Skills
99,719 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Tell me what you need and I'll handle the heavy lifting — whether that's captioning a tutorial, adding multilingual subtitles to a product demo, or burning readable text onto a social clip. This automatic-subtitle-generator skill detects speech, syncs captions to timing, and outputs subtitle-ready video files. Supports mp4, mov, avi, webm, and mkv formats. Perfect for educators, content creators, marketers, and accessibility advocates who need accurate, well-timed subtitles without manual transcription.
Looks up curated web security learning resources (XSS, SQLi, CSRF, SSRF, OAuth/JWT, deserialization, SAML, recon, evasion, defensive tooling, CTF). Filters by topic, difficulty, language, and resource type. Returns top references with archive fallbacks. Defensive and educational use only.
Use when the user asks about chaos engineering, fault injection, resilience testing, or HA verification for a SPECIFIC AWS service (e.g., RDS, EKS, MSK, ElastiCache, DynamoDB, S3, Lambda, OpenSearch, etc.). Triggers on "chaos testing on [service]", "fault injection for [service]", "how to test HA of [service]", "FIS scenarios/actions for [service]", "[service] failover testing", "[service] resilience testing", "[service] 混沌测试", "[service] 故障注入", "[service] 高可用验证", "对 [service] 做混沌实验", "test my [service]", "verify my [service] is resilient". Use this skill even when the user phrases it casually like "test my RDS" or "how resilient is my MSK cluster".
Use when exporting existing Azure resources to Terraform using aztfexport. Triggers on aztfexport, Azure import to Terraform, export Azure resource, bring Azure under Terraform management, reverse-engineer Azure infrastructure, bootstrap IaC from live Azure resources. Covers resource, resource-group, and query modes.
Remove backgrounds from images with BiRefNet via inference.sh CLI. Model: BiRefNet (high accuracy background removal). Use for: product photos, portraits, e-commerce, transparent PNGs, photo editing. Triggers: remove background, background removal, remove bg, transparent background, cut out image, background remover, rembg, product photo editing, cutout, transparent png, bg removal, photo cutout
Remove backgrounds from images using AI. Triggers include: "remove background", "transparent background", "cut out", "isolate subject", "remove bg", "make transparent", "extract subject", "background removal". Creates PNG or WebP images with transparent backgrounds.
Baidu Drive file management and document content capabilities — upload, download, save a copy, share, search files, search document passages, read full file contents, move, copy, rename, and create folders; check drive capacity, used space, and remaining space. Also supports Agent memory backup and restore (kimiclaw/maxclaw/qclaw/openclaw). Trigger when the user mentions “百度网盘/bdpan/网盘/云盘/baidu drive/Baidu Drive” and asks about file operations or drive capacity, remaining space, or usage; or mentions memory-related operations such as “备份记忆” (back up memory), “恢复记忆” (restore memory), or “查看记忆备份” (view memory backup). Do not trigger for non-file-storage operations, use of other cloud drives, local memory organization or cleanup, or PPT generation (handled separately by the baidu-wenku-aippt skill).
A skill for retrieving 2026 Milan Winter Olympics data, including medal standings, live news reports, and competition schedules. Scrapes real-time medal rankings, latest news, and match schedules from Baidu Sports. Use this skill when users need to query Winter Olympics medal standings, check medal counts by country, get live news, or view competition schedules.
Generates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining 10 color palettes and 7 rendering styles. Supports cinematic (2.35:1), widescreen (16:9), and square (1:1) aspects. Use when user asks to "generate cover image", "create article cover", or "make cover".
Use when an agent is executing work in any project repo and needs to coordinate with a human or other agents via BeadBoard. BeadBoard is the human-facing dashboard running separately; this skill is the agent-side operating contract for state, mail, assignment, and evidence flow.
There are two kinds of people who search for a cosmetology school. The first already knows they want to do hair or skincare — they have been doing it informally for years, everyone has told them they are good at it, and they are now ready to turn it into a career. What they need to see is whether your graduates are actually working in the industry at the level they want to reach. The second is not sure yet — they are considering cosmetology as a career alternative, and they are trying to figure out if this feels like something they could do every day for the next twenty years. What they need to see is what a day in your school actually looks and feels like. Beauty School Video creates the enrollment content that reaches both. Beauty School Video makes marketing and enrollment content for cosmetology schools, esthetics and skincare programs, nail technology schools, barbering programs, makeup artistry courses, hair styling academies, microblading and permanent cosmetics programs, lash and brow technician training, massage therapy schools, and continuing education providers for licensed beauty professionals. The content addresses the full range of prospective students: the career-changer in their twenties who wants out of an office job, the recent high school graduate who knows exactly what they want to do, the licensed professional who wants to add a specialty, and the entrepreneur who is building toward owning their own salon. Day-in-the-life and school culture videos that show what a typical Tuesday in the school actually looks like — the student working on a client, the instructor giving feedback over a haircut, the energy in the practical lab versus the classroom — because prospective students are buying an experience, not just a curriculum. Graduate outcome and career placement videos that show where your graduates are working, what specialties they have built, and how long it took from graduation to licensed employment — the specific proof that this school produces working professionals, not just graduates. Program-specific showcase videos for cosmetology, esthetics, nail technology, barbering, and every other credential you offer — matched content that shows up when a student is already searching for their specific program. Instructor and mentor introduction videos that put your faculty on camera to share their industry experience, their teaching approach, and the specific skills they have built over years of professional work — because a student choosing a beauty school is partly choosing the person who will teach them. Financial aid and enrollment process explainer videos that address the practical questions that stop prospective students from applying — how financial aid works, what the timeline looks like, what happens in the first week — because uncertainty about the process kills more enrollments than uncertainty about the career. Content for school websites, social media, targeted digital advertising to career-change audiences, high school counselor outreach, and the beauty community social networks where program recommendations spread among working professionals and students simultaneously. Beauty school video, cosmetology school promo, esthetics program video, nail tech school video, barbering school video, makeup artistry course video, cosmetology school enrollment video, beauty school marketing, hair school promo, skincare school video, beauty career video, cosmetology program tour, licensed cosmetologist training video, beauty school culture video.
PDCA + Sprint document templates — Plan, Design, Analysis, Report for individual features plus templates/sprint/{master-plan, prd, plan, design, iterate, qa, report}.template.md for sprint-level documents (v2.1.13). Triggers: template, plan document, design template
This skill should be used when the user asks "how do I customize Bootstrap", "how to create a custom Bootstrap theme", "what Sass variables can I override", "how to implement dark mode in Bootstrap", "how to change Bootstrap colors", "how to override Bootstrap defaults", "how to add custom colors to Bootstrap", "how to enable Bootstrap shadows", "how to compile Bootstrap Sass", "how to use Bootstrap CSS variables", or needs help with Bootstrap theming, Sass variable overrides, CSS custom properties, or color mode implementation.
Integrate and operate BOUND, the deterministic bounded-utility control policy for agent workflows. Use when an agent must install bound-policy, define StepContracts, collect real ExecutionEvidence, evaluate meaningful execution boundaries, react to ACCEPT/RETRY/REPLAN/ROLLBACK, audit an existing BOUND integration, or produce a reproducible numeric integration report.
Condense a detailed brand description into a usable Brand Kit (brand kit, design system, design tokens, style guide). Generates a short, binding BRAND.md, executable CSS tokens, wordmark SVGs, reference artboards, and a CLAUDE.md that makes the rules take effect automatically. Use this skill as soon as a brand interview exists, when someone wants to turn a long style guide into something workable, or asks why their design system gets ignored in everyday use.
Builds websites, PDFs and AI images from an existing Brand Kit and labels generated images in line with the EU AI Act (brand kit, landing page, PDF, AI images, AI labeling, EU AI Act, higgsfield, gpt image). Integrates the unslop, web-design-guidelines and seo-audit skills and burns in the AI marking via the bundled script. Use this skill as soon as something is to be built with an existing Brand Kit, or someone asks how to label AI images in a legally compliant way.
Build apps that integrate with external services via Membrane. Use when the user wants to add integrations to their product — let their customers connect to Slack, HubSpot, Salesforce, GitHub, Google Sheets, Jira, or any other app, execute actions, sync data, or handle webhooks. Covers backend token generation, frontend connection UI, running actions, data collections, and AI agent tooling.
Building envelope design: wall systems (masonry, timber, steel, CLT, curtain wall, rainscreen, precast, SIPs, ICF), glazing systems (single to triple, low-e coatings, gas fills, framing types), roofing (flat, pitched, green, membrane), thermal performance (U-value, R-value, SHGC, air permeability), moisture management (vapor barriers, condensation risk, Glaser method), air barriers, cladding, and thermal bridge prevention.
Building sustainability frameworks and certification systems: LEED BD+C v4.1, BREEAM New Construction, Passive House (PHI/PHIUS), WELL Building Standard v2, DGNB, Living Building Challenge, Net Zero Carbon strategies, whole-life carbon assessment, embodied carbon reduction, operational energy targets, circular economy in architecture, and design for disassembly.
Run a structured business analysis workflow: requirements elicitation with stakeholder interviews and MoSCoW prioritization, as-is/to-be process mapping with BPMN notation, data-driven analysis (CBA, SWOT, root cause), and production-ready documentation (BRD, FRD, user stories with INVEST acceptance criteria). Triggers on "gather requirements", "write user stories", "map business process", "BRD", "FRD", "gap analysis", "cost-benefit analysis", "facilitate workshop", "business requirements", "process mapping", "as-is to-be", "stakeholder interview", or "business analyst". For management consulting (issue trees, steerCo business cases, operating model), use business-consultant—not business-analyst. For business model canvas, market sizing, and unit economics research, use business-model-researcher. Human data / labeling platform PRDs: product-management-human-data-platform. Monetization PRDs and packaging: product-management-monetization.
Coding Agent Account Manager - Sub-100ms account switching for AI coding CLIs with fixed-cost subscriptions. Vault profiles, isolated profiles for parallel sessions, smart rotation with health scoring, cooldown tracking, automatic failover, TUI dashboard. Go CLI.
Performs arbitrary-precision arithmetic calculations including addition, subtraction, multiplication, division, and exponents. Use when the user asks to calculate, compute, or evaluate math expressions, or when precise decimal arithmetic is needed to avoid floating-point errors.
Drive the Capigo platform through the installed `capigo` CLI — the entry point for any Capigo work an agent does for a tenant. Use this whenever a request maps to Capigo data or capabilities — tasks, boards, members, products, variants, brands, categories, product types, product properties and property definitions, VAT policies, units, warehouses, stock locations, inbound receipts, outbound shipments, stock transfers, availability, tenants, authentication, configuration — even when the user never names the CLI or Capigo itself, and in whatever language they ask: "create a task and assign it to someone", "what's on the board this week", "read or post comments on that task", "list products", "look up this SKU or barcode", "set this product's origin or voltage", "tag this product Hè", "products tagged Sale", "how many brands do we have", "tag this task urgent", "tasks labelled X", "plan an inbound receipt for this PO", "which warehouse can cover this order". Also the reference for how the CLI itself works: detecting the install, logging in, picking a tenant, exit codes, JSON output, and self-diagnosing a misbehaving command. If a request touches Capigo and you are unsure how to talk to it, reach for this skill first instead of guessing raw API calls.
Capture learnings, patterns, or workflows from the current conversation into a new or existing skill. Use when the user wants to save what was learned, discovered, or built during a conversation as a reusable skill for future sessions. Triggers include "capture this as a skill", "save this for next time", "turn this into a skill", or when a useful workflow, pattern, or piece of domain knowledge emerged during the conversation.
B2B case study writing with STAR framework, data visualization, and research. Covers structure, customer quotes, metrics presentation, and distribution formats. Use for: customer success stories, portfolio pieces, sales enablement, marketing content. Triggers: case study, customer story, success story, b2b case study, client testimonial, customer case study, portfolio case study, use case, customer win, results story
When the user is analysing enterprise risk management, the boundaries of the CEO's responsibilities, or assessing whether an organisation truly takes risk control seriously. Language signals: "who should manage risk management" / "why should the CEO personally manage risk" / "isn't the risk control department enough" / "what is the CEO's greatest responsibility" Not applicable to: pure investment analysis that does not involve organisational risk management.
Query wallet addresses and on-chain balances on OpenAnt. Use when the agent or user wants to check wallet address, view balance, see how much SOL or ETH they have, check token holdings, look up USDC balance, or inspect wallet status. Also use when a wallet operation fails with "Insufficient balance". Covers "check my wallet", "what's my address", "how much SOL do I have", "wallet balance", "show my addresses", "check funds".
A Chinese content quality review tool and main entry point (gateway) for the writing suite. Comprehensively reviews a Chinese draft from four perspectives—editor, reader, author, and platform—across 16 criteria, then outputs a score, issue list, and routing recommendations. Does not edit; it only reviews and routes. Triggers: “review how this reads,” “does this have any issues,” “check this article,” “is this draft acceptable,” “review this for me,” “article quality review,” “Chinese writing diagnosis,” “can this be published,” “what needs changing in this draft,” “how should I revise it.” EN: “review my Chinese article,” “check this article quality,” “Chinese writing diagnosis,” “proofread this piece,” “is this article good enough”. Not for: direct rewriting (→ plainspoken-writing / editor-revisor); title, layout, or punctuation edits only (→ packaging-workshop); finding one’s voice (→ voice-dissolver); verifying the truth of facts, data, or quotations (→ L0 fact-review).
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.
Your EYES into the user's live Chrome browser and Electron apps. This skill lets you SEE and INTERACT with the user's actual browser or Electron app — their open tabs, logged-in sessions, and live page state. You MUST use this whenever the user's request involves browser content or Electron app inspection in ANY way. TRIGGER THIS SKILL when the user: - References pages they have open: 'I have X open', 'my tabs', 'open tabs' - Asks to look at, compare, or analyze anything in their browser: 'compare these pages', 'which looks better', 'check this page' - Mentions UI/visual analysis of live pages: 'dashboard', 'UI', 'layout', 'design quality' - Asks for screenshots or page inspection: screenshot, inspect, debug, check the page - Refers to 'the page', 'the browser', 'my tab' in any context - Mentions console errors, page state, or anything requiring browser access - Mentions Electron apps or CDP connections: 'Electron', 'electron app', 'CDP', 'CDP_PORT', 'DevTools Protocol', 'desktop app', 'remote-debugging-port' CRITICAL: NEVER say you cannot see the user's browser or ask users to paste screenshots. You CAN see their browser through this skill. Use `list` to discover open tabs, then `perceive` or `shot` to see page content. Do NOT use Playwright — it launches an isolated browser without the user's login state, cookies, or open tabs.
Skill dedicated to the custom cabinet pitfall-avoidance guide. Covers the full process of countertop materials, cabinet doors and panels, hardware and accessories, wardrobes, shoe cabinets and sideboards, cabinet layout and dimensions, and whole-house customization pitfalls, integrating in reverse order the highlights of the Xi'an Renovation Classroom member-edition knowledge base to help users customize cabinets with less hassle and fewer pitfalls.
The user is torn between "buying a poor business cheaply" and "buying a good business at a fair price" when choosing an investment target or business model. Language signals: "can I pick up this bargain" / "is a low valuation worth buying" / "is an expensive good company worth buying" / "what's wrong with cheap stuff" Not applicable to: situations where an explicit investment methodology already exists and there is no need to choose between the two styles.
Universal cinema worldbuilding director for Seedance video prompts with locked compositional rigor. Reads uploaded reference images for wardrobe, hair, makeup, identity, and environment, then composes production-ready Seedance prompts using a five-mode cinematography grammar (M1 Narrative, M2 Studio, M3 Action, M4 Performance, M5 Atmospheric) plus explicit Frame Map, Subject Lock, Movement, and Last Frame controls. Anchors subjects to screen positions, depth layers, contact points, and gaze so characters never drift, swap, or destabilize. Diegetic audio only — never music or lyrics. Use whenever the user wants a Seedance video prompt, mentions Seedance, asks for a cinematic scene breakdown, uploads references for a scene, describes a shot for video generation, or asks for music videos, action sequences, performance scenes, narrative shorts, fashion films, or atmospheric environment plates — even without saying 'cinematic' or naming a mode.
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.