Skills
99,448 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Generate images with GPT Image 2 (ChatGPT Images 2.0) inside Claude Code, using your existing ChatGPT Plus or Pro subscription — no separate OpenAI access, no per-image billing. Supports text-to-image, image-to-image editing, style transfer, and multi-reference composition via the local Codex CLI. Triggers on "gpt image 2", "gpt-image-2", "ChatGPT Images 2.0", "image 2", or any explicit ask to generate or edit an image through the user's ChatGPT plan.
Build a native macOS app using xcodebuild from the command line. Use this skill whenever the user asks to build, compile, or check if their macOS project compiles successfully. Also use it when the user asks to fix build errors, verify changes compile, or run a debug build. Trigger on phrases like "build the app", "does it compile", "run xcodebuild", "fix build errors", or even just "build".
MiMo V2.5 TTS speech synthesis. Generates speech with Xiaomi's MiMo V2.5 TTS model family. Activate this skill when text needs to be turned into speech, a voice message sent, content read aloud, or when the user asks to "say it out loud" or "reply by voice". Supports three modes — preset voice, voice design and voice cloning — plus natural language control and director mode, style tag control for tone, emotion and dialect, and singing with preset voices.
SAP Analytics Cloud (SAC) planning guidance for planning models, planning-enabled stories, data actions, multi actions, version management, data locking, calendar/input workflows, allocations, value driver trees, BPC live planning, and Seamless Planning with SAP Datasphere. Use this for planning design, planning APIs, data action debugging, planning performance reviews, and authenticated SAC planning story triage in Microsoft Edge via CDP; use sap-sac-scripting for non-planning SAC scripts and sap-datasphere for Datasphere modeling
Use this skill when the user wants to work with PowerPoint presentations. Triggers include: - Generating a new PPT from a topic: 'generate a PPT' / '帮我做个PPT' / 'PPTを作って' / 'PPT 만들어줘', 'create a presentation about X' / '生成关于X的演示文稿' / 'Xについてのプレゼンを作って' / 'X에 대한 발표 자료 만들어줘', 'help me make slides' / '帮我做幻灯片' / 'スライドを作って' / '슬라이드 만들어줘' - Imitating an existing .pptx style/template: 'use this template' / '用这个模板' / 'このテンプレートを使って' / '이 템플릿을 써줘', 'imitate this PPT' / '仿照这个PPT' / 'このPPTを真似して' / '이 PPT를 따라 해줘', 'imitate this style' / '仿照这个风格' / 'このスタイルを真似して' / '이 스타일을 따라 해줘' - Editing an existing PPT via natural language: 'modify slide N' / '修改第N页' / 'N枚目のスライドを修正して' / 'N번 슬라이드 수정해줘', 'change the background' / '更换背景' / '背景を変えて' / '배경 바꿔줘', 'add a slide' / '新增一页幻灯片' / 'スライドを追加して' / '슬라이드 추가해줘', 'make it more beautiful' / '美化一下PPT' / 'もっときれいにして' / '더 예쁘게 다듬어줘', 'edit this PPT' / '改一下这个PPT' / 'このPPTを編集して' / '이 PPT 수정해줘' - Local file operations on .pptx (no backend): 'delete slide N' / '删除第N页' / 'N枚目のスライドを削除して' / 'N번 슬라이드 삭제해줘', 'reorder slides' / '调整幻灯片顺序' / 'スライドを並べ替えて' / '슬라이드 순서 바꿔줘', 'merge pptx' / '合并PPT' / 'pptxを結合して' / 'pptx 합쳐줘', 'extract slides' / '提取幻灯片' / 'スライドを抽出して' / '슬라이드 추출해줘', 'how many slides' / '有多少页幻灯片' / 'スライドは何枚ある' / '슬라이드 몇 장이야'
Day 2 morning move of a Foundation Sprint. Forces generation of 3 to 7 candidate approaches as one-page summaries before the team converges on a top bet. Use after Day 1 is signed and before Magic Lenses on Day 2 afternoon. Enforces a minimum of 3 approaches to prevent first-idea anchoring. Each approach summary names what it is, why it serves the differentiators, and includes a simple visual.
Pre-sprint brief that locks scope, the decision the sprint must unlock, team and role assignments, logistics, inputs to bring, and success criteria before Day 1 of a Foundation Sprint. Use after the readiness verdict is Go and before the sprint begins. Produces a one-page artifact the team and Decider sign off on as the contract for the next two days.
Day 1 afternoon move of a Foundation Sprint. Converts the morning's Basics frame into a defensible strategic position by scoring differentiator candidates against customer-perceived value, choosing two committed differentiators, plotting alternatives on a 2x2 chart, writing decision principles, and producing a one-page Mini Manifesto. Use after Basics is signed; before Approach Options the next morning.
Day 2 end capstone move of a Foundation Sprint. Compresses the sprint's full strategic frame into a single canonical sentence (the Founding Hypothesis) plus an assumption scorecard, why-we-believe, what-could-prove-us-wrong, and recommended next validation step. Use after Magic Lenses is signed. Strict canonical template; paraphrase is not accepted in v0.1.0. The Founding Hypothesis is the spine artifact the sprint exists to produce.
Query Allium APIs for wallet PnL (current + historical, by-wallet and by-token), holdings timeseries history, Hyperliquid HyperCore trading data (info, fills, orders, orderbook), and custom SQL analytics across 70+ chains. NOT for token prices, token metadata, current wallet balance snapshots, transaction transfer history, or NFT metadata — for those use `alchemy-cli` (live work), `alchemy-mcp`, `alchemy-api` (app code), or `agentic-gateway` (no API key). Requires Allium credentials at `~/.allium/credentials`.
Design lens critique covering visual hierarchy, clarity, and anti-slop patterns — produces a findings table, no code edits unless asked. Use when the user wants a design review, says "what's wrong with this UI", or needs a second opinion before a handoff or presentation. Invoke when the user asks for critique on their UI, or mentions 'critique' alongside design / UI / frontend work.
Generate a high-cut-density action / fight scene by first composing a 16-cell storyboard image, then driving Seedance 2.0 image-to-video off that storyboard. Stacks GPT-Image-2 (character sheet + storyboard), Nano-Banana-2 (environment concept), and Seedance 2.0 i2v.
Rust profiling skill for performance analysis. Use when generating flamegraphs from Rust binaries, measuring monomorphization bloat with cargo-llvm-lines, analysing binary size with cargo-bloat, microbenchmarking with Criterion, or interpreting inlined frames in profiles. Activates on queries about cargo flamegraph, cargo-bloat, cargo-llvm-lines, Criterion benchmarks, Rust performance profiling, or binary size analysis.
Full Sentry SDK setup for Next.js. Use when asked to "add Sentry to Next.js", "install @sentry/nextjs", or configure error monitoring, tracing, session replay, logging, profiling, AI monitoring, or crons for Next.js applications. Supports Next.js 13+ with App Router and Pages Router.
Activate an Enhanced `MessagingChannel` (WhatsApp/Apple/Facebook/SMS/RCS) by PATCHing `MessagingChannelUsage.DeploymentStatus` from `Disabled` to `Provisioning` via the REST sobject endpoint. The UDD save-hook dispatches by `MessageType` for the external callout (`WHATS_APP`→Meta `/register`, `FACEBOOK`→`subscribeFacebookPage`, `TEXT`→`registerCsotSms`; Apple/LINE need none), writes the terminal `Active`/`Error`, and flips `IsActive`. Synchronous on the HTTP response — WhatsApp returns 204 after Meta confirms (~15-21s); no-callout channels are near-instant. No Aura RPC, no CSRF cookies. Use to activate an already-inserted Enhanced channel headlessly via REST. Do not use for full end-to-end setup — use `service-de-headless-channel-configure`.
Review custom components and layouts against shadcn design patterns, visual style conventions (Vega, Nova, Maia, Lyra, Mira), composition rules, design token usage, and Radix/Base UI composition patterns. Use PROACTIVELY after writing or modifying any custom UI component, page layout, or variant of a shadcn component. Use when the user says \"review this component\", \"check my spacing\", \"does this follow shadcn patterns\", \"audit this layout\", \"is this shadcn-idiomatic\", or shares a component for feedback. Catches spacing drift, hardcoded colors, missing data-slot attributes, inconsistent theme application, and composition anti-patterns that shipping-fast-with-AI tools often miss.
Day 3 (Wednesday) move of a Design Sprint that runs the art museum layout, heat map, speed critique, straw poll, Decider supervote, rumble-vs-all-in-one decision, and the storyboard that drives Thursday's prototype build. The most decision-heavy day of the sprint. Use Wednesday morning and afternoon after Tuesday's sketches are collected and attribution-stripped. Produces the canonical 5-15 step storyboard that becomes the build spec.
Day 1 (Monday) move of a Design Sprint that produces the bundled Monday artifact containing long-term goal, sprint questions (3-7 testable risks), customer or system map (5-15 step flow), expert interview notes, HMW (How Might We) cluster board, and the Decider's chosen target moment. Use Day 1 morning and afternoon after the sprint brief is locked. Sets the design target for Tuesday's sketches and Wednesday's storyboard.
Day 4 (Thursday) move of a Design Sprint that produces the planning artifact for the day. Output covers the prototype role plan (Maker, Stitcher, Writer, Asset Collector, Interviewer), prototype brief (what to build, fidelity bar, time allocation per role), canonical Five-Act Interview script (Welcome, Context, Intro, Tasks, Debrief), trial-run checklist, and Friday participant confirmation tracker. The actual prototype build is craft work outside the skill's AI invocation surface. Use Thursday morning after Wednesday's storyboard is signed off.
Day 5 (Friday) sprint-closing move of a Design Sprint that produces the bundled Friday artifact covering per-customer interview observations, best quotes, scorecard grid (sprint questions by customers), observed patterns, hot takes from each team member, and the Decider summary (build, iterate, pivot, or stop, plus highest-confidence learning, most important revision, and next artifact). Use Friday after Thursday's prototype passes trial run and during/after the 5 customer interviews. The sprint's payoff artifact.
Day 1 morning move of a Foundation Sprint. Forces explicit team choices on target customer, important problem, team advantage, and competitors and alternatives. Produces a single coherent strategic frame that becomes the input to Day 1 afternoon Differentiation. Use after the sprint brief is signed and Day 1 morning is scheduled. Bundled artifact, not four separate decisions.
Day 2 afternoon move of a Foundation Sprint. Evaluates the candidate approach set through multiple lenses (4 classic plus at least 1 custom) to surface trade-offs, identify consistent winners and contradictions, and produce a top bet plus a backup plan. Use after Approach Options is signed. Lens scoring is a sense-making tool, not mathematical truth; arbitrary precision is a smell.
Compare UX patterns across multiple reference apps using pattern libraries produced by ux-extract. Reads 2+ pattern-library.md files, walks them category by category, identifies where apps converge (strong signal), where they diverge (genuine design choice), what's unique to one app, and what's absent across the set. Produces an opinionated comparison document with recommendations for a new build. No browser needed — pure markdown analysis. Trigger with 'compare UX patterns', 'how do top apps handle X', 'ux comparison', 'pattern comparison across reference apps'.
Author, configure, structure, and troubleshoot OpenAPI/Swagger API reference documentation in GitBook. Use this whenever a task involves a GitBook OpenAPI block or `{% openapi %}` block, adding or updating an OpenAPI/Swagger spec in GitBook (by file or URL, via the API, MCP, CLI, or app UI), generating API reference pages from a spec, configuring the interactive "Test it" runner (auth, servers, CORS, proxy), customizing pages with GitBook `x-*` extensions (icons, titles, navigation hierarchy, code samples, enum descriptions), marking operations experimental/deprecated/hidden, or automating spec updates in CI/CD. Trigger even when the user only mentions GitBook plus OpenAPI, puts an `x-` extension on a spec destined for GitBook, or asks "why isn't my spec loading" or "why doesn't Test it work", without naming this skill.
TypeScript-first schema validation and type inference. Use for validating API requests/responses, form data, env vars, configs, defining type-safe schemas with runtime validation, transforming data, generating JSON Schema for OpenAPI/AI, or encountering missing validation errors, type inference issues, validation error handling problems. Zero dependencies, compact core (~5kb gzipped; zod/mini ~1.9kb).
Design MEL/SRHR data-collection instruments to IPPF/UNFPA publication standard: questionnaires, survey instruments, KII/IDI interview guides, focus group (FGD) guides, observation checklists, and topic guides, with disaggregation, consent, and care-referral for sensitive content built in by construction. Use when Ane asks for the data-collection tool itself, closing the gap between indicator design and analysis. Does not define indicators (indicator-designer) or analyse data.
Turn papers, study notes, and preliminary data into decision-grade research decks for lab meetings, PI review, grants, and seminars—with faithful numbers, evidence chains, and caveats. Use when the user asks for a research deck, lab meeting slides, study summary deck, academic review deck, or paper-to-slides for a faithful talk (not stylized social image decks). Create research decks with AI-native design and the highest aesthetic standards, powered by the K2F format and engine. Purpose-built for AI agents, K2F lets them focus on semantic content and design intent while automatically handling layout, typography, and formatting complexity.
Use when administering a Scenario team from an agent through MCP: restricting which models a team or project can run (model access control, allowlist, blocklist), inviting or removing team and project members, changing roles, capping a member's Creative Unit spend, creating or deleting projects, auditing API keys and their roles or scopes, or attributing consumption per user or model. Keywords: governance, model control, consumption cap, spend limit, API key hygiene, team admin, enterprise
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad pull requests, changes that grew beyond a fix, dependency additions, public API renames, config or CI edits, oversized hunks, and formatting-only files. Use when the user asks whether a change grew beyond the fix, a PR is too broad, or what unrelated stuff they touched, and wants keep, split, or justify guidance. Operates locally and offline.
Drive an Upstash Box (a remote sandboxed workspace) from the terminal with the `box` CLI. Use when asked to run commands, edit files, clone repos, run builds or tests, publish a public URL, browse or screenshot a page, open a pull request or issue with a screenshot attached, schedule recurring work, run an AI agent, or do any work inside a box rather than on this machine.
GNU binutils skill for binary manipulation and analysis. Use when using ar for static libraries, strip or objcopy for binary processing, addr2line for converting addresses to source locations, strings for text extraction, or c++filt for C++ name demangling. Activates on queries about ar, strip, objcopy, addr2line, strings, c++filt, ranlib, or binary post-processing tasks.
Estimate market opportunity (TAM, SAM, SOM) using multiple sizing frameworks (top-down, bottom-up, comparable company, analogous market). Triangulates across frameworks, highlights where they converge and diverge as signal, and produces a calibrated range with source-graded confidence labels. Refuses unbounded fabrications; always offers a labeled lower-confidence path when data is thin. Used for investment cases, go/no-go decisions, and stakeholder pitches.
Use this skill when a Salesforce Administrator needs to create OR maintain an institutional hierarchy for Education Cloud by parsing organizational structure from a PDF, URL, text, or CSV. On a first run it creates System, Campus, College, and Department Account records linked via ParentId plus 1:1 Business Profile records. On later runs it reconciles the org's existing hierarchy against the desired structure and applies only the delta — adding new units, renaming, or moving a node under a different parent — never recreating what exists. TRIGGER when the user wants to set up, configure, build, update, restructure, or reorganize a multi-campus structure, institutional hierarchy, or account hierarchy with business profiles; or add, rename, or move a campus, college, or department. DO NOT TRIGGER for single-campus flat setups without hierarchy levels, one-off manual account creation, or non-Education-Cloud account management
Create hand-drawn Excalidraw diagrams, flows, explainers, wireframes, and page mockups. Default to monochrome sketch output; allow restrained color only for page mockups when the user explicitly wants webpage-like fidelity. Use when the user asks for a diagram, flowchart, wireframe, sketch, visual explanation, mind map, architecture overview, or any Excalidraw-based drawing.
Linker and Link-Time Optimisation (LTO) skill. Use when configuring GNU ld, gold, or lld linker flags, diagnosing link-order issues or undefined symbols at link time, enabling LTO safely in real projects, or understanding inter-module optimisation trade-offs. Activates on queries about linker flags, -flto, thin LTO, LTCG, --gc-sections, link order errors, weak symbols, or linker scripts.
Read, fetch, extract, parse, or convert a URL or link into clean Markdown. Use FIRST whenever a user asks to read source content from a webpage, especially WeChat/微信公众号 mp.weixin.qq.com, Feishu/Lark docs, X/Twitter, PDFs, arXiv papers, or a URL that will feed a later summary, rewrite, article, podcast, or analysis. For WeChat and Feishu, prefer this specialist extractor over generic web open or generic content parsers. Exclude YouTube, pure web search, already-pasted text, and local non-PDF files.
Pre-sprint brief that locks challenge, sprint questions, team and role assignments, customer recruiting plan, prototype medium, interview format, logistics, and success criteria before Monday of a Design Sprint. Use after the readiness verdict is Go and before Monday begins. Produces a two-page artifact the team and Decider sign off on as the contract for the next five days.
Pre-sprint diagnostic that determines whether a team should run a Design Sprint now, postpone it, or do prerequisite work first. Produces a Go / Conditional Go / Wait verdict with diagnosis, recommended preconditions, attendee list, customer recruiting plan, and pre-sprint activities. Use when a team is considering starting a Design Sprint and wants a fast yes/no diagnosis before committing five days of team time and customer recruiting cost.
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.