Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Expert knowledge for Azure Service Connector development, including troubleshooting, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use when connecting Azure compute to Redis, databases, storage, messaging, AI services, or third-party endpoints, and for other Azure Service Connector development tasks. Not for Azure API Management (use azure-api-management), Azure Connector Namespace (use azure-connector-namespace), Azure Logic Apps (use azure-logic-apps), or Azure Service Bus (use azure-service-bus).
Expert knowledge for Azure Service Fabric development, including troubleshooting, best practices, decision-making, architecture and design patterns, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use for designing Service Fabric clusters, Reliable Services/Actors, CRP/CRM, reverse proxies, or sfctl/EventStore APIs, and other Azure Service Fabric development tasks. Not for Azure Kubernetes Service (AKS) (use azure-kubernetes-service), Azure Container Apps (use azure-container-apps), Azure App Service (use azure-app-service), or Azure Functions (use azure-functions).
Expert knowledge for Azure Stream Analytics development, including troubleshooting, best practices, decision-making, architecture and design patterns, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use when building ASA jobs with Event Hubs/Kafka, Cosmos/SQL outputs, autoscaling, VNets/private endpoints, or edge/IoT workloads, and for other Azure Stream Analytics-related development tasks. Not for Azure Data Explorer (use azure-data-explorer), Azure Synapse Analytics (use azure-synapse-analytics), Azure HDInsight (use azure-hdinsight), or Azure Event Hubs (use azure-event-hubs).
This skill should be used when modeling agent mental states with BDI concepts: beliefs, desires, intentions, RDF-to-belief transformations, rational agency traces, cognitive agents, BDI ontologies, and neuro-symbolic AI integration
Bitflow DEX on Stacks — unified route ranking across SDK routes and HODLMM quotes, token swaps, market ticker data, HODLMM bin inspection and liquidity management, price impact analysis, and Keeper automation for scheduled orders. All operations are mainnet-only. No API key required for public routes during beta. Write operations require an unlocked wallet.
Adds to the project's persistent knowledge layer: context, features and playbooks. Use when the user explicitly asks to remember a project decision, save information to the knowledge base, or update a persistent feature description. Do not use for outcome specifications and work plans (/bro-give-me-spec, /bro-give-me-plan), temporary context or personal preferences
Generate a CawPlan status report over a date range: for a single product (progress, risk analysis, priority recommendations, summaries), for a Team (CawPlan product line), or for a named member — ticket-change-based completion, in the last two cases. Also lists product-wide open tickets by a requested label-backed category and optional title keyword, including backlog and cross-version tickets. Use when: the user asks for a product status report, progress report, risk summary, release readiness, priority recommendations, the open/unclosed tickets in a product's current or named version, or a product-wide filtered list such as "remaining Collage bugs"; asks how a Team/product line is doing over a date range; asks which product/Team/version tickets were reopened over a period; or asks how a specific member's task completion looks over a date range (not their own — use `cawplan-my-work` for "my tasks"). NOT for: raw activity feed, user activity, ticket creation, metrics dashboards, or critical issue lists.
A tool for generating Chinese software copyright application materials. Outputs the application form directly in Markdown and generates the source code, user manual, and design specification in LaTeX, compiling them into PDFs. Automatically analyzes project code and generates four documents: 60 pages of source code (30 pages each at the beginning and end), a user manual and design specification with headers and footers, and a Markdown application form. Checks consistency across information, including version numbers, bidirectional module coverage, and word limits. Suitable for software projects such as WeChat mini programs, web applications, mobile apps, and desktop apps. This Skill must be used when users mention software copyright, copyright applications, or copyright registration. It should also be used when users need copyright materials or documents prepared for any software project.
Multi-agent parallel orchestration for OpenClaw. Spawn AI agents as a team — parallel research, multi-model comparison, code pipelines. Proven 50-65% time savings. Trigger words: multi-agent, parallel agents, swarm, spawn multiple agents, parallel research, compare models, deep research, comprehensive research, detailed investigation, thorough analysis, research multiple topics, 多智能体, 多个Agent, 并行调研, 并行搜索, 同时搜索, 同时调研, 深度调研, 详细调研, 全面调研, 深度研究, 详细检索, 多角度分析, 全面分析, 多个模型, 让多个AI, 分别搜索, 同时搜索, 组建团队, Agent小队, 多Agent.
Clean, maintainable, human-readable code principles combined with anti-over-engineering discipline: naming, single responsibility, DRY, and scoping changes to exactly what was requested. Use when writing new code, refactoring existing code, reviewing code for quality, or deciding how much abstraction a change actually needs.
Structured screenshot analysis for UI implementation and critique. Analyzes every UI screenshot with a 5×5 spatial grid, full element inventory, and design system extraction — facts and taste together, every time. Escalates to full implementation blueprint when building. Trigger on any digital interface image file (png, jpg, gif, webp — websites, apps, dashboards, mockups, wireframes) or commands like 'analyse this screenshot,' 'rebuild this,' 'match this design,' 'clone this.' Skip for non-UI images (photos, memes, charts) unless the user explicitly wants to build a UI from them. Does NOT trigger on HTML source code, CSS, SVGs, or any code pasted as text.
Generate various documents based on the current project or code, including thesis sections, project overviews, key issues, and resume project descriptions. Use when users ask to generate thesis sections, project overviews, technical challenges, or resume project descriptions. For onboarding documents for new colleagues (new-hire guides, architecture docs, code walkthroughs, onboarding), use project-docs.
Compares two documents (docx, md, txt, pdf) to identify substantive differences, focusing on financial data, key clauses, and statistical discrepancies. Generates a formatted comparison report. Use when the user asks to “compare documents”, “check differences between files”, “find discrepancies”, “比对文档”, “查看差异”, “比较实质性差异”, or “核对合同”
Apply critical rationalist epistemology (Popper, Deutsch) to evaluate reasoning, identify errors, and refine understanding. Use when the user explicitly requests help with reasoning—phrases like “help me think this through,” “does this make sense,” “any flaws in this,” “what am I missing,” “critique this,” “is this reasoning sound,” “stress test this idea,” “devil’s advocate,” or any request to evaluate arguments, identify logical problems, or improve thinking. Also use when errors in reasoning are significant enough to materially affect the user's goals, even if not explicitly requested
You MUST use this when an implementation plan or a finished implementation needs an independent review by other agent CLIs - by default the opposite CLI (Codex for work done in Claude Code, Claude Code for work done in Codex), plus any reviewer the user names, Antigravity (Gemini) included - whether the user asks for a cross-review, a cross-cr, or a second opinion from the other agent. Replaces devflow cross-review. Same-host review belongs to cr-request and deciding on findings to cr-received; spec review and per-task review are outside this skill.
After completing any task that took more than ~5 tool calls, or after long-running builds/tests finish, load this skill and deliver a dad joke to lighten the mood. Also load before any user-requested joke, pun, or limerick. Never improvise jokes without loading this skill first.
Guides managers out of the bottleneck role — provides the Team Rep pattern, Epic Ownership model, Task-Relevant Maturity framework, kingdom ownership, and three-layer assignment strategy. Use when the user wants to delegate work or says "I'm doing everything," "team isn't taking ownership," "I can't let go," "team rep," "project ownership," "I'm the go-to person," "bus factor," "I work weekends," "how do I delegate," or "engineers don't take initiative." Do NOT use for managing a specific underperformer (use performance-reviews) or deciding what work to prioritize (use roadmap-planning).
Structural and accuracy review of documents: gaps, clarity, completeness, organization, and claims checked against the code. Use when a brainstorm, plan, spec, ADR, or any doc needs polish before the next workflow step. For exploring new ideas from scratch, use brainstorming instead.
Download videos from 1000+ websites (YouTube, Bilibili, Twitter/X, TikTok, Vimeo, Instagram, Twitch, etc.) using yt-dlp. Use this skill whenever a user shares a video URL, asks to save or download a video, wants to extract audio from an online video, needs a specific quality like 1080p or 4K, or mentions downloading a playlist. Also trigger on "下载视频", "保存视频", "提取音频", or any URL from a supported video platform.
Use when optimizing for AI search visibility where individual experts and entities outperform generic brand pages. Use when building cross-platform authority for people, organizations, or products that AI models should recognize and cite.
Add the official EU AI-content labels (EU icons for labelling AI-generated content, AI Act Art. 50) to images and videos. Use when the user asks to label, watermark, mark, or badge media as AI-generated, AI-modified, or a deepfake, mentions the EU AI icons / AI Act transparency disclosure, or asks to put an "AI" label/badge in a corner of a photo, screenshot, GIF or video.
Explains code with C4 model diagrams, analogies, and step-by-step walkthroughs. Use when explaining how code works, teaching about a codebase, onboarding to architecture, or when the user asks "how does this work?", "explain this system", "walk me through this", "what does this code do?", "help me understand this", "show me the architecture", "explain this service", "how is this structured?", "trace the flow", "what happens when X calls Y?", or is new to a codebase and needs orientation. DO NOT USE when: a one-sentence answer suffices — only invoke when an architecture overview, diagram, or step-by-step code walkthrough is the actual need
Export Figma variables to design token files in DTCG, CSS custom properties, Tailwind v4/v3, SCSS, TypeScript, JSON, Style Dictionary, or Tokens Studio. Use when the user wants to pull design tokens OUT of Figma into code — triggers: “export tokens,” “export Figma variables,” “generate CSS variables from Figma,” “turn my Figma variables into a tokens.json / Tailwind config / SCSS,” “sync design tokens to code.” Works on ANY Figma plan (reads via the Plugin API, not the Enterprise-only Variables REST API). For the reverse direction (code → Figma) use figma-import-tokens.
Hunt REAL bugs and security holes in the current branch diff — verified, not a raw model dump: map each changed file's attack and defect surface, run the security-and-logic checklist against it, then verify every candidate against surrounding code, callers, and existing mitigations — runs as a forked review workflow with its own reasoning budget, isolated from the main flow. Reports only findings that survive the false-positive check, severity-ranked with file:line evidence and a fix direction, and states an explicit clean result when nothing real is found; stays read-only and never edits code. Use when the user asks to find bugs, review changes, or audit branch risk.
Executes on-chain token swaps via Gate DEX. Use when the user wants to swap, buy, sell, exchange, or convert tokens, or bridge cross-chain. Covers the full swap flow: price quotes, transaction building, signing, and submission. Do NOT use for read-only data lookups or wallet account management.
Create and manipulate images using GIMP, Inkscape, ImageMagick, FFmpeg, ExifTool, OptiPNG, jpegoptim, and pdftoppm via CLI. Use for: resizing, cropping, compositing, text overlays, watermarks, color correction, format conversion, WebP export, SVG creation, SVG-to-PNG export, OG images, social banners, logo manipulation, batch processing, lossless compression, metadata read/strip, GIF creation, animation, PDF-to-image. Triggers: gimp, inkscape, imagemagick, resize image, crop image, convert image, svg to png, add text to image, watermark, composite, image editing, banner, social card, compress image, strip metadata, gif, pdf to image, webp.
Expert-level GraphQL API development with schema design, resolvers, and subscriptions. Use when the user mentions API, apollo, schema, resolvers, subscriptions, or relay, or when the task involves Schema Design, Queries and Mutations, Apollo Server 4, or DataLoader for N+1 Prevention.
Use this skill to modify a specific element in an existing HAP app with the hap command-line tool (CLI). Trigger for targeted, localized changes to an existing app, such as “add a field to a table,” “rename this view,” “modify a workflow,” or “give a role permission.” Do not trigger for creating, deleting, or updating business records, querying data, or writing code that calls hap. To build a complete new app from scratch, use hap-mcp-app-builder instead.
Use this skill when querying, filtering, or summarizing business data in HAP worksheets with the hap command line—especially when filters are complex, require multiple AND/OR conditions or nested groups, or when creating pivot table aggregations (sums/counts/averages/grouping dimensions). Trigger whenever the user says “find records in a table that meet … conditions,” “filter data by status/date,” “how do I write this filter,” “calculate monthly/category totals,” or “create a pivot/summary,” even if they don’t explicitly name the tool. Not for writing data (use the record command to add, delete, or update records).
Use hostc when an agent needs to expose a local development server as a temporary public preview URL, share localhost with another device or teammate, test webhooks against a local app, or create a public tunnel for localhost. Trigger on public preview, share local app, expose localhost, tunnel localhost, webhook preview, remote preview, or similar requests.
Use when the user wants to reverse-engineer an existing image ad into a reusable prompt template. Validates via Arcads, choosing gpt-image-2 or Nano Banana at Phase 1. Triggers on “clone this ad as a template,” “reverse engineer this ad,” “turn this ad into a prompt,” “extract a template,” “make this ad reusable,” “add to my prompt library,” or “study this ad and make a template.” Input must be an existing ad image; does not trigger for fresh generation (use chatgpt-image-ad or nano-banana-image-ad).
Collect a redacted local diagnostic bundle (logs, config, version, state) for an OpsMill expert hand-off. TRIGGER when: Infrahub is broken/failing/erroring, the user asks for help debugging, wants to collect logs/diagnostics, prepares a hand-off for OpsMill support, or reports a crash/timeout/connection issue (upgrade failure, stuck branch, container CrashLoopBackOff, 500s, OOM). DO NOT TRIGGER when: debugging a check, transform, generator, menu, or schema in the repository (use the infrahub-managing-* skills), a bundle has already been collected and the user wants it analyzed (use infrahub-analyzing-diagnostics), filing a public GitHub issue (use infrahub-reporting-issues), running operational queries (use infrahub-analyzing-data), or planning an upgrade that has not run yet (use infrahub-planning-upgrades).
Discover, query, and analyze Israeli government open data from data.gov.il (CKAN API). Use when user asks about Israeli government data, "data.gov.il", government datasets, CBS statistics, or needs data about Israeli transportation, education, health, geography, economy, or environment. Supports dataset search, tabular data queries, and analysis guidance. Pair with the MCP servers listed below for direct tool access from your agent. Do NOT use for classified government data or data requiring security clearance.
Calculate cryptocurrency capital gains tax under Israeli Tax Authority (Reshut HaMisim) rules and generate capital-gains reporting data and Form 1399י advance-payment data (within 30 days of each sale). Use when a user needs to calculate crypto tax using FIFO cost basis, classify DeFi income (staking, liquidity mining, airdrops), prepare annual filing data, understand advance payments (mikdamot) and reporting duties, or handle unreported crypto from past years now that the Voluntary Disclosure Procedure (Nohal Gilui Mirtzon) has closed. Covers Section 88 of the Income Tax Ordinance, Circular 2018/05, the 25% capital gains ceiling for individuals, and the surtax (3% above NIS 721,560, plus 2% on capital income that itself exceeds it; frozen through 2027). Do NOT use for non-Israeli tax jurisdictions, general income tax calculations, or VAT (maam) on crypto business activities, which require separate professional consultation.
Validate and format Israeli identification numbers including Teudat Zehut (personal ID), company numbers, amuta (non-profit) numbers, and partnership numbers. Use when user asks to validate Israeli ID, "teudat zehut", "mispar zehut", company number validation, or needs to implement Israeli ID validation in code. Includes check digit algorithm and test ID generation. Do NOT use for non-Israeli identification systems.
Cache and refresh remote git repositories under ~/.cache/checkouts/<host>/<org>/<repo> so future references can reuse a local copy. Use this skill when the user points you to a remote git repository as reference or you encountered a remote git repo through other means.
调试与验收 MaaFramework（MaaFW）应用（开发态、设备在线）：节点识别失败、点击不落点（识别成功 ≠ 点击生效）、ROI 校准与调参、单节点验证、流程卡死、controller 连接、pipeline_override 生效验证、端到端验收（含 pipeline / custom / interface 改完、声明完成 / 交付 / 开 PR 前的真机跑通）。按配置 / 识别 / 动作 / 流程 / 验收五层分诊，产出定位结论与证据，修复交接 maafw-pipeline / maafw-interface / maafw-custom。Use when debugging or acceptance-testing a MaaFW app with a device attached — recognition failures, clicks that miss, ROI tuning, stuck flows, controller faults, pipeline_override checks, pre-delivery acceptance.
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.