Skill rankings
AI agent skills with proven usage
Skills with reported agent calls and success signals, ranked by real usage when feedback data is available.
Shown: 19 · Candidates: 62
Compare top 4Saved directory data is shown because current data is unavailable. Dates and metrics may be out of date.
- 01
Vox Director
Turn one topic into a narrated Vox-style paper-collage explainer or ad video, from script through captions.
@Alisa0808Design326Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 50/100
- Quality
- 100/100
- Freshness
- 0/100
- Agent evidence
- 80/100
- Evidence confidence
- 94/100
- Install readiness
- 100/100
- 02
Canvas Design
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
@anthropicsDesign163,076Review before useRanking 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
- 77/100
- Evidence confidence
- 85/100
- Install readiness
- 100/100
- 03
Frontend Design
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
@anthropicsDesign163,076Review before useRanking 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
- 94/100
- Install readiness
- 68/100
- 04
Web Design Guidelines
Review UI code for web interface guidelines, UX quality, accessibility, and interaction design best practices.
@vercel-labsDesign29,271Review before useRanking 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
- 0/100
- Agent evidence
- 77/100
- Evidence confidence
- 83/100
- Install readiness
- 100/100
- 05
Taste Skill: Anti-Slop Frontend
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
@LeonxlnxDesign65,810Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 96/100
- Quality
- 100/100
- Freshness
- 0/100
- Agent evidence
- 66/100
- Evidence confidence
- 100/100
- Install readiness
- 68/100
- 06
Webapp Testing
Use Playwright to interact with and test local web applications, capture screenshots, debug UI behavior, and inspect browser logs.
@anthropicsBrowser Automation163,076Review before useRanking 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
- 73/100
- Evidence confidence
- 69/100
- Install readiness
- 100/100
- 07
Equity Research Earnings Analysis
Create a structured post-earnings equity research update with key metrics, estimate changes, charts, and thesis review.
@anthropicsFinance34,158Review before useRanking 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
- 63/100
- Evidence confidence
- 47/100
- Install readiness
- 90/100
- 08
Anthropic Brand Guidelines
Apply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related artifacts.
@anthropicsDesign163,076Review before useRanking 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
- 57/100
- Evidence confidence
- 44/100
- Install readiness
- 100/100
- 09
Figma Implement Design
Translate Figma designs into production-ready UI code with close visual fidelity and component-level detail.
@openaiDesign24,000Review before useRanking 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
- 57/100
- Evidence confidence
- 44/100
- Install readiness
- 100/100
- 10
Seedance 2.0 Prompt Writing
Write precise Seedance 2.0 prompts for multimodal video, camera movement, editing, music, and product storytelling.
@dexhunterDesign2,917Review before useRanking 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
- 0/100
- Agent evidence
- 51/100
- Evidence confidence
- 37/100
- Install readiness
- 100/100
- 11
Aaron Marketing Skills
120 marketing skills for SEO/GEO, influencer, paid ads, email, launch, organic social, and brand narrative agents.
@aaron-he-zhuMarketing2,313Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 67/100
- Quality
- 100/100
- Freshness
- 0/100
- Agent evidence
- 51/100
- Evidence confidence
- 37/100
- Install readiness
- 90/100
- 12
RNSkill HeyGen Digital Avatar
Create a consent-aware digital-avatar layer for AI video production with narration approval and final quality gates.
@PluviobyteVideo Creation797Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 58/100
- Quality
- 98/100
- Freshness
- 0/100
- Agent evidence
- 51/100
- Evidence confidence
- 37/100
- Install readiness
- 90/100
- 13
Agent Skills
Production-grade engineering skills and quality gates for AI coding agents.
@addyosmaniCoding Agents61,800Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 96/100
- Quality
- 100/100
- Freshness
- 0/100
- Agent evidence
- 37/100
- Evidence confidence
- 31/100
- Install readiness
- 78/100
- 14
Vercel React Best Practices
React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.
@vercel-labsCoding29,271Review before useRanking 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
- 0/100
- Agent evidence
- 42/100
- Evidence confidence
- 22/100
- Install readiness
- 100/100
- 15
Portfolio Monitoring
Review portfolio-company financial packages, flag variance to plan, and prepare monitored KPI summaries.
@anthropicsFinance34,158Review before useRanking 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
- 42/100
- Evidence confidence
- 22/100
- Install readiness
- 90/100
- 16
3-Statement Financial Model
Complete and link income statement, balance sheet, and cash flow statement model templates with formulas and checks.
@anthropicsFinance34,158Review before useRanking 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
- 42/100
- Evidence confidence
- 22/100
- Install readiness
- 90/100
- 17
Browser Use
Browser automation layer for agents that need to interact with websites.
@browser-useBrowser Automation75,000Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 98/100
- Quality
- 100/100
- Freshness
- 0/100
- Agent evidence
- 42/100
- Evidence confidence
- 22/100
- Install readiness
- 77/100
- 18
RNSkill Local Talking-Head Cut
Build a reproducible local rough-cut workflow for talking-head or narrated screen-recording videos with transcript review gates.
@PluviobyteVideo Creation797Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 58/100
- Quality
- 100/100
- Freshness
- 0/100
- Agent evidence
- 42/100
- Evidence confidence
- 22/100
- Install readiness
- 90/100
- 19
Crawl4AI
Open-source LLM-friendly web crawler and scraper for agent workflows.
@unclecodeWeb Scraping66,000Review before useRanking signals
Signals use a 0–100 scale. They explain the shortlist; the ordering follows this list’s method, not any one score.
- Popularity
- 96/100
- Quality
- 100/100
- Freshness
- 0/100
- Agent evidence
- 39/100
- Evidence confidence
- 22/100
- 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
Requires reported outcomes; combines outcome signals, evidence confidence and usage volume. Reports are not independent safety certification.
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