AGENT SKILLS · ミッション装備

実際に使われている Agent Skills

公開リポジトリの検証済み Skills を比較し、機能、内容、導入状況、出典を確認してから追加できます。

掲載範囲: 検証済み
Skills: 21,476
リポジトリ: 3293
最終同期: 2026/10/22

21,476 Skills

verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

導入数: 2
GitHub Stars: 1.3万
更新日: 6月16日

whisper

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.

導入数: 2
GitHub Stars: 1.3万
更新日: 6月16日

workshop-facilitation

Facilitate workshop sessions in a one-step, multi-turn flow. Use when an interactive skill needs consistent pacing, options, and progress tracking.

導入数: 2
GitHub Stars: 6929
更新日: 9月1日

latex-conference-template-organizer

Organize messy conference LaTeX template .zip files into clean Overleaf-ready structure. Use when the user asks to "organize LaTeX template", "clean up .zip template", or "prepare Overleaf submission template".

導入数: 2
GitHub Stars: 5442
更新日: 8月27日

paper-self-review

This skill should be used when the user asks to "review paper quality", "check paper completeness", "validate paper structure", "self-review before submission", "audit claims", "check overclaiming", "verify whether results support claims", or mentions systematic paper quality checking. Provides comprehensive quality assurance checklist for academic papers.

導入数: 2
GitHub Stars: 5442
更新日: 8月27日

writing-anti-ai

This skill should be used when the user asks to "remove AI writing patterns", "humanize this text", "make this sound more natural", "remove AI-generated traces", "fix robotic writing", or needs to eliminate AI writing patterns from prose. Supports both English and Chinese text. Based on Wikipedia's "Signs of AI writing" guide, detects and fixes inflated symbolism, promotional language, superficial -ing analyses, vague attributions, AI vocabulary, negative parallelisms, and excessive conjunctive

導入数: 2
GitHub Stars: 5442
更新日: 8月27日

muapi-youtube-shorts

Auto-generate viral 9:16 YouTube Shorts (or TikTok / Reels clips) from a long-form video. Thin platform-aware wrapper around the AI Clipping skill — picks sensible defaults for short-form social platforms (9:16, 30–60s sweet spot) and delegates the actual highlight extraction + crop to muapi.ai's /ai-clipping endpoint.

導入数: 2
GitHub Stars: 4266
更新日: 9月8日

citation-verification

This skill provides reference guidance for citation verification in academic writing. Use when the user asks about "citation verification best practices", "how to verify references", "preventing fake citations", or needs guidance on citation accuracy. This skill supports ml-paper-writing by providing detailed verification principles and common error patterns.

導入数: 2
GitHub Stars: 5442
更新日: 8月27日

shopify-app-pricing

Merchant product subscriptions such as selling plans and subscription contracts use Admin, not App Pricing. For app monetization, MUST be used first for a new public app with pricing plans, paid tiers, recurring subscriptions, monthly or yearly options, usage pricing, or free trials. Shopify App Pricing is the default for supported public-app pricing models. Do not choose Admin GraphQL first merely because an app-monetization request asks for server-side code or mentions billing or subscriptions

導入数: 2
GitHub Stars: 543
更新日: 9月11日

on-page-seo-checker

Use when the user asks to "audit on-page SEO" or "diagnose why a single page dropped"; scores titles, meta, header structure, keyword placement, links, and images with prioritized fixes. Not for E-E-A-T / publish-readiness scoring — use content-quality-auditor; not for crawl / CWV / indexing — use technical-seo-checker. 页面SEO审计/排名诊断

導入数: 2
GitHub Stars: 2770
更新日: 9月12日

technical-seo-checker

Use when the user asks to "check technical SEO"; audits crawlability, indexing, Core Web Vitals, robots.txt, sitemaps, canonicals, redirects, and migrations. Not for on-page tags or content — use on-page-seo-checker. 技术SEO/网站速度

導入数: 2
GitHub Stars: 2770
更新日: 9月12日

xurl

A curl-like CLI tool for making authenticated requests to the X (Twitter) API. Use this skill when you need to post tweets, reply, quote, search, read posts, manage followers, send DMs, send or read end-to-end encrypted XChat messages, upload media, or interact with any X API v2 endpoint. Supports multiple apps, OAuth 2.0, OAuth 1.0a, and app-only auth.

導入数: 2
GitHub Stars: 1330
更新日: 7月21日

humanizer-zh

Remove signs of AI-generated, translated, or overly mechanical Chinese prose. Use when rewriting, editing, or reviewing Chinese blog posts, essays, newsletters, nonfiction chapters, product analysis, or long-form commentary so they read like native Chinese writing. Trigger this skill when the user asks to 「去 AI 味」, 「润色成中文母语表达」, 「改得像博客或书里写的」, 「减少翻译腔」, or similar. Detect and fix translation-like phrasing, empty big words, formulaic contrast frames, sloganized endings, list inflation, punctuation m

導入数: 2
GitHub Stars: 151
更新日: 5月22日

tinybird

Tinybird file formats, SQL rules, optimization patterns, and best practices for datasources, pipes, endpoints, and materialized views.

導入数: 2
GitHub Stars: 20
更新日: 7月29日

accessibility-fix

Remediation only — repair web accessibility (a11y) violations against WCAG 2.2 with a baseline, edit, and verify loop. Takes a target (URL, files, directory) or a findings worklist from accessibility-scan/accessibility-inspect/accessibility-audit, applies mechanical fixes as given, leaves TODOs for visual or contextual judgment, and verifies by re-running the baseline check. It only fixes. To find issues use accessibility-scan (one page, automated), accessibility-inspect (one page, manual), or a

導入数: 2
GitHub Stars: 98
更新日: 8月25日

animate

Animation patterns and best practices for Next.js/React applications. Use this skill when implementing animations, transitions, hover effects, page transitions, modals, or any motion in React components. Based on Emil Kowalski's "Animations on the Web" course.

導入数: 2
GitHub Stars: 91
更新日: 1月28日

coingecko

Crypto spot prices, OHLC charts, market discovery, and global stats. Use when looking up coin prices, market caps, trending coins, sector rankings, or comparing tokens (e.g. BTC price, ETH chart, top gainers).

導入数: 2
GitHub Stars: 27
更新日: 9月12日

twelvedata

Stocks, forex, and commodities prices: real-time quotes and historical bars. Use when looking up traditional-market prices (e.g. AAPL quote, EUR/USD chart, gold price, SPY history). Not for crypto.

導入数: 2
GitHub Stars: 27
更新日: 9月12日

shadcn-component-discovery

Discover shadcn-compatible components and registries across the entire ecosystem before writing any custom UI. Use PROACTIVELY before building tables, forms, modals, animations, dashboards, auth pages, or any UI component. Use when the user says "find a component for...", "is there something for...", "search registries", "what exists for...", or asks about shadcn blocks, Magic UI, Aceternity, ReUI, Animate UI, DiceUI, Tailark, AI Elements, or any other shadcn-compatible registry. Complements the

導入数: 2
GitHub Stars: 19
更新日: 4月27日

shadcn-component-review

Review custom components and layouts against shadcn design patterns, visual style conventions (Vega, Nova, Maia, Lyra, Mira), composition rules, design token usage, and Radix/Base UI composition patterns. Use PROACTIVELY after writing or modifying any custom UI component, page layout, or variant of a shadcn component. Use when the user says "review this component", "check my spacing", "does this follow shadcn patterns", "audit this layout", "is this shadcn-idiomatic", or shares a component for f

導入数: 2
GitHub Stars: 19
更新日: 4月27日

consolidate-notes

Promote existing research into a stable-status canonical article under articles/ in a Knowledge Base project (the knowledge-base starter pack). Read when a decision has actually been made and the team wants the source-of-truth written down, or when asked to consolidate, canonicalize, promote research, or supersede an older article. Carries the decision-confirmation gate, the supersedes: chain that keeps the evidence trail intact, and the canonical voice. Does not conduct new research — that is t

導入数: 2
GitHub Stars: 8
更新日: 9月10日

knowledge-base

How to work in a Knowledge Base project (the knowledge-base starter pack). Read when the project has the three-layer source-grounded layout — external-sources/ → research/ → articles/ — or when asked how this project is organized. Carries the layer model, per-folder rules, status flows, and log discipline so this guidance does NOT live inside template bodies or log.md. The three procedures live elsewhere: ingest in the platform open-knowledge skill, research and consolidate as their own sibling

導入数: 2
GitHub Stars: 8
更新日: 9月10日

research-with-sources

Investigate a topic against preserved sources and write a draft-status research article under research/ in a Knowledge Base project (the knowledge-base starter pack). Read when asked to research a topic, compare options, synthesize sources, gather evidence, or extend an existing research doc. Carries the full procedure: scan existing coverage, agree a research rubric, capture every source verbatim before analyzing, write the article incrementally so a crash never loses work, cite every claim, an

導入数: 2
GitHub Stars: 8
更新日: 9月10日

architecting-nestjs-modules

Designs NestJS feature modules with clean dependency boundaries, provider scopes, and dynamic modules. Use when adding a new feature module, splitting a monolithic AppModule, or fixing tangled imports between modules.

導入数: 2
GitHub Stars: 1
更新日: 5月3日

MIT3 ファイル

詳細を見る →