Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Expert knowledge for Azure SQL Managed Instance development, including troubleshooting, best practices, decision-making, architecture and design patterns, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use when planning MI networking, HA/DR, backups, Managed Instance link, or app connectivity patterns, and for other Azure SQL Managed Instance-related development tasks. Not for Azure SQL Database (use azure-sql-database), SQL Server on Azure Virtual Machines (use azure-sql-virtual-machines), or Azure Virtual Machines (use azure-virtual-machines).
Design and deploy a Threat Intelligence Platform (TIP) by integrating open-source CTI tools (MISP, OpenCTI, TheHive, Cortex) into a unified system with feed ingestion pipelines, enrichment workflows, STIX/TAXII interoperability, and analyst dashboards. Use when architecting or standing up a centralized CTI platform to collect, analyze, and disseminate threat intelligence across a security team.
Convert text to speech (TTS). Uses the Volcano Engine Doubao speech synthesis API and supports streaming synthesis, multiple voices, speech rate/pitch/volume adjustment, Markdown filtering, and LaTeX formula narration. Use this skill when the user wants to convert text to speech, generate read-aloud audio, create voice-overs or narration, make announcements, or mentions “text to speech”, “TTS”, “speech synthesis”, “read aloud”, or “voice-over”.
Organizes, redacts, and reports GitHub bugs for chengfeng-videocut. Use when the user asks to report a bug, report an issue with 剪口播, submit a GitHub Issue, tell the developers about a problem, or continue submitting a bug draft they have previewed. Do not use for feature requests, general troubleshooting, code commits, or automatic reporting without user confirmation.
Draft resonance diagnosis. You’ve finished a piece of content but aren’t sure it will connect—perhaps it won’t get views, resonate with the audience, or achieve a high completion rate. Submit the draft to this skill for a communication psychology-based diagnosis of whether it resonates, what the issues are, and how to fix them. Triggers: /dbs-resonate, “这个文稿有没有戳中人”, “帮我看看能不能发”, “这个完播率会不会低”, “文稿发出去有没有流量”. Draft resonance diagnosis. You finished a draft but aren't sure it will connect. Diagnoses psychological resonance issues and gives specific fixes. Triggers: /dbs-resonate, “will this resonate”, “check my draft”, “will people watch this”.
Structured fortune-telling workflow skill using MCP tools. Use when users ask for divination, 八字/四柱, 六爻, 紫微斗数, 塔罗, 大运, 运势/流年, or want standardized解读流程 (e.g., 八字先看身强弱与喜用神再看大运流年). Enforce fixed analysis order, call the right MCP tool, and produce actionable interpretations.
Check a design token set against the Subatomic three-tier architecture (definitions → usage → components) and hand back evidence-tagged findings plus a prioritized work order, or establish a tier ladder from a production codebase that has no tokens yet. Use when the user pastes their token JSON and asks "is this right?", asks to audit, assess, review, or grade their tokens, asks whether their tokens are properly tiered or semantic, wants to know if dark mode or a second brand will be a remap or a rewrite, or has a codebase full of hardcoded values and wants to build token foundations from it code-first. Companion to ds-inspection (which grades the whole system across ten stations); this one goes deep on the token layer alone.
Run, read, and diagnose a skill's Caliper eval — its success rate over k attempts, whether it fires, and whether it beats the agent without it. Use when the user wants to run, validate, interpret, or compare a skill's eval, or write an .eval.yaml spec whose tasks they have already decided.
Use this skill when users need to raise funding, create a pitch deck, prepare for investor meetings, understand the fundraising process, or navigate seed/pre-seed rounds. Activates for “how do I raise money”, “pitch deck”, “investors”, or fundraising questions
Complete design system reference for React applications. Covers colors, typography, spacing, component patterns, glassmorphism effects, GPU-accelerated animations, and WCAG AA accessibility. Use when implementing UI, choosing colors, applying spacing, creating components, or ensuring brand consistency.
Operate a Gitea instance via its REST API at /api/v1/... with curl. FORCED ROUTING — use this skill for any repository whose git remote host is not github.com: derive the candidate HTTPS base URL from the remote host, probe /api/v1/version, then call the REST endpoints directly.
Create, retrieve, update, and manage GitLab issues with full context gathering. Use when the user wants to create a new issue, view issue details, update existing issues, list project issues, or manage issue workflows on GitLab (glab CLI). If the user does not specify the platform, check the repository's git remote: use this skill only if the remote is GitLab — otherwise see github-issues
Jekyll blog publishing pipeline: generates articles in Iris's style (time-anchored opening, parenthetical asides, em-dash turns, Key Stats table), with frontmatter (title / date / canonical_url / hreflang_ja / hreflang_ko / FAQ schema), multilingual synchronization (en/ja/ko), and automatic internal linking. Invoke when the user says “write a blog post,” “publish a new article,” or “sync the Japanese and Korean versions.” Defaults to dev/B2B readers; 2C education/healthcare/finance (YMYL) content has different E-E-A-T requirements and distribution channels; see gingiris-seo-geo/references/2c-adaptation.md
Build software products autonomously via GSD headless mode. Handles the full lifecycle: write a spec, launch a build, poll for completion, handle blockers, track costs, and verify the result. Use when asked to "build something", "create a project", "run gsd", "check build status", or any task that requires autonomous software development via subprocess
Use when the user asks to “create a hook,” “add a PreToolUse/PostToolUse/Stop hook,” “validate tool use,” “implement prompt-based hooks,” “use ${CLAUDE_PLUGIN_ROOT},” “set up event-driven automation,” “block dangerous commands,” or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks, focusing on the advanced prompt-based hooks API
Huawei Cloud SWR enterprise instance management skill using hcloud CLI. Use this skill when the user wants to: (1) manage SWR enterprise instances - create/list/show/delete/update configuration, (2) manage instance namespaces - create/list/show/update/delete with security scanning settings, (3) manage instance registries (sync targets) - create/list/show/update/delete, (4) manage instance repositories - list/show/delete/update, (5) manage instance artifacts (image versions) - list/show/delete/scan, (6) manage instance credentials - long-term and temporary, (7) manage instance endpoints - internal/public access, (8) manage instance domains - add/list/show/delete/update, (9) check instance statistics and job status. Trigger: user mentions "SWR enterprise instance", "SWR 企业实例", "SWR 企业版", "企业仓库实例", "SWR instance", "SWR 专业版", "swr.ee", "instance namespace", "instance registry", "instance repository", "instance artifact", "instance credential", "instance endpoint", "instance domain", "企业仓库", "实例管理", "同步目标仓库", "sync target"
Guides interactive Horizon Platform SDK (PSDK) integration for Meta VR and Horizon OS Android/Kotlin apps—analyzes the codebase, recommends public platform features, plans the integration, and validates on device. Use for workflow guidance; use hz-platform-sdk for the detailed API reference. Build paths: Standard Android and Meta Spatial SDK; use hz-quest-verify-first if the path is unclear
Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly coupled modules, or make a codebase more AI-navigable.
Prepare, validate, and guide submission of Israeli VAT reports (Doch Maam) per Tax Authority standards. Use when user asks about VAT reporting, VAT calculation, "doch maam", "maam", Israeli VAT filing, VAT deadlines, or input/output VAT reconciliation. Supports monthly, bi-monthly, and annual reporting. Handles zero-rated exports and exempt transactions. Do NOT use for income tax, corporate tax, non-Israeli VAT systems, or bookkeeping statements such as profit and loss, balance sheet or trial balance (use israeli-financial-reports).
Create, validate, run, inspect, reuse, and edit Jinkō virtual-population subsampling designs with the jinko-sdk. Use whenever a completed Trial's simulated patients must be filtered or selected to match population-level targets, then emitted as a matched Vpop. This is SDK mechanics only: do not use it to choose scientific targets, filters, or algorithm settings; do not use it to create or run the source Trial, author a Vpop, or orchestrate a calibration workflow.
Apply Karpathy-style agentic engineering to any coding or building task. Use this skill when the user wants to set up an agent-driven workflow, needs to write a CLAUDE.md or AGENTS.md, wants to orchestrate agents with clear success criteria, or says things like "agent loop", "let the agent handle it", "agentic coding", "set up agent workflow". Includes the 7-step inner loop from Karpathy claude coding notes.
Create bulletproof Terms of Service and Privacy Policy documents for SaaS applications. Infers company information from codebase/marketing site, conducts comprehensive audits, drafts documents, then asks the user ONLY for missing details at the end. Minimizes user interaction. Use when the user needs to draft, review, or update legal documents (ToS, Terms of Service, Privacy Policy, legal pages). Triggers on requests for legal documents, terms drafting, privacy policy creation, "cover our bases legally", liability protection, or legal compliance for software products.
Expert in AT-SPI2 (Assistive Technology Service Provider Interface) for Linux desktop automation. Specializes in accessible automation of GTK/Qt applications via D-Bus accessibility interface. HIGH-RISK skill requiring security controls for system-wide access
Search and recall past AI conversations across Claude Code, Codex, Devin CLI, Grok, OpenCode, Pi, and ZCode via the `trellis mem` CLI. Use whenever the user asks to remember, find, or look up anything discussed in previous AI sessions across platforms, projects, or time. Triggers on phrases like "我之前跟 Claude/Codex 讨论过 X", "上次怎么处理 Y", "翻一下历史对话", "我们当时怎么决定 X 的", "为什么我们选了 X 而不是 Y", "find what I said about Z", "what did I discuss last week", "the rationale for choosing X", or "find the brainstorm where we picked Z over alternatives". Use even when the user doesn't say "history" or "recall"—any reference to past AI-conversation content should trigger this skill. The tool reads sessions directly from each platform's local storage; nothing is uploaded.
Expert-level monitoring and observability with Prometheus, Grafana, logging, and alerting. Use when the user mentions observability, Prometheus, Grafana, logging, metrics, or alerting, or when the task involves The Three Pillars of Observability, Monitoring Fundamentals, Prometheus Configuration, or Alert Rules.
A guided, zero-friction installer and maintenance assistant for OpenClaw. Use this skill when the user wants to install OpenClaw, set up OpenClaw on a local machine or remote server, connect OpenClaw to DingTalk, get OpenClaw skill recommendations for their use case, or perform post-installation maintenance (health checks, troubleshooting, installing new skills, changing AI models, adding chat channels, updating OpenClaw). Handles full environment detection, installation, optional DingTalk integration, scene-based skill recommendations, and daily maintenance — all interactively, with no wasted steps.
Transform outside-of-diff review files into properly formatted issue files for a given PR. Use when converting review files from ai-docs/reviews-pr-<PR>/outside/ into issue format in ai-docs/reviews-pr-<PR>/issues/. Automatically determines starting issue number and preserves all metadata (file path, date, status) from original review files. Don't use for inline-diff review files, non-PR review artifacts, or creating GitHub issues directly.
Bridges Claude Code and Codex sessions when native tools can't reach the target. Use for 跨产品通信 / 脚本回帖 / 送达排查: cross-product messages, hooks or scripts posting to a session, verifying delivery (Held messages included), shared-work ownership, or an inbound peer assertion. Not for same-product or parent/subagent messaging (use native tools), spawning agents, moving full history, or cross-machine pairing (deprecated).
Guide for testing Polar payment integrations using the sandbox environment. Use this skill when: (1) Setting up the Polar sandbox for development; (2) Testing checkout flows without real payments; (3) Using Stripe test cards with Polar; (4) Writing integration tests for payment flows; (5) Testing webhooks locally with the Polar CLI (`polar webhook listen`, `polar webhook trigger`) and generating webhook fixtures; (6) Mocking Polar in unit tests; (7) Setting up CI/CD pipelines with Polar sandbox; (8) Debugging payment issues in sandbox.
Download source video or audio from Douyin, YouTube, Bilibili, Twitter/X, Xiaohongshu, and other yt-dlp-supported URLs into the content-creation workspace. Use when the user says 下载视频, 下载音频, 保存这个链接, 把源视频拉下来, or when another video workflow needs a local source file before transcription, frame analysis, editing, reference replication, or archiving.
Implement retrieval-augmented generation systems. Use when building knowledge-intensive applications, document search, Q&A systems, or need to ground LLM responses in external data. Covers embedding strategy, vector stores, retrieval pipelines, and evaluation.
Search for hotels by location and dates. Use this skill whenever the user wants to find a place to stay, look for accommodation, search for hotels, or asks questions like "find me a hotel in X", "where can I stay in Y", "show me hotels near Z", or provides a destination plus check-in/check-out dates. Always use this skill before book-hotel or search-room since those require a sessionId from this search.
SonarCloud deep dive via its REST API: pull open issues (bugs, vulnerabilities, code smells), coverage/duplication metrics, quality-gate pass/fail with failed thresholds, security hotspots, and measure/analysis history for a whole project, branch, or PR, then return a ranked summary. Use whenever the user names SonarCloud or asks about code-quality metrics, technical debt, a red/failing quality gate, or static-analysis vulnerabilities/hotspots — e.g. 'why is the SonarCloud gate failing on this PR' or 'pull every BLOCKER vulnerability with file and line'. NOT for: the thin `/sonarcloud <query> <project>` slash command for a quick lookup (sibling 'sonarcloud'); replying to/resolving PR review threads across Greptile, CodeRabbit, or GitHub Actions ('review'); running local lint/type-check/test/security scans pre-ship ('validate'); implementing or patching a flagged issue ('dev'); or an external market/competitor report on SonarSource or DevSecOps vendors ('parallel-deep-research').
Provides comprehensive guidance for Spring Cloud microservices including service discovery, configuration management, load balancing, circuit breakers, API gateways, and distributed tracing. Use when the user asks about Spring Cloud, needs to build microservices, implement service discovery, or work with Spring Cloud components.
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.