Skill rankings

Highest quality AI agent skills

Skills with the strongest blend of adoption, freshness, metadata quality, and agent usage signals.

Shown: 30 · Candidates: 472

Compare top 4
  1. 01

    Canvas Design

    Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.

    @anthropicsDesign196,151
    Review before use
    Ranking signals

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

    Popularity
    100/100
    Quality
    100/100
    Freshness
    97/100
    Agent evidence
    78/100
    Evidence confidence
    92/100
    Install readiness
    100/100
  2. 02

    Webapp Testing

    Use Playwright to interact with and test local web applications, capture screenshots, debug UI behavior, and inspect browser logs.

    @anthropicsBrowser Automation196,151
    Review before use
    Ranking signals

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

    Popularity
    100/100
    Quality
    100/100
    Freshness
    97/100
    Agent evidence
    74/100
    Evidence confidence
    71/100
    Install readiness
    100/100
  3. 03

    Web Design Guidelines

    Review UI code for web interface guidelines, UX quality, accessibility, and interaction design best practices.

    @vercel-labsDesign34,215
    Review before use
    Ranking signals

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

    Popularity
    91/100
    Quality
    100/100
    Freshness
    89/100
    Agent evidence
    78/100
    Evidence confidence
    91/100
    Install readiness
    100/100
  4. 04

    Anthropic Brand Guidelines

    Apply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related artifacts.

    @anthropicsDesign196,151
    Review before use
    Ranking signals

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

    Popularity
    100/100
    Quality
    100/100
    Freshness
    97/100
    Agent evidence
    66/100
    Evidence confidence
    59/100
    Install readiness
    100/100
  5. 05

    Equity Research Earnings Analysis

    Create a structured post-earnings equity research update with key metrics, estimate changes, charts, and thesis review.

    @anthropicsFinance41,350
    Review before use
    Ranking signals

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

    Popularity
    92/100
    Quality
    100/100
    Freshness
    90/100
    Agent evidence
    73/100
    Evidence confidence
    68/100
    Install readiness
    90/100
  6. 06

    Frontend Design

    Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.

    @anthropicsDesign196,151
    Review before use
    Ranking signals

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

    Popularity
    100/100
    Quality
    100/100
    Freshness
    97/100
    Agent evidence
    68/100
    Evidence confidence
    94/100
    Install readiness
    60/100
  7. 07

    unslop

    Applies Cursor's prose-discipline rules to remove filler and AI writing tells from agent-facing and user-facing text.

    @cursorProductivity4,829
    Review before use
    Ranking signals

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

    Popularity
    74/100
    Quality
    100/100
    Freshness
    77/100
    Agent evidence
    76/100
    Evidence confidence
    83/100
    Install readiness
    87/100
  8. 08

    Portfolio Monitoring

    Review portfolio-company financial packages, flag variance to plan, and prepare monitored KPI summaries.

    @anthropicsFinance41,350
    Review before use
    Ranking signals

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

    Popularity
    92/100
    Quality
    100/100
    Freshness
    90/100
    Agent evidence
    59/100
    Evidence confidence
    43/100
    Install readiness
    90/100
  9. 09

    Taste Skill: Anti-Slop Frontend

    Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.

    @LeonxlnxDesign117,009
    Review before use
    Ranking signals

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

    Popularity
    100/100
    Quality
    100/100
    Freshness
    82/100
    Agent evidence
    66/100
    Evidence confidence
    100/100
    Install readiness
    68/100
  10. 10

    3-Statement Financial Model

    Complete and link income statement, balance sheet, and cash flow statement model templates with formulas and checks.

    @anthropicsFinance41,350
    Review before use
    Ranking signals

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

    Popularity
    92/100
    Quality
    100/100
    Freshness
    90/100
    Agent evidence
    57/100
    Evidence confidence
    44/100
    Install readiness
    90/100
  11. 11

    Vercel React Best Practices

    React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.

    @vercel-labsCoding34,215
    Review before use
    Ranking signals

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

    Popularity
    91/100
    Quality
    100/100
    Freshness
    89/100
    Agent evidence
    42/100
    Evidence confidence
    22/100
    Install readiness
    100/100
  12. 12

    Figma Implement Design

    Translate Figma designs into production-ready UI code with close visual fidelity and component-level detail.

    @openaiDesign28,777
    Review before use
    Ranking signals

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

    Popularity
    89/100
    Quality
    100/100
    Freshness
    60/100
    Agent evidence
    64/100
    Evidence confidence
    53/100
    Install readiness
    100/100
  13. 13

    Dashi Ppt Skill

    AI agent skill for generating browser-editable presentations with multiple visual themes and export to HTML, PDF, and PPTX.

    @chuspeeismPresentations10,756
    Review before use
    Ranking signals

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

    Popularity
    81/100
    Quality
    100/100
    Freshness
    77/100
    Agent evidence
    47/100
    Evidence confidence
    38/100
    Install readiness
    92/100
  14. 14

    GenericAgent

    Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

    @lsdefineAgent Frameworks14,431
    Review before use
    Ranking signals

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

    Popularity
    83/100
    Quality
    100/100
    Freshness
    99/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    100/100
  15. 15

    Cherry Studio

    AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs

    @CherryHQAgent Skills53,440
    Review before use
    Ranking signals

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

    Popularity
    95/100
    Quality
    100/100
    Freshness
    88/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    100/100
  16. 16

    Awesome Agent Skills

    A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.

    @VoltAgentAgent Skills36,881
    Review before use
    Ranking signals

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

    Popularity
    91/100
    Quality
    100/100
    Freshness
    75/100
    Agent evidence
    24/100
    Evidence confidence
    22/100
    Install readiness
    92/100
  17. 17

    Deploy to Vercel

    Deploy applications and websites to Vercel, including preview deployments and shareable deployment links.

    @vercel-labsDevops34,215
    Review before use
    Ranking signals

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

    Popularity
    91/100
    Quality
    100/100
    Freshness
    89/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    100/100
  18. 18

    Cc Connect

    Bridge local AI coding agents (Claude Code, Cursor, Gemini CLI, Codex) to messaging platforms (Feishu/Lark, DingTalk, Slack, Telegram, Discord, LINE, WeChat Work). Chat with your AI dev assistant from anywhere — no public IP required for most platforms.

    @chenhg5Coding16,317
    Review before use
    Ranking signals

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

    Popularity
    84/100
    Quality
    100/100
    Freshness
    86/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    87/100
  19. 19

    DashiAI Ppt Skill

    An AI agent skill that generates editable web-based PPT presentations with 12 themes, 1020 layouts, and one-click PPTX export.

    @chuspeeismProductivity10,756
    Review before use
    Ranking signals

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

    Popularity
    81/100
    Quality
    100/100
    Freshness
    77/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    100/100
  20. 20

    Humanizer

    Rewrites AI-sounding text so it reads naturally while preserving every factual claim and matching the writer's voice.

    @bladerProductivity57,595
    Review before use
    Ranking signals

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

    Popularity
    95/100
    Quality
    100/100
    Freshness
    36/100
    Agent evidence
    50/100
    Evidence confidence
    31/100
    Install readiness
    100/100
  21. 21

    Vox Director

    Turn one topic into a narrated Vox-style paper-collage explainer or ad video, from script through captions.

    @Alisa0808Design2,904
    Review before use
    Ranking signals

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

    Popularity
    69/100
    Quality
    100/100
    Freshness
    14/100
    Agent evidence
    77/100
    Evidence confidence
    94/100
    Install readiness
    92/100
  22. 22

    Apple Design

    Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations (feedback, spatial consistency, restraint) behind Apple-style interfaces.

    @emilkowalskiDesign34,452
    Review before use
    Ranking signals

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

    Popularity
    91/100
    Quality
    100/100
    Freshness
    0/100
    Agent evidence
    78/100
    Evidence confidence
    93/100
    Install readiness
    100/100
  23. 23

    no-ai-slop

    Audits or minimally edits drafts to remove named AI-writing patterns without flattening the author's voice.

    @petergyangProductivity5,828
    Review before use
    Ranking signals

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

    Popularity
    75/100
    Quality
    100/100
    Freshness
    31/100
    Agent evidence
    51/100
    Evidence confidence
    37/100
    Install readiness
    100/100
  24. 24

    Guizang Ppt Skill

    AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime.

    @op7418Agent Skills24,929
    Review before use
    Ranking signals

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

    Popularity
    88/100
    Quality
    100/100
    Freshness
    0/100
    Agent evidence
    76/100
    Evidence confidence
    82/100
    Install readiness
    100/100
  25. 25

    Playwright Browser Skill

    Automate a real browser from the terminal for navigation, form filling, snapshots, screenshots, extraction, and UI-flow debugging.

    @openaiBrowser Automation28,777
    Review before use
    Ranking signals

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

    Popularity
    89/100
    Quality
    100/100
    Freshness
    60/100
    Agent evidence
    0/100
    Evidence confidence
    0/100
    Install readiness
    100/100
  26. 26

    stop-slop

    Eliminates predictable AI writing patterns from prose while preserving specific meaning and reader trust.

    @hardikpandyaProductivity16,263
    Review before use
    Ranking signals

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

    Popularity
    84/100
    Quality
    100/100
    Freshness
    28/100
    Agent evidence
    49/100
    Evidence confidence
    60/100
    Install readiness
    84/100
  27. 27

    Archify

    Any agent Skill: generate beautiful architecture diagrams with dark/light theme toggle and PNG/JPEG/WebP/SVG export

    @tt-a1iAgent Skills47,183
    Review before use
    Ranking signals

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

    Popularity
    94/100
    Quality
    100/100
    Freshness
    0/100
    Agent evidence
    75/100
    Evidence confidence
    79/100
    Install readiness
    90/100
  28. 28

    mono-color

    Generate original one-ink or controlled two-ink editorial images from any theme, sentence, article idea, object, or reference photo. Always use this skill when the user asks for 单色海报、双色印刷、单色调视觉、蓝色/绿色孔版印刷、risograph、网点照片、复古或当代编辑排版、zine poster, monochrome editorial poster, duotone print, or asks to use the mono-color style. It uses an adaptive white, gray, or pale-beige substrate, no more than two printing inks, active negative space, terse human language, and strong serif/grotesk/mono typography without making retro styling the default or copying a source composition, wording, logo, or artwork. Produce both the final generation prompt and the generated raster image unless the user explicitly asks for prompt only.

    @yanliudesignResearch1,919
    Review before use
    Ranking signals

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

    Popularity
    66/100
    Quality
    100/100
    Freshness
    0/100
    Agent evidence
    80/100
    Evidence confidence
    94/100
    Install readiness
    90/100
  29. 29

    Superpowers

    An agentic skills framework & software development methodology that works.

    @obraAgent Skills257,155
    Review before use
    Ranking signals

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

    Popularity
    100/100
    Quality
    100/100
    Freshness
    0/100
    Agent evidence
    69/100
    Evidence confidence
    73/100
    Install readiness
    92/100
  30. 30

    Open Design

    🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design Systems 🖼️ Web · desktop · mobile prototypes · slides · images · videos · HyperFrames 📦 Sandboxed preview · HTML/PDF/PPTX/MP4 export 🤖 Claude Code / OpenClaw / Codex / Cursor / OpenCode / Qwen / Copilot / Hermes / Kimi & 17+ CLIs.

    @nexu-ioAgent Skills88,117
    Review before use
    Ranking signals

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

    Popularity
    99/100
    Quality
    100/100
    Freshness
    0/100
    Agent evidence
    67/100
    Evidence confidence
    69/100
    Install readiness
    92/100

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

Combines quality, freshness, installation metadata and outcome evidence, with a relevance penalty for records that are not Skill-like.

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