Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Default image generation and image editing skill for AI agents. Use this skill for general requests to generate images, create pictures, draw illustrations, make posters, design wallpapers, produce avatars, edit photos, optimize images, restore images, upscale images, combine images, or merge reference images using a configured OpenAI-compatible Images API endpoint. Also trigger on Chinese requests such as 生成图片, 生图, 画图, 生成海报, 做宣传图, 生成头像, 图片编辑, 改图, 修图, 优化图片, 图片增强, 图片合成, 多图融合, 参考图生图, and 最新生图模型调用. Prefer this skill over generic built-in image generation when it is installed and configured.
GraphQL Code Generator for TypeScript. Generates typed operations, hooks, and document nodes from GraphQL schemas. Use for type-safe GraphQL in frontend. USE WHEN: user mentions "GraphQL Codegen", "generate GraphQL types", "GraphQL TypeScript", "typed GraphQL", "client preset", "React Query GraphQL", asks about "GraphQL code generation", "type-safe GraphQL client", "fragment masking" DO NOT USE FOR: REST API types - use `openapi-codegen` instead; tRPC - use `trpc` instead; GraphQL schema design - use `graphql` instead; Manual GraphQL queries without codegen
Write prompts for MiniMax-H3-Image text-to-image generation and image editing, and optionally render them through the MiniMax API. Use when the user wants an image such as a poster, infographic, chart, product shot, UI screen, character, scene, storyboard or grid, wants to improve an image prompt, or wants to edit, combine or restyle reference images with MiniMax-H3-Image.
Write property-based tests using Hegel across Rust, Go, C++, TypeScript, Java, and OCaml projects. Use this skill whenever the user asks to write tests, add test coverage, or improve testing for functions, modules, or libraries — especially when the code has properties like round-trips, invariants, or contracts that hold across many inputs. Also triggers on: "property-based tests", "PBT", "hegel", "fuzz", "generative tests", "randomized testing", "test with random inputs", "shrinking", or when existing tests use proptest, quickcheck, rapid, gopter, rapidcheck, fast-check, jqwik, junit-quickcheck, qcheck, or crowbar.
Use when the user wants to add QQ platform support to the main branch of Hermes Agent stable, or explicitly mentions "add a QQ channel to hermes main", "install QQ support as a skill into Hermes", or "make stable Hermes support QQ and file sending". This skill patches the current repository into a version that supports QQ Bot, QQ file sending, QQ platform configuration, and toolset wiring.
Create retention-optimized opening hooks for any content type. Use when designing a video intro, newsletter opening paragraph, social post hook, or when the user mentions "hook", "opening", "intro", "first 15 seconds", "retention", or "how should I start this".
Hook design for Chinese web fiction. Use when the user wants to write an opening/first line, a golden-three-chapters hook, a chapter-ending cliffhanger, a paywall-node suspense point, or complains that the opening fails to keep readers. Produces several candidate hook options and explains the underlying hook mechanics.
Guide to creating and managing Claude Code hooks. Implementing PreToolUse, PostToolUse, Stop, and other hooks. When to use: (1) blocking dangerous operations, (2) suggesting actions after a tool runs, (3) cleaning up at session end, (4) customizing Claude Code. Example triggers: "create a hook", "PreToolUse hook", "block dangerous operations", "suggest after commit", "Claude Code hooks".
Create single-file HTML slide presentations with vanilla JS/CSS. Themed (terminal.css, catppuccin, nord), keyboard-navigable, with inline SVG diagrams and animations. Use when the user asks for an HTML presentation, slide deck, or single-file slides without a framework.
Query and manage Huawei Cloud HSS (Host Security Service) for daily security inspection and incident response. Covers host assets, vulnerabilities, security baselines, intrusion alerts (trojan/brute-force), login audit logs, risk scoring, and alert handling status updates. Read-only queries plus alert status marking — no isolation or antivirus actions. Use this skill when the user needs to inspect host security risks, investigate suspected intrusion, review vulnerability/baseline reports, or handle security alerts. Triggers include: 主机安全, HSS, Host Security Service, 安全巡检, 漏洞查询, 安全基线, 入侵告警, 木马检测, 暴力破解, 登录审计, 告警处置, 风险诊断, host security inspection, vulnerability scan, baseline check, intrusion alert, trojan detection, brute force, login audit, alert handling, risk diagnosis, security event response.
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.
Guide for creating, updating, and deprecating hybrid cloud RPC services in Sentry. Use when asked to "add RPC method", "create RPC service", "hybrid cloud service", "new RPC model", "deprecate RPC method", "remove RPC endpoint", "cross-silo service", "cell RPC", or "control silo service". Covers service scaffolding, method signatures, RPC models, cell resolvers, testing, and safe deprecation workflows.
Provides guidance on all Ignite UI for Angular data grid types (Flat Grid, Tree Grid, Hierarchical Grid, Grid Lite, Pivot Grid) including setup, column configuration, sorting, filtering, selection, editing, grouping, summaries, toolbar, export, paging, remote data, and state persistence. WHEN TO USE: users ask about grids, tables, data grids, tabular data display, cell editing, batch editing, row selection, column pinning, column hiding, grouping rows, pivot tables, tree-structured data, hierarchical data, master-detail views, or exporting grid data. WHEN NOT TO USE: non-grid UI components such as forms, dialogs, navigation, or charts (use igniteui-angular-components); theming or styling (use igniteui-angular-theming).
Implements, configures, and debugs Unity In-App Purchases, including subscriptions, receipt validation, and direct-to-customer payments via Stripe or Coda. Use when asked about real-money purchases or microtransactions, or migrating from native store billing, RevenueCat, Adapty, Essential Kit, or UniPay.
Implements a PostHog API (headless) survey inside the user's own codebase so it renders with their UI components and captures the exact events PostHog expects, then verifies the first response arrived. Use when asked to implement a survey, build a headless survey, build a custom survey UI, render a survey in my app, or wire up a survey of type `api` in a browser, server, or custom mobile UI. Covers the posthog-js event contract, server-side SDK capture, and post-implementation verification through MCP. To design or create the survey definition, use creating-surveys instead. For a survey that is implemented but not showing or not recording, use debugging-surveys.
Secures SaaS apps (Microsoft 365, Google Workspace, Salesforce, Slack) via CASB/SSPM deployment, conditional access policies, OAuth app governance, and session-level DLP controls enforcing identity verification and device compliance. Use when adding MFA/device-compliance conditional access, discovering shadow IT, governing OAuth consent grants, or applying session controls to sensitive SaaS data.
Compresses and clarifies an existing LLM prompt through concept elevation, verifying that no original instruction is lost. Use when the user says "improve this prompt", or when the user supplies a prompt or prompt file and asks to improve, tighten, optimize, or refine it. Not for writing a new prompt; use writing-system-prompts.
Generate Instagram marketing content from product URLs. Extract product information and create engaging Instagram posts with image suggestions, captions, and hashtags optimized for engagement. Use when user provides a product URL from e-commerce sites like Amazon, Shopify, Taobao, etc. and wants Instagram marketing content such as Image/text post ideas, engaging captions with CTAs, hashtag strategy, or Story/reels content suggestions.
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Create interactive iOS/mobile app UX flow prototypes as HTML documents with realistic phone mockups. Use when: (1) Visualizing user journeys and navigation flows, (2) Creating mobile app wireframes, (3) Documenting screen-to-screen navigation patterns, (4) Presenting iOS UI designs with annotations, (5) Prototyping app architecture before implementation. Generates self-contained HTML files with iOS-native styling, phone frames, flow arrows, and callout annotations.
Full health check of all your skills in one report. Use when the user wants to check for errors, find duplicates, detect broken skills, or get a complete overview of skill health. Pass --brief for inventory only. Trigger with '/janitor-report'.
Autonomous job application agent. Searches jobs, tailors resumes per JD, generates cover letters, fills ATS forms, and submits applications across 10+ platforms — fully hands-free. Triggers on: "apply", "job application", "auto apply", or job URLs.
Stop AI coding agents from shipping sloppy code — over-abstraction, drive-by refactors, obvious comments, extra files, unrequested deps, giant unreadable files, or fishing outside the workspace for “inspiration”. Use when writing or editing code, implementing features, fixing bugs, splitting or organizing files, or when the user mentions slop, cleanup, keep it simple, minimal diff, file too big, hard to navigate, or stay in the repo.
Provides comprehensive guidance for Koa.js framework including middleware, context, async/await patterns, and application structure. Use when the user asks about Koa, needs to create Koa applications, implement middleware, or build Node.js web applications.
Landscape evolution and surface process modelling in Python. Build 2D numerical models for erosion, hydrology, soil transport, and geomorphology. Use when the agent needs to: (1) Model landscape evolution over time, (2) Simulate river/stream erosion, (3) Route water flow across terrain, (4) Model hillslope diffusion processes, (5) Simulate weathering and soil production, (6) Analyze drainage networks, (7) Combine multiple geomorphic processes, (8) Load/save DEM data for modeling.
This skill should be used when the user asks to convert an academic paper in LaTeX from one format (e.g., Springer, IPOL) to another format (e.g., MDPI, IEEE, Nature). It automates extraction, injection, fixing formatting, and compiling.
Codifies the latest correction or mistake in the conversation as a short imperative rule in the project or global CLAUDE.md or AGENTS.md, after the user approves it. Use when the user says "learn from this mistake", or when the user asks to learn from a mistake, remember a lesson for next time, add a rule to CLAUDE.md, or not repeat a behavior. Not for a whole session; use running-retros.
Use this skill when the user needs OCR, scan recognition, image text recognition, document recognition, or conversion of PDF, images, Office documents, or URLs to Markdown. When legal material is detected, it can perform conservative optimization of legal terminology and document structure. Do not use it for legal fact judgment, filling in missing content, semantic rewriting, deep seal recognition, or chart entity analysis.
Integrates the LevelPlay ad mediation SDK via the Ads Mediation package. Use when the user asks about adding rewarded, interstitial, or banner ads, mediation or ad privacy setup, Android or iOS ad dependency build failures, or migrating from Unity Ads or IronSource APIs.
Define retention rules and erasure mechanisms (LGPD Arts. 15-16) reconciling subject's right to erasure (Art. 18, VI) with legal retention obligations (fiscal, labor, banking). Use when user asks 'retenção LGPD', 'quanto tempo guardar', 'eliminação de dados', 'soft delete vs hard delete', 'crypto-shredding', 'right to be forgotten'.
Use this skill when the user says 「记录选题」「新选题」「这个选题怎么样」「我有个想法」「帮我记一下」 or shares a rough content idea that needs evaluation and logging. Even if the user merely mentions a content idea in passing, proactively trigger the evaluation flow instead of waiting for an explicit 「记录」. First use the five-dimension logic of dbs-content to diagnose whether the topic is worth doing; log it only if it is, and by extension recommend 3-5 similar topics. Should not trigger: deepening a topic into an outline (use li-topic), writing a script directly (use li-writer), or AI polishing or beautifying topic titles. Use when the user wants to "record a topic", "log a topic idea", "is this topic worth doing", or shares a rough content concept needing diagnosis and logging.
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.