Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when the user has one or more video clips and wants to add post-production on top — AI-generated cover as first frame, HTML/CSS captions synced to SRT, kinetic illustration overlays at hook moments, chapter chips, end-card CTA, or any other timed motion graphics. Most often used as the downstream of `/wjs-segmenting-video` — pick up where that skill stopped (raw cropped clip + per-clip SRT) and produce the upload-ready MP4. Backed by HyperFrames so everything compiles to ONE final encode — no cascade of re-encodes. Triggers — "加封面", "加字幕", "加动画", "加 CTA", "做后期", "post-production", "title card", "kinetic captions", "end card".
Use when the user wants to teach or learn an English word as a video — turn a single English word into a self-contained HLS “supercut” lesson built from the mira video base. Stitches every season2 clip where the word is spoken (via the search-app API) into one .m3u8, prepended with a Claude-written bilingual word-intro card (word + IPA + Chinese gloss + usage, Volcano TTS) and appended with a 关注王建硕 CTA card. No MP4 burn. Triggers — “teach <word>”, “讲讲 <word>”, “学英语 <word>”, “把 <word> 做成视频”, “/wjs-teaching-english <word>”
Write docs/<feature>/ACCEPTANCE.md — the ordered checklist a person works through by hand to deploy, test and accept finished work, because a machine could not do it. Use at the end of every implementing skill (execute-plan, execute-roadmap, build-feature), or when the user invokes /write-acceptance <feature> or asks for a test plan, an acceptance checklist, or "tell me how to verify this". Covers only what could not be automated — consoles and accounts, physical devices, GUI surfaces, two-machine and multi-user cases — with copy-pasteable commands, the exact observable that counts as evidence, and what you expect back. The reader may be the user or a tester who has never seen the feature. For handing unfinished work to the next agent, use write-handoff instead.
Write a feature spec or PRD from a problem statement or feature idea. Use when turning a vague idea or user request into a structured document, scoping a feature with goals and non-goals, defining success metrics and acceptance criteria, or breaking a big ask into a phased spec.
Master prompt for analyzing and generating an AGENTS.md governance system. Analyze the current project and immediately generate a root AGENTS.md and subordinate AGENTS.md files; incorporate team-specific knowledge found in the code (asymmetries, test boundaries, hard constraints, defense in depth, security boundaries) into Golden Rules with supporting evidence; and add an @AGENTS.md link to CLAUDE.md. Must run when called with “Create AGENTS.md,” “Create agent rules,” or “/agents-md.”
Query Alibaba Cloud domain information: domain details, domain list, advanced search, and instance ID lookup. Query Alibaba Cloud domain information: domain details, domain list, advanced search, and lookup by instance ID. Triggers: "domain info", "domain query", "domain details", "domain list", "domain search", "域名查询", "查询域名", "域名信息", "域名详情", "域名列表", "查看域名", "搜索域名", "domain status", "域名状态", "到期时间", "expiration date"
Manage the full lifecycle of Alibaba Cloud EMR Serverless StarRocks instances — create, scale, configure, maintain and diagnose. Use this Skill when operations engineers, SREs, or architects need to manage StarRocks instances. Typical scenarios include: "create a StarRocks", "check instance status", "scale up CU", "modify configuration", "restart instance", "diagnose issues", etc. Not applicable for: writing SQL/DDL, data import/export, query tuning, materialized view configuration, or managing non-StarRocks products (EMR clusters, Spark, Milvus, ClickHouse, Doris, RDS, ECS).
Run the author's half of the document review loop without the user relaying each round — wait for the reviewer's <DOC>.revN.notes.md, answer it with <DOC>.rev(N+1).md, and repeat until the reviewer says ready for final, a round cap is hit, or only the user can move it forward. Use after rev1 exists, when the user invokes /answer-notes-loop <feature> [max-rounds] in the session that authored the plan, roadmap, technical or experience document. Its counterpart is review-doc-loop in a fresh session
Stops defensive writing across the entire paper lifecycle — writing, revising, cutting, and organizing experiments. Treats the paper as a press conference, not a project summary, lab log, or self-audit: identify the single most publishable strength of the work and build the most favorable, complete, and persuasive narrative around it. Never present everything evenly, never volunteer weakness, never write an experiment diary, never attack the paper on the reviewer's behalf. Triggers: polish my paper, revise manuscript, write abstract, write introduction, write conclusion, shorten paper, rebuttal, respond to reviewers, organize experiments, defensive writing, AI-flavored academic writing.
Use when profiling async/await performance, diagnosing actor contention, or investigating thread pool exhaustion. Covers the Swift Concurrency Instruments template, task visualization, actor contention analysis, and thread pool debugging
Expert knowledge for Azure CycleCloud development, including troubleshooting, best practices, decision making, architecture and design patterns, security, configuration, integrations, coding patterns, and deployment. Use when automating CycleCloud via API/CLI/SDK, configuring Slurm clusters, tuning HB/HC VMs, securing access, and other Azure CycleCloud development tasks. Not for Azure Batch (use azure-batch), Azure HDInsight (use azure-hdinsight), Azure Databricks (use azure-databricks), or Azure Kubernetes Service (AKS) (use azure-kubernetes-service)
Expert knowledge for Azure Deployment Environments development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when defining environment.yaml, configuring dev centers/projects, using ADE/Dev CLI, custom images, or CI/CD deployments, and other Azure Deployment Environments related development tasks. Not for Azure DevTest Labs (use azure-devtest-labs), Azure Dev Box (use azure-dev-box), Azure Managed Applications (use azure-managed-applications), Azure Resource Manager (use azure-resource-manager).
Expert knowledge for Azure Dev Box development, including troubleshooting, best practices, decision making, limits and quotas, security, configuration, integrations, coding patterns, and deployment. Use when designing Dev Box images, configuring pools/catalogs, securing access (RBAC/SSO), managing quotas, fixing connectivity, and other Azure Dev Box development tasks. Not for Azure DevTest Labs (use azure-devtest-labs), Azure Virtual Machines (use azure-virtual-machines), or Azure Virtual Desktop (use azure-virtual-desktop)
Expert knowledge for Azure IoT Hub development, including troubleshooting, best practices, decision-making, architecture and design patterns, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use for IoT Hub/DPS provisioning, device twins, routing, direct methods, or Device Update workloads, and other Azure IoT Hub development tasks. Not for Azure IoT (use azure-iot), Azure IoT Central (use azure-iot-central), Azure IoT Edge (use azure-iot-edge), or Azure IoT Operations (use azure-iot-operations).
Expert knowledge for Azure IoT Operations development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building MQTT/OPC UA data flows, WASM transforms, Dapr/Akri integrations, or Arc Kubernetes deployments, and other Azure IoT Operations related development tasks. Not for Azure IoT (use azure-iot), Azure IoT Hub (use azure-iot-hub), Azure IoT Edge (use azure-iot-edge), Azure Defender For Iot (use azure-defender-for-iot).
Expert knowledge for Azure Update Manager development, including troubleshooting, best practices, decision-making, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use when onboarding VMs/Arc, configuring update schedules/ESU, automating via SDK/REST, or migrating from ConfigMgr, and for other Azure Update Manager development tasks. Not for Azure Automation (use azure-automation), Azure Monitor (use azure-monitor), Azure Policy (use azure-policy), or Azure Site Recovery (use azure-site-recovery).
Expert knowledge for Azure Virtual WAN development, including troubleshooting, decision-making, architecture and design patterns, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use when designing Virtual WAN hubs, P2S/Always On VPN, BGP/IPsec routing, ExpressRoute, or SD-WAN/NVA integrations, and for other Azure Virtual WAN-related development tasks. Not for Azure Virtual Network (use azure-virtual-network), Azure VPN Gateway (use azure-vpn-gateway), Azure ExpressRoute (use azure-expressroute), or Azure Application Network (use azure-application-network).
Generate one or more standalone Meta image-ad creatives via ChatGPT Image 2 (gpt-image-2) through the Arcads external API. Locks the model, auto-strips platform chrome, enforces edge-safe layouts and glyph-safety inside body text. Use when the user asks for a “gpt-image-2 ad,” “ChatGPT Image ad,” “Image 2 ad creative,” “make a static image ad with GPT,” or anchors on a need for typography-heavy / dense-text / UI-mimicry ad creatives (chat threads, comparison tables, fake search results, iOS dialogs, Slack snapshots, ChatGPT-conversation ads, Apple Notes lists). Does NOT trigger on Nano Banana cues — use nano-banana-image-ad for those.
freeCodeCamp's "Command-line Chic" UI design system and aesthetic guidelines. Apply these rules whenever building, styling, or reviewing any UI that should look and feel like a freeCodeCamp product — web apps, dashboards, landing pages, admin tools, component libraries, or themes. Use this skill when the user mentions freeCodeCamp styling, fCC design, "Command-line Chic", dark theme development for fCC, or asks for a UI that follows freeCodeCamp's visual identity. Also use when working on any freeCodeCamp repository, contributing to freeCodeCamp projects, or building tools and dashboards for freeCodeCamp staff, even if the user doesn't explicitly mention the design system
Commissaire aux comptes IA pour l'audit des comptes annuels d'entreprises françaises. Applique la démarche NEP en 7 phases : prise de connaissance, contrôle du FEC, vérification du bilan, du compte de résultat, de la balance, de la liasse fiscale, et contrôles transversaux. Émet une opinion motivée sur la fiabilité des comptes avec rapport structuré. Triggers: audit, commissaire aux comptes, CAC, certification, comptes annuels, validation comptes, révision comptable, statutory audit
Write a high-level commit summary of the current work — what changed and why the decisions were taken — show it for approval, then commit on approval without pushing. Use when the user asks to summarise, write up, or commit a batch of work, or says "commit this" / "write a commit message". Its length is proportional to the change — a one-line fix gets a sentence or two, a multi-file batch gets the full sectioned body. The summary is also read downstream by people and LLMs generating changelogs, release notes, marketing copy and user-guide updates, so it is written for that second audience as well as for git. Never commits a binary file without asking first.
Scaffold and fully configure a new Agentic Coding Starter Kit project — a Next.js 16 + TypeScript + Better Auth + Drizzle + PostgreSQL + AI SDK boilerplate. Use whenever the user asks to set up, scaffold, create, initialize, or bootstrap an “agentic coding starter kit,” “agentic app,” “agentic boilerplate,” a “Next.js app with auth and db,” or mentions `create-agentic-app` / `npx create-agentic-app`. Guides the user through folder strategy, package-manager choice, Postgres setup (Docker / Neon / Vercel / BYO), OpenRouter AI configuration, migrations, a build check, and dev-server verification, ending with a working http://localhost:3000.
Data discovery and analysis specialist focused on extracting actionable insights from complex datasets, identifying patterns and anomalies, and transforming raw data into strategic intelligence. Excels at multi-source data integration, advanced analytics, and data-driven decision support.
Generate professional presentations with AI-generated images. Use when asked to create a deck, presentation, pitch deck, or slides. Supports style presets (whiteboard, corporate, minimalist, etc). Uses Imagen 4.0 API for image generation and Google Slides API for assembly. Produces full decks from markdown content specs in minutes.
Build and manage pages, elements, components, and styles in Webflow Designer. Use when adding sections, creating layouts, building elements, inspecting or updating components, viewing what's inside a component, restructuring pages, creating new pages, previewing page structure, styling elements, or managing component properties. Requires Webflow Designer connection.
Provider-independent dialogue editing and ADR direction for AI agents producing generated videos, films, ads, avatar clips, explainers, localization/dubbing, podcasts, recuts, and social content. Use for dialogue prep, repair, room tone, take comping, sync, ADR cueing, dubbing direction, pronunciation, de-essing, plosives, mouth clicks, voice continuity, synthetic voice consent boundaries, captions/transcripts handoff, mix handoff, loudness, intelligibility, accessibility, and QA.
Checks whether a developer understands a pull request before they merge it, especially code an AI agent wrote. It reviews the author rather than the code by questioning them about changes they can't explain. Use whenever someone is about to open, submit, review, or merge a PR, branch, or diff containing AI-generated code, or wants to ensure they understand a change before shipping.
Shape a feature as a product before anyone plans how to build it — the sentence, the ladder of use cases smallest to largest, what stays hidden, and the open product questions. Use when the user invokes /draft-experience <feature>, asks what a feature should be, asks whether something is simple enough, or wants the experience document that a technical design, roadmap or plan is then written from. Also use to check an existing feature, bug or proposal against the product shape it claims to serve. Writes docs/<feature>/EXPERIENCE.rev1.md, which is reviewed on its own before any technical planning starts
Design how a feature is built as an engineering conversation with the user before any plan document exists — discover the architecture together, find what the codebase already has to build on, challenge complexity, record every decision with its reason, and write docs/<feature>/TECHNICAL.rev1.md only when the user says the design is ready. Use when the user invokes /draft-technical <feature>, or asks to design, architect, or think through how to build a feature, subsystem, integration, migration or infrastructure change. This is the first technical step for a new feature or a roadmap — it will not have the whole picture, and it is the strong start that build-feature's plan and draft-roadmap's milestones are then derived from
Translate natural-language requests about AI-agent behavior, skills, MCP tools/servers, prompts, routing, context loading, memory, hooks, plugins, permissions, delegation, portability, or other agentic-system behavior into the concrete runtime mechanism and change surface. Use when a request is phrased as what the AI should understand/do rather than how the target harness actually observes, triggers, routes, persists, or enforces that behavior
Transport to the Iskron graph — only when it is unavailable: there are no iskron_* tools or they fail at the transport level (not connected, OAuth, dead token); if even one responds, the skill is not needed. Installs iskron-bridge (stdio bridge, OAuth or personal token) — the path for working; web is a connector with a price. Triggers: “connect the graph”, “raise the bridge”, “iskron tools unavailable”, “mcp not connecting”, “oauth failing”, “log in with a token”, “PAT instead of oauth”, “connect opencode”, “what version is the bridge”, connect to the graph, raise the bridge, MCP tools missing. Composes entry
Execute an approved roadmap or plan by orchestrating sub-agents — in parallel, in isolated checkouts, where the runtime allows — you are the delivery lead, not the coder. Use when the user invokes /execute-roadmap, or asks to implement, execute, or oversee an approved roadmap or plan after draft-roadmap or build-feature has produced a signed-off final doc, e.g. "/execute-roadmap implement m2, plans 3.1-3.4, parallelize" or "oversee the roadmap until it is complete". Resolves the requested scope against the final doc, gives each plan to its own sub-agent, reviews and verifies each result against the project's principles, then merges, cleans up, and commits without waiting for approval. Honors model/effort directives where the agent tool supports them; questions that need the user are recorded with a recommendation instead of blocking.
Evaluates whether a business idea is technically buildable and financially viable. Covers unit economics (CAC, LTV), revenue modeling, break-even, and go/no-go verdicts. Triggers on: “feasibility assessment”, “viability analysis”, “unit economics”, “build vs buy”, “go/no-go decision”, “ROI projection”
Turn a signed-off plan, roadmap, technical or experience revision into docs/<feature>/<DOC>.final.md — the approved document plus the collapsed history of questions, answers and decisions across every rev and its review notes — and then delete the revs and notes. Use when the user signs off a rev after review-doc or a direct review, or invokes /finalize-doc <feature>, or asks to "write the final", "finalize the plan", "collapse the revs". Works for any stem (PLAN, ROADMAP, TECHNICAL, EXPERIENCE, …) and its companion documents. Never changes what was approved; never finalizes without sign-off
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.