Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Executes a structured incident response workflow based on NIST SP 800-61 Rev 2 and the SANS Incident Handler's Handbook. Auto-invoked when the user reports a security incident, asks how to respond to a breach, or needs help with incident classification, containment decisions, stakeholder notification, or evidence preservation. Produces an incident response plan with severity determination, containment decision tree, communication templates, and escalation criteria.
Xiaohongshu sensitive-word checker. Triggers when the user says "帮我查敏感词", "小红书违禁词检查", "检查下这篇笔记有没有敏感词", "小红书合规检查", "笔记审查", "文案排查" or "查一下有没有违规". It checks the user's Xiaohongshu note copy sentence by sentence against Xiaohongshu community guidelines and a high-risk word list, identifies potential sensitive words, prohibited words and risk points, and outputs a detailed check report with revision suggestions.
Chinese-language job application auto-fill skill: reads user-confirmed resume data in a browser, fills in job board application forms field by field, and verifies the results; use when the user types "/job-apply", or asks to auto-fill a resume or an application form.
Systematic research expert across all areas of Chinese law. ## Key features - Supports user identity recognition (ordinary person / law student / lawyer / judge or prosecutor) - Provides differentiated services based on identity - Complete legal source retrieval (statutes / administrative regulations / judicial interpretations / guiding cases / typical cases) - Quotation of original statutory text and mapping of cross-references between provisions ## Key trigger conditions (triggered when any is met) **High priority (must trigger)**: - Explicitly requests finding statutes / regulations / judicial interpretations / normative documents - Requests a judgment of legality / illegality ("is it illegal", "is it legal", "is there liability") - Requests compensation standards / compensation amounts / liability determination / procedural requirements - Asks "according to which law", "what does the law say", "what is the legal basis" **Medium priority (triggered in context)**: - "What should I do", "how do I defend my rights", "can I sue" - "What procedures are needed", "what conditions must be met" - "What else can I claim", "where can I file a complaint" ## Applicable scenarios - Labor disputes: unlawful termination, severance, work-related injury, social insurance, job transfer, etc. - Contract disputes: deposits, penalties, liability for breach, sales contracts, etc. - Tort liability: traffic accidents, personal injury, medical malpractice, environmental pollution, etc. - Marriage and family: divorce property, child custody, real estate inheritance, etc. - Administrative / criminal / corporate and financial, etc. ## When not triggered - Only asking about legal concepts / term definitions (not research) - Only requesting lawyer recommendations / legal services - Only discussing legal news / case stories (without specific regulations) - Only asking about legal exams / study questions **Note**: Even if the user does not explicitly request a "research report", it triggers this skill as long as it involves finding, organizing, interpreting, or applying legal norms.
Based on a case fact description, calls 8 atomic capabilities in combination to predict the charge, applicable legal provisions, sentence length and sentencing circumstances, and outputs a structured prediction report with a confidence assessment.
Comprehensive reference for LINE Front-end Framework (LIFF) SDK — building web apps inside LINE with authentication, messaging, QR scanning, permanent links, pluggable SDK, and LIFF plugin development. This skill should be used when the user asks to "build a LIFF app", "initialize liff.init()", "send messages from LIFF", "use Share Target Picker", "scan a QR code in LIFF", "create a permanent link", "develop a LIFF plugin", or mentions LIFF SDK, LINE Front-end Framework, CDN/npm integration, pluggable SDK tree-shaking, LIFF-to-LIFF transitions, LIFF browser vs external browser, Endpoint URL configuration, or server-side ID token verification from LIFF. Always use this skill whenever the user mentions LIFF, web apps inside LINE, or LINE Front-end Framework, even if they don't explicitly say "LIFF SDK".
Manage LLMem — structured memory system with SQLite-backed factual memory, semantic search, and background dreaming (decay, boost, promote, merge). Use when the user wants to: (1) add, search, update, or delete memories, (2) generate context for injection, (3) check memory stats, (4) run background consolidation/dream. Triggers on: "memory", "remember", "recall", "llmem", "memories", "forget", "consolidate memories", "dream".
Framework-agnostic internationalization (i18n) and localization (l10n) patterns for multilingual applications. Covers ICU message format, pluralization rules (CLDR), RTL layout with CSS logical properties, locale negotiation and detection strategies, SEO hreflang tags, cookie/header-based locale resolution, and translation workflow management. Use when adding multi-language support, choosing an i18n library, implementing pluralization or gender-aware messages, formatting dates/numbers/currencies by locale, handling RTL layouts, setting up locale detection, configuring hreflang SEO tags, or managing translation workflows.
Technical guide to integrate mapcn in React + shadcn projects. Use when the user asks to integrate mapcn, add mapcn to a shadcn app, use mapcn MapControls/Markers/Routes/Clusters, implement controlled viewport state, use the useMap hook, or access MapLibre through mapcn.
Design, implement, or review Material 3 and Material 3 Expressive interfaces for Android Compose, Android Views, Wear OS, and the web. Use for Material Design, M3, Material You, adaptive Material layouts, Material-focused Android UI modernization, or Material web component work; do not apply it to a non-Material design unless the user asks to adopt Material
Fix the errors reported by MegaLinter. Use after megalinter-check found errors, or when the user pastes MegaLinter/CI lint errors and wants them fixed. Applies safe fixes automatically (auto-fix linters first, then guided manual fixes using per-linter fix guides), asks the user when fixing is ambiguous, and can disable rules or linters with user confirmation. Never pushes to the default branch.
Provides expert-level analysis and diagnosis for Meta Ads campaigns. Use this skill to interpret performance data, identify root causes of issues, and generate actionable recommendations, with a special focus on correctly handling the 'Breakdown Effect'.
Create and compose tRPC middleware with t.procedure.use(), extend context via opts.next({ ctx }), build reusable middleware with .concat() and .unstable_pipe(), define base procedures like publicProcedure and authedProcedure. Access raw input with getRawInput(). Logging, timing, OTEL tracing patterns.
Use when the user says 'migrate elementor to gutenberg', 'convert elementor to blocks', 'remove the elementor dependency', or 'go back to native wordpress'. Maps Elementor widgets to core blocks and creates draft duplicates for review.
Writing style distillation skill — analyze multiple articles by one author, deeply reconstruct their thinking patterns and writing style, and generate a dedicated writing-twin sub-skill and style prompt. Supports automatic material collection across platforms such as WeChat Official Accounts and Douyin, and also allows manually pasting articles or specifying file paths. Trigger words: distill writing style, writing twin, clone writing style, replicate and distill writing skill.
Provides comprehensive guidance for MySQL including SQL syntax, functions, indexing, optimization, replication, backup, and high availability. Use when the user asks about MySQL, needs to write MySQL queries, design database schemas, optimize performance, or manage MySQL databases.
Generate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Nano Banana 2's strengths (rapid iteration, in-image typography rendering, predictable framing, optional web-grounded context), the resolution-tier pricing, the safety-tolerance dial, and when to route to Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream instead. Calls `runcomfy run google/nano-banana-2/text-to-image` through the local RunComfy CLI. Triggers on "nano banana", "nano-banana-2", "nano banana 2", "google image gen", "gemini image", or any explicit ask to generate with this model
REQUIRED for all image generation requests. Generate and edit images using Nano Banana (Gemini CLI). Handles blog featured images, YouTube thumbnails, icons, diagrams, patterns, illustrations, photos, visual assets, graphics, artwork, pictures. Use this skill whenever the user asks to create, generate, make, draw, design, or edit any image or visual content.
Generate videos using Google Veo models via the nano-banana CLI. Use this skill when the user asks to create, generate, animate, or produce videos with AI. Supports text-to-video, image-to-video animation, dialogue with lip-sync, and scene extensions. Trigger on requests like "create a video", "animate this image", "make a video clip", "generate footage", "produce a short film", "add motion to this".
Audit whether code that still has consumers really needs to keep existing, focusing on wrappers/facades, compatibility layers, stale public APIs, defensive branches, fallbacks, default values, configuration, duplicate sources, and hypothetical extension points. Use for code that is used but not necessary, legacy compatibility cleanup, meaningless wrappers, defensive code removal, cleanup with no compatibility requirements, deep necessity checks, and "is this still needed?" requests; do not use it as a pure unused/dead-code proof tool.
Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 8 major sources: Hacker News, GitHub Trending, Product Hunt, 36Kr, Tencent News, WallStreetCN, V2EX, and Weibo. Best for 'daily scans', 'tech news briefings', 'finance updates', and 'deep interpretations' of hot topics.
This skill should be used when the user wants to publish a package to npm, bump a version, release a new version, or mentions "npm publish", "bun publish", "version bump", or "release to npm". Handles version bumping, changelog updates, default-branch release delivery, scripted npm web login and bun publish confirmation (--local opens a browser, --remote prints a link). Do not trigger for unrelated uses of "release" (e.g. GitHub releases, press releases).
Check the consistency and authenticity risk between in-text citations and the reference list in NSFC proposals (read-only): verify whether bibkeys exist and check formatting issues in BibTeX fields and DOIs, and generate structured input for the host AI to assess item by item whether the in-text statement truly cites that reference; by default only output an audit report, without directly modifying the proposal or .bib (unless the user explicitly requests it).
Define knowledge bundles with Google's Open Knowledge Format (OKF) v0.1. Use when the user mentions OKF, Open Knowledge Format, Google's knowledge format, LLM wiki bundles, agent knowledge packs, creating OKF bundles, validating OKF documents, or converting knowledge into the OKF standard. Do not use this skill for unrelated requests; route to the nearest named specialist.
Open Source License guidance, selection, compliance review, and drafting. Use this skill when users ask about choosing open source licenses, checking license compatibility, reviewing projects for OSS compliance, generating LICENSE/NOTICE files, or understanding specific license terms. Triggers include questions about MIT, Apache, GPL, BSD, LGPL, AGPL, copyleft, permissive licenses, license compatibility, SPDX identifiers, or any OSS licensing topic.
Create specialized OpenCode agents with proper configuration for primary agents and subagents. Use when the user wants reusable OpenCode agent profiles, needs `agent/*.md` files or `opencode.jsonc` agent entries, wants to configure prompts/models/tool access, or needs to split work between a primary agent and subagents safely.
Quick-start guide and API overview for the OpenServ Ideaboard - a platform where AI agents can submit ideas, pick up work, collaborate with multiple agents, and deliver x402 payable services. Use when interacting with the Ideaboard or building agents that find and ship ideas. Read reference.md for the full API reference. Read openserv-agent-sdk and openserv-client for building and running agents.
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.