OpenAgentSkill
GitHub200+

Skill rankings

New AI agent skills this week

Freshly indexed skills from the latest OpenAgentSkill import runs, useful for spotting new additions early.

Choose a ranking

Shown: 30 · Candidates: 480

Compare top 4
  1. 01

    jarvis-plan-review

    11-section rigorous design plan review covering problem framing, scope, architecture, security, observability, deployment, performance, reliability, testing, maintainability, and migration. Korean adaptation of gstack /plan-ceo-review, tuned for sole-developer + AI-pair-programming workflows. Not a rubber stamp — pushes plans toward best-in-class.

    @RamsbabySecurity20
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    26/100
    Quality
    54/100
    Freshness
    97/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  2. 02

    remember

    오너가 방금 말한/확정한 사실을 Jarvis 위키(`~/jarvis/runtime/wiki/`)에 즉시 주입합니다. 디스코드·Claude Code CLI·macOS 앱 어디서 호출하든 동일한 뇌에 쌓이며, source 태그로 호출 표면이 자동 구분됩니다. 오너의 명시적 "기억해" 요청이나 대화 중 확정된 사실·결정·선호를 즉시 영속시킬 때 사용합니다.

    @RamsbabyCoding20
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    26/100
    Quality
    48/100
    Freshness
    97/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  3. 03

    jarvis-deep-interview

    Convergent Socratic interview that turns vague requirements into a production-grade specification via 8-15 narrowing rounds with mathematical ambiguity gating. Inspired by Sorbh/interview-me, adds Contrarian/Simplifier Challenge Mode and JSONL decision log. Use when an idea exists but implementation decisions are still undefined.

    @RamsbabyOther20
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    26/100
    Quality
    54/100
    Freshness
    97/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  4. 04

    social-media-image-sizes

    Social media image sizes, video specs, safe margins, and character limits for 2026 on Instagram (feed 4:5 1080x1350, Stories and Reels 9:16), TikTok, Facebook, LinkedIn, X (Twitter), Threads, Pinterest (1000x1500 pins), Bluesky, and Mastodon, matching what SocialRobot prepares at publish. Resize or crop one master image for cross-posting, check file-size caps, then upload it with the SocialRobot MCP media tools so it publishes without bad crops. Use for "Instagram post size", "social media image sizes cheat sheet", "Pinterest pin size", "Facebook story size", "LinkedIn image size", "one image for Instagram, Facebook and LinkedIn", "my image got cropped", "character limit for LinkedIn / X / Threads". Scheduling the post is social-media-manager.

    @socialrobot-ioCreative0
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    0/100
    Quality
    41/100
    Freshness
    94/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  5. 05

    cleanup-dashboards

    Audit and consolidate HubSpot reporting dashboards. Identifies unused, duplicate, or outdated dashboards. Must be performed manually — no dashboard API is available.

    @TomGranotOther75
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    38/100
    Quality
    54/100
    Freshness
    100/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  6. 06

    bto-create-skill

    Giúp bạn biến một việc hay lặp lại thành skill của riêng mình, viết theo template SKILL.md một trang, chạy thử trên một ca thật, có eval đếm được và sổ feedback, rồi cài vào Claude Code hoặc Cursor. Dùng khi nói "tạo skill", "làm thành skill", "viết skill", "skill mới", "sửa skill", "create a skill", "turn this into a skill", hoặc khi bạn thấy mình dán lại cùng một prompt lần thứ hai. Không dùng khi việc chỉ làm một lần (viết prompt là đủ), hay khi cần một luật máy tự chặn được (làm hook hoặc script).

    @sonpiazCoding20
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    26/100
    Quality
    54/100
    Freshness
    72/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  7. 07

    bto-whats-next

    Triage phiên làm việc — trả lời "giờ làm gì tiếp?" bằng cách rà toàn session tìm việc dở, đề xuất bước kế, và phụ thuộc của thay đổi lớn. Dùng khi nói "làm gì tiếp", "what's next", "còn gì", "tóm lại session". Chỉ đọc và đề xuất — không tự làm.

    @sonpiazOther20
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    26/100
    Quality
    54/100
    Freshness
    72/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  8. 08

    bto-researchmarket

    Research sâu một thị trường bằng nhiều agent chạy song song, ra một bản research đã kiểm chứng, mọi nhận định gắn nhãn độ tin, số phải tự tính chứ không trích lại, bắt buộc có TAM SAM SOM. Dùng khi cần biết một thị trường có những ai, giá bao nhiêu, còn khoảng trống nào, trước khi build. Kích hoạt khi nói "research market", "research thị trường", "làm research về", "so sánh thị trường".

    @sonpiazResearch20
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    26/100
    Quality
    54/100
    Freshness
    72/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  9. 09

    bto-teardown

    Phân rã một sản phẩm có sẵn để hiểu ruột của nó, viết thành bản đặc tả sạch, rồi build bản của riêng mình trong một phiên làm việc mới chỉ đọc đặc tả. Đúng phương pháp clean-room hai đội mà ngành công nghệ dùng để học từ đối thủ không phạm luật. Kích hoạt khi nói "teardown", "phân rã sản phẩm", "reverse engineer", "build cái tương tự X", "sản phẩm X hoạt động thế nào".

    @sonpiazOther20
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    26/100
    Quality
    54/100
    Freshness
    72/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  10. 10

    bto-agent-team

    Playbook duyệt một lần rồi chạy tới xong — build → review độc lập → sửa → merge → verify — với nhiều agent theo role (backend, frontend, design, data) trong các wave. Dùng khi nói "chia wave", "duyệt một lần chạy tới xong", "/bto-agent-team", hoặc giao thay đổi nhiều phần cùng lúc. Khớp Buổi 7 Build to Own.

    @sonpiazDesign20
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    26/100
    Quality
    54/100
    Freshness
    72/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  11. 11

    excel-automation

    >

    @claude-office-skillsAutomation516
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    54/100
    Quality
    45/100
    Freshness
    0/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  12. 12

    ai-slop-detector

    Write without AI slop, or check a draft for it. Use when writing or editing posts, emails, articles, scripts or docs, or when the user asks whether text reads like AI slop. Covers 120 patterns in 9 categories.

    @FeedHiveOther21
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    27/100
    Quality
    49/100
    Freshness
    99/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  13. 13

    copywriting

    When the user wants to write or optimize short-form marketing copy—headlines, CTAs, ad copy, landing page copy, email copy. Also use when the user mentions "copywriting," "headline," "CTA copy," "ad copy," "landing page copy," "sales copy," "conversion copy," "PAS," "AIDA," "BAB," "copy formula," or "differentiation." For long-form article bodies (blog posts, guides), use article-content.

    @kostja94Marketing1,032
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    60/100
    Quality
    72/100
    Freshness
    87/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  14. 14

    article-content

    When the user wants to write, generate, or create article body content—blog post body, long-form content, how-to guide, listicle. Also use when the user mentions "write article," "article content," "blog post content," "article body," "long-form content creation," "generate article," "article draft," "how-to guide content," "listicle content," "information gain," or "content density." For single post page structure, schema, and SEO metadata, use article-page-generator. For blog index/listing page, use blog-page-generator. For short ad, landing, or email copy, use copywriting.

    @kostja94Marketing1,032
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    60/100
    Quality
    72/100
    Freshness
    87/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  15. 15

    url-slug-generator

    When the user wants to create, optimize, or validate URL slugs for content pages. Also use when the user mentions "URL slug," "URL path," "blog URL," "article URL," "short URL," "clean slug," "permalink," "slug optimization," "URL structure," "SEO-friendly URL," "create URL slug," or "SEO slug." For site-wide URL policy, use url-structure.

    @kostja94Marketing1,032
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    60/100
    Quality
    72/100
    Freshness
    87/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  16. 16

    top-banner-generator

    Deprecated compatibility entry for Top Banner construction. This component is now maintained in Bricks; install and use component-builder to build a new Top Banner.

    @kostja94Other1,032
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    60/100
    Quality
    66/100
    Freshness
    87/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  17. 17

    social-share-generator

    Deprecated compatibility entry for Social Share construction. This component is now maintained in Bricks; install and use component-builder to build a new Social Share.

    @kostja94Other1,032
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    60/100
    Quality
    66/100
    Freshness
    87/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  18. 18

    toc-generator

    Deprecated compatibility entry for Table of Contents construction. This component is now maintained in Bricks; install and use component-builder to build a new Table of Contents.

    @kostja94Other1,032
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    60/100
    Quality
    66/100
    Freshness
    87/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  19. 19

    sidebar-generator

    Deprecated compatibility entry for Sidebar construction. This component is now maintained in Bricks; install and use component-builder to build a new Sidebar.

    @kostja94Other1,032
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    60/100
    Quality
    66/100
    Freshness
    87/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  20. 20

    navigation-menu-generator

    Deprecated compatibility entry for Navigation Menu construction. This component is now maintained in Bricks; install and use component-builder to build a new Navigation Menu.

    @kostja94Other1,032
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    60/100
    Quality
    66/100
    Freshness
    87/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  21. 21

    configure-auth

    Add authentication and authorization to a Blazor Web App, accounting for the app's render mode. USE WHEN the user needs [Authorize] on pages, AuthorizeView, role or policy-based access, login/logout Identity pages, or AuthenticationStateProvider. Also USE WHEN auth state is null after WebAssembly loads, SignInManager throws in an interactive component, NotAuthorized content never renders in static SSR, or HttpContext.User is null in an interactive component. DO NOT USE for general component authoring (see author-component), for prerendering concerns unrelated to auth (see support-prerendering), or for managing non-auth cascading state (see coordinate-components).

    @managedcodeOther486
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    54/100
    Quality
    68/100
    Freshness
    99/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  22. 22

    3d-high-resolution-textures

    Build sharp, physically coherent high-resolution materials for 3D rendering with appropriate PBR maps, texel density, UV direction, mipmaps, anisotropic filtering, and progressive asset delivery. Use for detailed wood, stone, fabric, foliage, and architectural close-ups without excessive download or GPU memory costs.

    @MengToOther6,720
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    77/100
    Quality
    80/100
    Freshness
    87/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  23. 23

    3d-high-poly-models

    Create or integrate highly detailed 3D models with smooth silhouettes, shaped surfaces, believable bevels, and close-up geometry, then prepare suitable runtime LODs and loading. Use when a user requests high polygon counts, ultra-realistic models, detailed architectural assets, or removal of visibly faceted geometry.

    @MengToOther6,720
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    77/100
    Quality
    80/100
    Freshness
    87/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  24. 24

    3d-four-seasons

    Add coordinated spring, summer, fall, and winter states to a 3D scene, blending foliage, sunlight, sky, ground materials, snow, and particles without rebuilding the world. Use for seasonal controls, architectural walkthroughs, and outdoor scenes with four-season transitions.

    @MengToOther6,720
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    77/100
    Quality
    80/100
    Freshness
    87/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  25. 25

    avalonia

    Build and debug Avalonia 11/12 .NET applications with XAML, compiled bindings, MVVM, custom controls, desktop lifetimes, and platform publishing. USE FOR: Avalonia projects, bindings, commands, themes, UI dispatch, trimming, or Native AOT. DO NOT USE FOR: WPF, WinUI, MAUI, Uno, or Avalonia XPF compatibility work. INVOKES: inspect installed versions, implement, and validate on the actual target platforms.

    @managedcodeDesign486
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    54/100
    Quality
    68/100
    Freshness
    99/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  26. 26

    3d-falling-leaves

    Build recognizable falling leaves in world space using instanced geometry, independent tumble, coupled sideways drift, shared wind, scene occlusion, and camera-aware recycling. Use for 3D autumn leaves or drifting foliage in Three.js and similar scenes; use falling-leaves for a 2D canvas overlay.

    @MengToOther6,720
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    77/100
    Quality
    80/100
    Freshness
    87/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  27. 27

    ln-94-authentication-engineer

    Implements or repairs identity verification and session or credential lifecycle; not operation permissions, resource access policy or a new identity provider by default.

    @levnikolaevichOther576
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    55/100
    Quality
    63/100
    Freshness
    99/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  28. 28

    ln-93-configuration-engineer

    Establishes configuration ownership, validation, secret boundaries and environment isolation; not credential identity policy or live deployment.

    @levnikolaevichDevops576
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    55/100
    Quality
    63/100
    Freshness
    99/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  29. 29

    ln-92-container-engineer

    Builds, hardens or reviews container images and local runtime packaging with startup and shutdown evidence; not remote deployment or host administration.

    @levnikolaevichDevops576
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    55/100
    Quality
    63/100
    Freshness
    99/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100
  30. 30

    ln-91-engineering-baseline-builder

    Creates project technical rules and recurring local procedures from the actual stack; edits guidance only, not architecture targets or application code.

    @levnikolaevichCoding576
    Review before use

    Indexed

    View details
    Ranking signals

    Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

    Popularity
    55/100
    Quality
    63/100
    Freshness
    99/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    90/100

A shortlist from up to 480 directory candidates, not the entire registry. Stars belong to repositories. Signals are not safety guarantees or runtime verification.

How this list works

Only skills indexed within the last seven days, newest first. This is the registry addition date, not the repository creation date.

Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.

30-day snapshot data