", "what keywords", "long tail keywords", "keywords for my listing", "keyword map". Works with zero tools. the user describes the product and audience.
Optimize a full Amazon listing for both ranking and conversion, and diagnose why a listing is not ranking against the A9 + COSMO pillars. Rewrites the title, bullets, and description, places keywords correctly, sharpens the benefit argument, and checks policy and mobile compliance. Use when a user asks to optimize a listing, improve a title, rewrite bullets, fix a listing that does not convert, improve listing copy, do a listing makeover, rank higher in search, audit search visibility, or asks about the A9 or COSMO algorithm. Trigger phrases: "optimize my listing", "listing optimization", "rewrite my bullets", "improve my title", "listing not converting", "listing makeover", "amazon SEO", "rank higher", "A9", "COSMO", "search ranking", "search visibility", "why doesn't my listing rank". Works with zero tools.
Build Amazon FBA reimbursement claims under the 2025 manufacturing-cost policy. Identifies eligible cases (lost units, warehouse-damaged units, customer-return losses, fee errors), assembles the cost-basis evidence Amazon now requires, and produces a claim packet per case within the 60-day window. Use when a user asks about FBA reimbursements, lost inventory claims, warehouse damage, the new reimbursement policy, manufacturing cost evidence, or unrecovered refunds. Trigger phrases: "reimbursement", "FBA claim", "lost inventory", "warehouse damage", "manufacturing cost", "60 day window", "SAFE-T". Works with zero tools. the user pastes the relevant Amazon report rows and supplier invoices.
Mine Amazon reviews for product, listing, and marketing intelligence. Extracts recurring complaints, feature requests, the words customers use, and the reasons they chose the product, then turns them into listing fixes, product improvements, and copy. Use when a user pastes reviews and asks to analyze them, find complaint patterns, mine reviews, understand customer sentiment, pull insights from competitor reviews, or turn reviews into improvements. Trigger phrases: "analyze reviews", "review analysis", "complaint patterns", "what customers say", "mine reviews", "competitor reviews". Works with zero tools. the user pastes the reviews.
Plan supplier diversification away from China-only sourcing into Vietnam, India, Mexico, or domestic light-assembly. Compares HS-code duty rates, lead times, MOQ, and tariff exposure across alternative origins. Use when a user asks about diversifying suppliers, moving sourcing out of China, alternative manufacturing countries, tariff exposure, or de-risking supply chain. Trigger phrases: "diversify suppliers", "out of China", "Vietnam supplier", "India supplier", "Mexico", "tariff exposure", "supply chain risk". Works with zero tools.
Diagnose whether a seller is stuck in the "ACoS trap" by reading ACoS, TACoS, organic rank, and conversion trends together. Identifies whether bid cuts are killing organic sales and outputs a rebalancing plan. Use when a user asks about TACoS, ACoS trap, ads cannibalizing organic, organic rank dropping, or rebalancing ad spend. Trigger phrases: "TACoS", "ACoS trap", "ad cannibalization", "organic rank dropping", "ad spend rebalance". Works with zero tools. the user pastes trend data.
Aggregate and analyze annual security reports from major vendors — extract trends, compare threat landscapes year-over-year, produce synthesized threat intelligence summaries. Fetch, list, and update report sources. USE WHEN annual reports, security reports, threat reports, industry reports, vendor reports, threat landscape, fetch report, list sources, update sources.
Recolor every overlay, text element, background, and shape in an existing video to the brand palette in one pass, leaving footage, narration, and timing untouched. Use when the user says "apply our brand colors", "make this video on-brand", "recolor the overlays to our palette", "fix the colors to match our brand", or "this video doesn't match our brand kit".
Системный архитектор — форма системы поверх контуров: контракты, схемы, жизненные циклы, переиспользование, целостность, архитектурный пересмотр, спорные вопросы, решения владельцу. Триггеры: «архитектор», «системный архитектор», «держи целостность», «спроектируй сквозное», «подготовь решение», architect, cross-cutting decision; «продумай» о предмете нескольких контуров или превращении целиком. Не для кодинга. Композирует design, integrity, assembly, reality-audit, reconcile, inquiry, writing. Нужны iskron_*.
Convert a help-center article, blog post, changelog entry, or any pasted document into a narrated explainer video using only the Clueso MCP. Use when the user says "turn this article into a video", "make a video version of this doc", "video from these release notes", "explain this guide as a video", or pastes long-form text and asks for a video.
Aspire orchestration for cloud-native distributed applications in any language (C#, Python, Node.js, Go). Handles dependency management, local dev with Docker, Azure deployment, service discovery, and observability dashboards. Use when setting up microservices, containerized apps, or polyglot distributed systems.
Content extraction from Chinese news sites. Supports WeChat Official Accounts, Toutiao, NetEase News, Sohu News, and Tencent News. Activate when the user needs to extract Chinese news content, scrape WeChat Official Account articles, crawl news, or get news as JSON/Markdown.
Upload local files or images to the project's Cloudinary CDN (cloud “cyeam”) via the official `cld` CLI, replicating the /admin/upload behavior. Converts images to webp during storage and uploads them to a target folder. Use when the user wants to upload images or files to Cloudinary, batch-upload a directory, or asks “上传图片到cloudinary”, “传图”, or “upload to cloudinary”.
This skill should be used when the user asks to "deploy to Locaweb Cloud", "set up GitHub Actions deployment workflows", "create a preview environment", "add a production environment", "tear down an environment", "configure a custom domain", "connect to the database", "check deployment logs", "scale the VM", "recover from snapshots", "disaster recovery", "what is the app URL", "what is the deployed URL", "where is my app", or asks about architecture decisions (monolith vs microservices, vertical vs horizontal scaling), platform constraints (Postgres only, single container, port 80), managing secrets and environment variables, Dockerfile requirements, database migrations, or performing operations and troubleshooting on live infrastructure (SSH access, container logs, health checks).
The cofounder's core operating instructions — persona, session-startup procedure, development and deployment workflows, the skill reference, and the standing rules. The project's AGENTS.md points here; invoke this skill at the very start of every session and follow it for the entire session.
This skill should be used when the user asks to "rotate SSH keys", "regenerate SSH keys", "replace SSH keys", "renew SSH keys", or when the agent needs SSH access to a deployed VM for troubleshooting (logs, debugging, database access) but discovers the expected SSH key file is missing from the local disk (e.g. `~/.ssh/<repo-name>` does not exist). Also use when the user mentions "lost SSH key", "SSH key not found", "can't SSH into server", "permission denied SSH", "moved to a new computer", or "cloned repo on another machine".
Cold email and outreach sequence design with personalization, deliverability optimization, follow-up cadence, and compliance (CAN-SPAM/GDPR). Use when the user asks about cold email, outreach sequences, email prospecting, cold outreach, or email deliverability for outbound.
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.
