Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Make a repository Superset-ready — author .superset/config.json with setup/teardown/run scripts so every new workspace boots configured, then verify with a real workspace. Use when the user wants to set up a project or repo for Superset, configure workspace setup scripts, or fix a failing workspace setup.
Project onboarding and session entry point for swain. On first run, performs full onboarding: migrates CLAUDE.md to AGENTS.md, verifies vendored tk, configures pre-commit security hooks, and offers swain governance rules — then writes a .swain/init.json marker. On subsequent runs, detects the marker and runs the per-session fast path (greeting, focus lane, session state). Use as a single entry point — it routes automatically. Triggers also on: 'session', 'session info', 'focus on', 'tab name'.
Create, edit, and convert Word documents (.docx) using Syncfusion DocIO. Supports to generate java code for the user's project. Use when the user mentions docx, Word processing, document generation, Syncfusion DocIO, or syncfusion java word.
System maintenance with three core operations - integrity check (find/fix broken references), document session (current transcript), document recent (catch-up since last update). Plus security workflows. USE WHEN integrity check, audit system, document session, document this session, document today, document recent, catch up docs, what's undocumented, check for secrets, security scan, privacy check, OR asking about past work ("we just worked on", "remember when we").
Universal React UI framework for web and native (v1.144.0+). Use when building cross-platform apps with React Native + Web, creating styled components with `styled()`, configuring design tokens/themes, using Tamagui UI components (Button, Dialog, Sheet, Input, Select, Tabs, etc.), working with animations, or needing Bento/Takeout premium components. Triggers: "tamagui", "universal UI", "react native web", "styled()", "design tokens", "$token", "XStack/YStack/ZStack", "useTheme", "useMedia", "@tamagui/*" imports, "bento", "takeout", "one.js router", "createStyledContext", "withStaticProperties", "@tanstack/react-table", "zero sync", "better auth".
Review VC term sheets for pre-seed, seed, and Series A rounds. Analyzes each clause from investor or startup perspective, identifies investor-friendly vs. founder-friendly terms, flags deviations from market standards, and provides negotiation guidance. Use when reviewing any VC term sheet, evaluating investment terms, or preparing for funding negotiations. Triggers on term sheet, VC financing, Series A, seed round, liquidation preference, anti-dilution, protective provisions.
Test environment provisioning, infrastructure as code for testing, Docker/Kubernetes for test environments, service virtualization, and cost optimization. Use when managing test infrastructure, ensuring environment parity, or optimizing testing costs.
Use meitu-cli to generate React/TSX page code from scratch, with asset references and prompt expansion. Trigger only when the user explicitly asks to generate React/TSX/HTML front-end code files; ordinary page design discussions, product plans, and visual design requests do not trigger it.
Use meitu-cli to call a standalone LLM to generate text/copy/storyboards/video prompts from scratch. Trigger when the user mentions writing copy, polishing, rewriting, slogans, product descriptions, social media copy, articles, storyboards, storyboard scripts, or prompt optimization. Disabled when the context already contains complete content; use write_file instead.
Adapts content for different audiences while preserving core accuracy, changing tone, depth, emphasis, and framing to match audience expertise and goals. Use when technical content needs business framing, strategic vision needs tactical translation, expert knowledge needs simplification, formal content needs casual tone, long-form needs summarization, internal content needs external framing, or cross-cultural adaptation is needed. Use when user mentions "explain to", "reframe for", "translate for [audience]", "adapt for [executives/engineers/customers]", or "same content, different audience".
Reach into past AI conversation history through the `trellis mem` CLI. Use whenever the user asks 'how did we solve X last time', 'have we discussed this before', 'what was the decision on X', 'remind me what we did in this task', '上次怎么解的', '之前讨论过吗', '想起一段对话', or when starting a brainstorm that overlaps prior work, debugging a familiar bug, continuing a task across sessions, or doing a finish-work review. Returns raw past dialogue; decide for the moment whether to update spec, append to task notes, quote inline in the answer, or just internalize.
Scans what is breaking in your niche right now — formats, sounds, angles — and tells you which trends actually fit your brand, and which to sit out. Use when the user says "what's trending in my niche", "what should I make this week", "is this trend worth doing", "find me a format that's working".
Use when providing DDEV URLs, accessing TYPO3 backend in browser, performing any ddev command (e.g. start, stop, restart, describe, exec), setting up DDEV for TYPO3 extension development, or testing across multiple TYPO3 versions. Triggers on: ddev URLs, backend URLs, local development, docker environment, PHP version management, multi-version testing.
A comprehensive skill for the uni-app plugin market and automatic plugin installation. Use this skill to browse plugins, auto-install plugins, configure plugin settings, and integrate third-party plugins based on the official plugin market docs.
Reviews URLSession networking code for iOS/macOS. Covers async/await patterns, request building, error handling, caching, and background sessions. Use when reviewing code that uses URLSession, URLRequest, URLCache, or URLError, or any iOS networking path.
Use when starting any conversation that touches Oracle Database or PL/SQL - it establishes how to pick the right pythia skill BEFORE any response or action, including clarifying questions. Fires on plain requests in any language, no slash command needed - "build/add/fix/explain/review/deploy X", "lam/them/sua/tao/giai thich/kiem tra/trien khai X" (Vietnamese, with or without diacritics). Also use whenever unsure which pythia skill applies, or on catching yourself answering an Oracle question with none open.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Prove that a command-line tool actually did what it said, instead of trusting its exit code and its output. Snapshots the filesystem before and after, names the expected consequence in advance, and returns one of four verdicts with what could not be seen. Use after running a build, a migration, a scaffolder, a formatter, a codegen step, or an AI coding CLI; when a command printed success and you are about to report "done"; when you are about to write "exit code 0, so it worked"; or when a tool claims it edited files. Needs nothing installed.
Use meitu-cli to do outward video canvas outpainting, with AI intelligently filling in the extended areas based on the prompt. Trigger when the user mentions extending a video, video outpainting, expanding the frame left/right/up/down, video outpainting, adding imagery to a video, expanding more background, or making the video frame wider.
Transcribe a supplied local or linked video with Gemini, or from its frames with a Claude subagent when Gemini fails, and check the transcript against one frame per second, when a recording's contents are needed as evidence, such as a bug recording on an issue, PR or comment, or a question about what a video shows.
This skill should be used when the user asks to "escalate privileges on Windows," "find Windows privesc vectors," "enumerate Windows for privilege escalation," "exploit Windows misconfigurations," or "perform post-exploitation privilege escalation." It provides comprehensive guidance for discovering and exploiting privilege escalation vulnerabilities in Windows environments.
HubSpot Work, the project and work-management product inside HubSpot — workspaces, projects, tables of items and subitems, project documents, record comments, and the AI agents that automate a table. Use this skill whenever someone wants to look at, report on, or change work their team tracks in HubSpot Work — find a tracker or board, see what's overdue, blocked or assigned to someone, add tasks, update or bulk-update statuses, mark things done, comment on or @mention someone about an item, read a project's documents, or explain what a project's agents do — even when they only say "my tracker", "the launch board", "our onboarding table" or "my tasks in Work". Not for CRM records (contacts, companies, deals, tickets, CRM tasks), CRM workflows, or HubSpot developer projects, which have their own skills.
I Ching wisdom advisor — activates when the user mentions keywords such as 周易, 易经, casting a hexagram, divination, hexagram image, 八卦, or the sixty-four hexagrams. Provides three casting methods (coins, numbers, time), lookups for the sixty-four hexagrams, multi-dimensional readings of hexagram images, I Ching philosophical analysis, and decision-making reference.
Make YouTube Shorts that hold attention with Pexo — vertical 9:16, fast-paced, hook in the first 3 seconds. Describe your topic and Pexo writes the script, generates the shots, picks the models, and assembles a finished Short with music and captions. Use for YouTube Shorts: "youtube short", "make a youtube short", "shorts video", "short-form video". NOT for long-form or landscape video.
Migrates an app, renderer, catalog or agent that uses A2UI (or a predecessor such as Flutter `genui`) to a newer SDK or protocol version. Use when a task mentions migrating, upgrading, porting or moving A2UI code between SDKs, packages or protocol versions (v0.8, v0.9, v0.9.1, v1.0), when a dependency such as `genui`, `a2ui_core`, `@a2ui/web_core`, `a2ui-core` or an A2UI Swift package needs a major bump, or when payloads or fixtures must change wire version. The skill first identifies the language, the source and the target, then routes to a case-specific guide where one exists.
Make one video accessibility-ready: captions on, on-screen text sized and contrasted to be readable, pacing checked so every step can be followed. Use when the user says "accessibility pass", "make this video accessible", "check WCAG for my video", "is this readable for everyone", or "prep this for an accessibility review".
When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad copy variations,' 'ad creative,' 'generate headlines,' 'RSA headlines,' 'bulk ad copy,' 'ad iterations,' 'creative testing,' 'ad performance optimization,' 'write me some ads,' 'Facebook ad copy,' 'Google ad headlines,' 'LinkedIn ad text,' or 'I need more ad variations.' Use this whenever someone needs to produce ad copy at scale or iterate on existing ads. For campaign strategy and targeting, see ads. For landing page copy, see copywriting.
Annotate an existing video with callout boxes and arrows that point at the exact buttons and fields the narration mentions, appearing and leaving in time with the voice. Use when the user says "add callouts", "add arrows", "annotate my video", "point at the buttons", "label the steps on screen", or "highlight where to click".
Put the takeaway on screen: add short text overlays that surface the key point of each section of an existing video as it's narrated. Use when the user says "add key points on screen", "add takeaway text", "put the main points as text overlays", "reinforce the message visually", or "viewers skim - make the points readable".
Replace a video's cold open with a 5-second hook that states the payoff or problem up front, before the walkthrough starts. Use when the user says "add a hook", "the opening is boring", "it takes too long to get to the point", "give it a stronger start", "lead with the payoff", or shares a video that opens straight into a UI with no reason to keep watching.
Build AI agents and automate Claude Code programmatically via the Claude Agent SDK and headless CLI mode. Covers Python SDK, claude -p, SDK MCP servers, hooks, sessions. Triggers on: "build an agent", "agent SDK", "headless mode", "automate Claude", "programmatic agent".
Use this skill when creating, reviewing, or editing Agent Skills-format skills, or when implementing skill discovery and loading in an agent client. It covers directory structure, SKILL.md metadata, progressive disclosure, evals, and repository conventions. Do not use this skill for general software work that does not involve the Agent Skills format or lifecycle.
Design, review, and debug agent workflows, and decide when a request should use a prompt, instruction, skill, agent, or hook before escalating to multi-agent design. Use for .agent.md / .instructions.md / .prompt.md / AGENTS.md work, workflow architecture, orchestration planning, scheduled automation model allocation, or when agent workflows may be overkill. Triggers on 'agent workflow', 'create agent', 'automation models', 'ワークフロー設計', 'orchestrator'.
Full-pipeline AI skill for producing PowerPoint presentations, benchmarked against top-tier consulting firms such as McKinsey and Deloitte (Aham UI v6.1 · Office track · PPT). Triggers immediately when the user says "帮我做PPT", "做演示文稿", "做一个汇报", "根据这份资料做PPT", "做客户方案PPT", or "制作幻灯片". Triggers even if the request is a single sentence. Eight-stage modular process: specification loading → material analysis → argument distillation → narrative skeleton → outline and layout → sample approval → page-by-page design → quality check and delivery. Built-in adaptive coaching mechanism that guides users of any skill level to above-passing output. Note: this skill is for PowerPoint / pptx output; for the SVG/HTML version see the ppt-svg skill.
Expert in building comprehensive AI systems, integrating LLMs, RAG architectures, and autonomous agents into production applications. Use when building AI-powered features, implementing LLM integrations, designing RAG pipelines, or deploying AI systems.
Diagnoses ClickHouse table design - partitioning, ORDER BY and primary key, column count, Nullable usage, identifier length and materialized view structure. Use for schema anti-patterns, too many partitions, oversized partitions, bad sort keys and materialized view design problems.
Audit and complete the Amazon Seller Central Attributes section for a listing. Diffs the category template against the filled fields, ranks the missing fields by impact on AI-driven search (Rufus, Alexa+) and traditional ranking, and proposes the optimal values. Use when a user asks about the Attributes section, missing attributes, product attributes, category fields, or \"how to fill the back end of my listing\". Trigger phrases: \"attributes\", \"attributes section\", \"category fields\", \"back end fields\", \"missing attributes\". Works with zero tools.
Build the optimal 250-byte Amazon backend search term string. Collects every candidate keyword, removes anything already indexed in the title and bullets, strips duplicates and Amazon-prohibited terms, prioritizes by search value, and packs the field to the byte limit. Use when a user asks about backend keywords, search terms, the hidden keyword field, generic keywords, "Search Terms" in the listing back end, or wants to fix wasted backend space. Trigger phrases: "backend keywords", "search terms field", "hidden keywords", "250 bytes", "generic keywords". Works with zero tools. the user pastes the current title, bullets, and any keyword list.
Plan Amazon Brand Tailored Promotions: targeted discounts sent to specific shopper audiences such as repeat customers, recent customers, brand followers, cart abandoners, and high-spend shoppers. Picks the right audience, the right discount depth, and the right goal for each promotion. Use when a user asks about Brand Tailored Promotions, targeting past customers with a discount, re-engaging repeat buyers, rewarding brand followers, or winning back lapsed customers. Trigger phrases: "brand tailored promotions", "BTP", "target repeat customers", "win back customers", "brand follower discount". Works with zero tools. The user describes their brand and audience sizes.
Guide a seller through getting ungated in a restricted Amazon category or brand. Identifies what is gated, what documents Amazon wants, how to source a compliant invoice, and how to submit an approval request that passes the first time. Use when a user asks about ungating, restricted categories, getting approved to sell a category or brand, gated products, or an approval request that was denied. Trigger phrases: "ungating", "restricted category", "get approved to sell", "gated", "category approval", "brand approval", "invoice for ungating". Works with zero tools.
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.
