Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Expert knowledge for Azure Repos development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and integrations & coding patterns. Use when managing Git/TFVC repos, branch policies/PR checks, ELM migrations, GA Security, or SARIF scanners, and other Azure Repos related development tasks. Not for Azure DevOps (use azure-devops), Azure Pipelines (use azure-pipelines), Azure Boards (use azure-boards), Azure Test Plans (use azure-test-plans).
Turn any text, webpage, or URL into an HTML information card in the Claude/Anthropic design language, then capture it as a PNG with Playwright. Supports 14 formats: platform covers (WeChat Official Accounts, Channels, Bilibili, Douyin), image-and-text content cards (Xiaohongshu, tutorials, comparisons), social sharing cards (quotes, data, square), and long-form editorial layouts (Broadsheet, Feature, Reader, Digest). Use this skill when the user mentions “information card,” “card,” “cover,” “image-and-text post,” “layout,” “screenshot,” “generated image,” or “content card.”
Generates full consulting proposals from a brief. Input client name, problem description, and rough scope. Outputs proposal.md with executive summary, problem statement, proposed approach, timeline, team, pricing tiers, and terms. Researches client company for personalization. Multiple pricing models. Professional formatting matching consulting standards.
Use this skill to explain or reason about the foundational concepts of context engineering: what context is, the anatomy of a context window, how attention mechanics work, the U-shaped attention curve, why context quality matters more than quantity, and the mental models needed to interpret every other context-engineering decision. Use it for conceptual explanation, onboarding, and background reading. Route operational work to the specialized skills: debugging attention failures goes to context-degradation, token-efficiency work to context-optimization, conversation summarization to context-compression, and project-shape decisions to project-development.
Estimate what a codebase, branch diff, or single commit would COST to build — evidence-driven, not a guess: measure the real scope with the helper scripts (LOC counter + git session analyzer), classify every source line into one productivity bucket, run the cost calculator for engineering hours, organizational overhead, calendar and team-cost views plus Claude ROI, and sanity-check the effective lines/hour — runs as a forked analysis workflow with its own reasoning budget, isolated from the main flow. Keeps raw engineering hours separate from overhead and team multipliers, never presents a number without scope, assumptions, and a confidence level, and never claims region-specific market rates unless the user asked and that research was actually done. Use when the user asks to estimate development cost, effort, engineering hours, or ROI.
Diagnose whether writing matches the active writer, project, publication, and platform voice context, then offer a closer revision. Use when the user asks whether text sounds like them, feels generic, or has drifted from an established voice.
Exploits JWT algorithm confusion where the server's verification library trusts the alg named in the token header, by switching RS256 to HS256 (signing with the RSA public key as HMAC secret), setting alg to none, or injecting kid/jku/x5u headers to supply an attacker-controlled key. Use when testing RS256 JWT auth for algorithm downgrade, alg:none bypass, or key-confusion signature forgery.
Design forms that convert, validate well, resist spam, and integrate cleanly with downstream systems. Use this skill when designing or auditing any form (contact, signup, checkout, multi-step, embedded), planning validation logic, fighting spam, choosing form tooling, or improving form conversion. Triggers on form design, form validation, form conversion, multi-step form, form spam, captcha, honeypot, form abandonment, signup form, contact form. Also triggers when form completion rates are low or spam is overwhelming.
Create Huawei Cloud Flexus L Instance (Lightweight Server), deploy OpenClaw application platform on it, and support installation and configuration of models and channels for deployed OpenClaw instances. Web UI access needs to be manually enabled in Huawei Cloud console. Trigger words: "Deploy OpenClaw", "Deploy Flexus L Instance", "Deploy Huawei Cloud Lightweight Server", "Model setting", "Channel Setting", "部署OpenClaw", "部署Flexus L实例", "部署华为云轻量服务器", "设置模型", "设置通道"
Detect and humanize AI-generated Chinese text. 20+ rule detection categories + statistical features + scene-aware LR fusion (rule × 0.2 + LR × 0.8) trained on three scenes: general / academic / longform 长文本 (≥1500 字)。Unified CLI: ./humanize {detect,rewrite,academic,style,compare}. 8 style transforms (casual/zhihu/xiaohongshu/wechat/academic/literary/weibo/novel)。 Multi-paragraph rewriting + best-of-N humanize。165 replacement patterns + CiLin 同义词词林 38873。 Academic paper AIGC reduction for CNKI/VIP/Wanfang (知网/维普/万方 AIGC 检测降重)。 Pure Python, no dependencies, offline。v5.0.0 — HC3 fused 95%, 学术 -65 / 工作汇报 -83 / 长篇博客 -55。 Use when user says: "去AI味", "降AIGC", "人性化文本", "humanize chinese", "AI检测", "AIGC降重", "去除AI痕迹", "文本改写", "论文降重", "知网检测", "维普检测", "AI写作检测", "让文字更自然", "detect AI text", "humanize text", "reduce AIGC score", "make text human-like", "去ai化", "改成人话", "去机器味", "降低AI率", "过AIGC检测", "长文本改写", "小说改写"
Use this skill in the MathModel LaTeX sandbox when the user asks to reproduce built-in scientific visualization templates, especially prompts from the Improve tab mentioning $mathmodel-figure-templates, 科研绘图模板, SHAP蜂群柱状图, 配对云雨图, 交叉验证ROC, 泰勒图, 相关矩阵组合图, 预测真实值边缘分布图, TPE调参3D曲面, 下三角相关矩阵半边小提琴图, 分组环形热图, 城市公园降温组合图, or Nature和弦图. It provides ready-to-run Python scripts bundled inside the skill.
Run the Ouroboros specification-first development loop: reduce ambiguity with a Socratic interview grounded in live git data (commits, churn, contributors), freeze an immutable seed/spec, render the execution plan through spec-kit (/speckit.plan → /speckit.tasks), execute against that contract through cli-anything agent-native CLI harnesses (cli-hub, --json evidence), verify before claiming success, and keep looping until completion is actually verified. Use when the user wants spec-first clarification, git-aware interviews, immutable requirements, drift-aware implementation, harness-driven execution, or a persistent completion loop that should keep going until tests / checks / acceptance criteria pass. Triggers on: ooo, ouroboros, interview, seed, run workflow, evaluate, evolve, ooo ralph, specification first, socratic interview, git-aware interview, ambiguity reduction, execution plan, cli harness execute, persistent completion.
Performs pandas DataFrame operations for data analysis, manipulation, and transformation. Use when working with pandas DataFrames, data cleaning, aggregation, merging, or time series analysis. Invoke for data manipulation tasks such as joining DataFrames on multiple keys, pivoting tables, resampling time series, handling NaN values with interpolation or forward-fill, groupby aggregations, type conversion, or performance optimization of large datasets.
macOS screen capture, window recording, GIF conversion, and agent evidence bundles from the terminal. Built on ScreenCaptureKit for window-level targeting ffmpeg cannot do. Use when the user wants a screenshot of a specific window or app, a screen recording, a GIF conversion, a before/after diff, an evidence bundle for a PR, OCR text from a window, a terminal VHS recording, a Remotion render, or wants to watch a UI for changes. Requires macOS Screen Recording permission on first run.
You are a security expert specializing in dependency vulnerability analysis, SBOM generation, and supply chain security. Scan project dependencies across multiple ecosystems to identify vulnerabilities, assess risks, and provide automated remediation strategies.
Full-featured SEO, GEO, and AEO website audit tool. Analyzes any URL or website for Search Engine Optimization (SEO), Generative Engine Optimization (GEO — for AI-powered search engines like Perplexity, ChatGPT Search, and Gemini), and Answer Engine Optimization (AEO — for featured snippets and voice search). Use this skill whenever a user provides a URL, domain, or website and asks about search performance, SEO issues, rankings, AI search readiness, answer engine visibility, meta tags, schema markup, content quality, or visibility in search. Also trigger when the user asks to "audit my site", "check my SEO", "why isn't my site ranking", "optimize for AI search", or any similar request involving a web property and search performance.
Run keyword research, classify by search intent, cluster into topical groups, and prioritize for content production. Use this skill whenever the user asks to do keyword research, find target keywords, identify ranking opportunities, classify search intent, build a topical map, or plan a content strategy around what people search for. Triggers on keyword research, keyword strategy, search intent, keyword clustering, topic clusters, keyword difficulty, search volume, ranking opportunity, content gap, what should I write about, target keyword, primary keyword, secondary keyword, long-tail. Also triggers when planning a content calendar or new site without keywords yet defined.
Episode and season structure for TV series (剧集单集与季的结构) — teasers and cold opens, broadcast four/five/six-act grids with page anchors, three tests for finding the invisible acts in streaming scripts, act-out and cliffhanger taxonomies, Oberg's four information tools, A/B/C/runner weaving and scene-count ratios, the Calvisi pilot beat sheet, five-part scene structure, and season shape (tentpoles, bottle and container episodes, two-parters, finales). Merged from Calvisi, Douglas, Oberg, Landau, Goldberg & Rabkin, Miller, Rabkin and Blum, plus act lengths measured from published West Wing, Succession, Sopranos, Downton and Fleabag scripts. Use when breaking an episode into acts, deciding how many acts a script needs, placing act outs and cliffhangers, designing a teaser, weaving A/B/C stories and runners, beating out a one-hour pilot, auditing an episode that has no shape, reverse-engineering a show's structure, or planning a season's episode order (分幕、出幕、悬念结局、季弧、瓶子集).
Diagnose and fix Lingui SWC plugin compatibility errors with Next.js, Vite, Rspack, or other SWC runtimes. Use for errors such as “failed to invoke plugin”, “failed to run Wasm plugin transform”, “Failed to deserialize program received from host”, “Failed to execute SWC plugin”, “out of bounds memory access”, or “LayoutError” during builds with @lingui/swc-plugin — or when macros are silently not transformed (the build succeeds, but Trans/t render as raw untranslated output).
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
Vue 3 and Vue.js best practices for TypeScript, vue-tsc, Volar, and component patterns. Use when writing, reviewing, or refactoring Vue 3 components with TypeScript, configuring Volar/vueCompilerOptions, extracting component types, working with defineModel/withDefaults, setting up Pinia store tests, or debugging Vue tooling issues. Triggers on Vue components, props extraction, wrapper components, template type checking, strictTemplates, vueCompilerOptions, Volar 3, CSS modules, fallthrough attributes, defineModel, withDefaults, deep watch, vue-router typed params, Pinia mocking, HMR SSR, moduleResolution bundler, useTemplateRef, onWatcherCleanup, useId, generic components, reactive props destructure.
Full-repository code sweep. Scans every file with Warden, verifies findings through deep tracing, and creates draft PRs for validated issues. Use when asked to “sweep the repo,” “scan everything,” “find all bugs,” “full codebase review,” “batch code analysis,” or run Warden across the entire repository
Use when you need to add or review fuzz testing for Java APIs with CATS — including contract-driven negative testing, malformed payload validation, boundary input exploration, CI integration, reproducible failures, and local execution guidance. This should trigger for requests such as Add fuzz testing to a Java project; Use CATS for API negative testing; Review CI quality gates for API contract robustness; Improve boundary and malformed input test coverage; Run CATS fuzz tests against an OpenAPI contract. Part of Plinth Toolkit
Multi-agent adversarial code review. Spawns three reviewer subagents (Auditor, Adversary, Pragmatist) on a single model, runs a cross-examination round, then deterministically synthesizes a single ranked report. Use this for non-trivial PRs, security-sensitive changes, refactors that touch many files, or any change where one perspective has obvious blind spots. Trigger phrases include "adverse review", "adversarial review", "multi-perspective review", "review my changes from multiple angles", "panel review". NOT suitable for trivial diffs (typos, dependency bumps, formatting).
Use this skill for **on-chain DEX trading and wallet operations on EVM/Solana chains**: token swap quotes and execution, wallet portfolio/balance queries, gas estimation, transaction broadcasting, and token search/info on Ethereum/Solana/Base/BSC/Arbitrum/Polygon, etc. Use when the user says: 'swap ETH for USDC', 'buy token on-chain', 'DEX swap', '钱包余额', '钱包持仓', 'Uniswap', 'gas 费', '广播交易', '链上 swap', 'DEX 交易', '买币' (meaning an on-chain purchase). Powered by OKX Web3 DEX API. MUST run node scripts. **⚠️ Important routing note**: For **data queries** such as 'what major on-chain moves happened today / on-chain whales / smart money / what are the whales doing', do not start with this skill — use **aicoin-hyperliquid** first (Hyperliquid is a true on-chain perp DEX, and whale positions/liquidations/OI are real on-chain data available in the free/standard version), then add a CEX proxy comparison using big_orders / ls_ratio from **aicoin-market**. This skill's OKX Web3 interface is primarily for **trading actions** (swap/wallet balance), not data exploration; even though token.mjs has trending/hot_tokens, it requires the user to configure an OKX Web3 API Key, while the two data-query paths above do not. For CEX trading (Binance/OKX spot/futures), use aicoin-trading. For CEX market data (funding rates, OI, liquidations), use aicoin-market.
Detect PowerShell Empire post-exploitation framework artifacts in Windows Script Block Logging (Event ID 4104) and Module Logging (Event ID 4103), including the default launcher string, Base64-encoded WebClient/FromBase64String payloads, known module invocations (Invoke-Mimikatz, Invoke-Kerberoast), and staging URL patterns. Use when hunting for or confirming Empire C2 activity in Windows event logs
Use when defining or checking how a product speaks: tone of voice, terminology, canonical facts, register. Triggers: "tone of voice" / "тон оф войс", "brand voice" / "голос бренда", "брендбук", "наша терминология". Not for writing the text (copywriting). Refusal phrase "no brand" / «без бренда».
Create, inspect, convert, apply, replace, verify, troubleshoot, update, publish, or restore reversible CodeDrobe themes for supported Chromium/Electron AI desktop apps, including OpenAI Codex, Tencent WorkBuddy, QoderWork (CN/global), and TRAE SOLO (global/CN). Use when a user asks to turn an attached or local reference image into a Codex, WorkBuddy, QoderWork, or TRAE SOLO skin, reproduce a visual style with native UI, build a multi-app theme, work with .codedrobe-theme packages or theme images, analyze a live CDP DOM snapshot, repair DOM compatibility failures, use a custom port or installation path, capture verification screenshots, search the CodeDrobe store or install a store theme by name, publish or submit a theme to the CodeDrobe store, or migrate a legacy .codex-theme file.
Use to write one component's documentation entry from its code, stories and real call sites, such as "document the button", "write docs for Select", "what states does Toast have", or usage rules for a new or changed component. Not for foundations or pages that span components, which no skill here writes, nor for changing the component, which is build-design-system.
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.