GITHUB AGENT SKILLS / 技能收录
给你的 AI 助手
装上专业技能
我们从 GitHub 持续收录、审核并分类优质的 Agent Skills,按职业与使用场景整理,复制一行命令即可安装到 Claude Code、Cursor 等智能体。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
hyper-google-tagmanager
Use this skill when the user asks to install Google Tag Manager on a website, audit an existing GTM install or a Google tag that runs beside a container, design or change a GTM container (dataLayer, tags, triggers, variables, consent, ecommerce), verify that tags fire, diagnose broken or duplicate tracking, or analyze what a container and its data show. It reads the repository, the served page, and a container export with bundled scripts, writes framework-specific install code, gates container publishing and live consent changes behind explicit approval, and saves a report under `.hyper/gtm/`. Do not use for GA4 property administration or reporting alone, ad campaign setup, or a tracking plan written as a document.
hyper-google-analytics
[Hyper] Use this skill when the user asks to audit an existing Google Analytics 4 setup, install GA4 on a website, change property settings such as custom dimensions, key events, data retention, internal-traffic filters, or unwanted referrals, analyze report data with a Data API request, or diagnose analytics data that is missing, duplicated, or wrong. It reads the site code, the live page's collection requests, and the property configuration read-only, gates property writes and permanent filter effects behind approval, proves collection with network requests or DebugView instead of lagging standard reports, and saves a Korean report under `.hyper/google-analytics/`. Do not use for a search-visibility audit, a tag-manager container built for other vendors, Google Ads conversion setup, or legal advice on a privacy notice.
hyper-frontend
Use this skill when the user wants web frontend code built, fixed, matched to a visual reference, or checked in a rendered browser - a component, page, layout, form, animation, or responsive or state bug in HTML, CSS, JavaScript, React, Vue, Svelte, or Astro - where the job is how the interface is built to hold real content, keep one shape in every state, move safely, and be proven in a real browser. It builds inside the project's existing look, reads a concrete reference as a contract, and saves a report under `.hyper/frontend/[slug]/`. Do not use it for choosing or auditing the visual direction, project structure or tooling, native app UI, or reading a blocked page.
hyper-diagram
Use this skill when the user asks to draw, diagram, visualize, or map any structure - architecture, flowchart, data flow, sequence, state machine, ERD, class model, tree, mind map, timeline, schedule, or layered stack - as a polished standalone HTML plus a JPG by default, and a one-page vector PDF on request. Write a typed JSON spec, render it with automatic layout, and verify overlap, overflow, and page checks before delivery. Do not use for numeric data charts, UI mockups, illustrations, or slide decks.
hyper-decision
Use this skill when the user wants a decision API in software: a model call that returns a typed judgment (a yes/no probability, one option from a closed set, an ordered score, or an image box) instead of text, through TypeSafe Jev, OpenAI Decisions, Perplexity, Liquid, Cloudflare Clef, the Vercel AI SDK or AI Gateway, OpenRouter, or an emulation on a general LLM. It decides fit, writes typed questions, calling code, request templates, eval plans, audits of label-only LLM calls, and route setup. Do not use for chat or code generation, model training, moderation policy writing, or general prompt writing.
hyper-debug
Use this skill when a reported runtime failure - a stack trace, a failing test, wrong output, a crash, or an intermittent failure - needs a confirmed cause and a reproduction, plus a minimal fix only when the user authorized one. It reproduces first, tests at least two competing hypotheses against runtime evidence, proves the cause by toggling it, and journals under `.hyper/debug/`. Do not use for a deployment or platform failure, a product-language change request, a new feature plan, or a commit.
hyper-data
Use this skill when the user asks a question about a dataset - a CSV, Parquet, JSON, or database export - and wants the answer computed: totals, group comparisons, trends, distributions, joins, or a data-quality check. It probes the installed engines, chooses in-memory or in-place placement from a size and free-memory check, runs the smallest query that answers the question, and saves `.hyper/data/[slug]/report.md` with the answer first, then the query, grain, filters, null and duplicate handling, row counts, timing, and the input digest. Do not use for schema, migration, query-tuning, or index work; GA4 property report data; dashboard UI; or model training and forecasting.
yandex-connector
Use this skill when the operator needs Yandex Market data — price checks across many sellers, product ratings with their star breakdown, or buyer reviews. Trigger on Russian queries like "цена на Яндекс Маркете", "отзывы на маркете", "найди на яндекс маркете", "сравни предложения продавцов", or English equivalents. Skip for Wildberries/Ozon-specific tasks.
wb-connector
Use this skill when the operator needs Wildberries data — product price/availability checks, review pool analysis, seller identity and tax details, catalog category browsing, finding root_id (imt_id) for product variants, or comparing SKUs. Trigger on Russian queries like "цена на WB", "отзывы на вб", "найди на вайлдберриз", "кто продавец", "какие категории", or English equivalents. Skip for non-WB tasks.
taobao-connector
Use this skill when the operator needs Taobao marketplace data — search Chinese listings or read an item card. Trigger on Chinese or English queries like "taobao", "淘宝", "найди на таобао", "цена taobao". Always needs the operator's Chrome over CDP (signed mtop API). Skip for non-Taobao tasks.
ozon-connector
Use this skill when the operator needs Ozon marketplace data — product details, search, prices, ratings, or reviews. Trigger on Russian queries like "найди на озоне", "цена ozon", "отзывы на озоне", or English mentions of Ozon. Tier 1 (TLS impersonation) handles most queries with no browser; Chrome CDP is only the tier-2 fallback when Cloudflare challenges. Skip for non-Ozon tasks.
mpstats-connector
Use this skill for MPStats sales/stock analytics on a specific Ozon or Wildberries item — per-day sales, current price and stock, FBS/FBO warehouse split, seller/brand identity, and a rolling orders-per-day average. Trigger on "продажи товара на озон", "аналитика ozon sku", "mpstats по артикулу", "продажи за 30 дней", or English equivalents. Requires a paid MPStats account (MPSTATS_MP_AUTH env). Skip raw catalog price checks — use wb_/ozon_ connectors (no account needed).
megamarket-connector
Use this skill when the operator needs Megamarket data — search the catalog or read a product card. Trigger on "мегамаркет", "megamarket", "цена мегамаркет". Always needs the operator's Chrome over CDP (ServicePipe IP block). Skip for non-Megamarket tasks.
marketplace
Use this skill when the operator wants the full marketplace mount, routing metadata, or client setup. Trigger on "один MCP", "все источники", "marketplace_sources", "настроить marketplace", or "full marketplace". Route price questions such as "где дешевле" and "compare prices" to compare-prices; skip single-source tasks.
lamoda-connector
Use this skill when the operator needs Lamoda fashion data — search or a product card with sizes. Trigger on "ламода", "lamoda", "кроссовки lamoda". Cards try anonymous GraphQL first, then the operator's Chrome when it is refused; search needs Chrome over CDP. Skip for non-Lamoda tasks.
dns-connector
Use this skill when the operator needs DNS-Shop electronics data — search or a product card. Trigger on "днс", "dns-shop", "dns", "ноутбук днс". Always needs the operator's Chrome over CDP (Qrator proof-of-work). Skip for non-DNS tasks.
detmir-connector
Use this skill when the operator needs Detsky Mir data — prices and availability for kids' and baby goods, toys, strollers, nappies, kids' clothing. Trigger on Russian queries like "цена в детском мире", "детский мир наличие", "сколько стоит коляска", or English equivalents. Skip for general marketplace tasks; note that Detsky Mir has NO text search, so discovery goes through categories.
compare-prices
Use this skill when the operator asks where something is cheapest across marketplaces. Fans out to ten searchable sources — Wildberries, Ozon, Yandex Market, Avito, Taobao, Megamarket, Lamoda, DNS, Citilink and AliExpress (Detsky Mir is excluded — no text search; Taobao prices are reported in yuan, not ranked). Trigger on "где дешевле", "сравни цены", "сколько стоит X на маркетплейсах", "найди самую низкую цену", or English equivalents. Skip single-marketplace questions — use the per-marketplace skills.