Editorial best list

Agent Skills worth evaluating first

This is not an automated list sorted by stars. Inclusion requires a clear job, traceable source, useful documentation, and explainable risk boundaries.

See the selectionsRead selection method
Selected
8
Reviewed
2026-07-30
Editorial status
Maintained

Selection method

Define what “best” means before ranking

There is no universal winner across jobs. Selections are reviewed for usefulness, evidence, maintenance, risk, and alternative value.

Clear job and output

The source explains when to use the Skill, what to bring, and what a useful result looks like.

Evidence beyond popularity

Repository popularity is contextual. Documentation, source depth, maintenance, and test evidence carry more weight.

Explicit exclusion rules

Thin source files, unclear identity, abandoned projects, or unbounded external actions are excluded.

Current selections

Ordered by practical decision value

  1. 01

    ab-testing

    Editorial pick

    When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program

    coreyhaines31/marketingskills · quality 100/100

    Review
  2. 02

    design-intelligence

    Editorial pick

    Grounded design brief from the adopted corpus — style, WCAG-checked color tokens, typography, layout pattern, anti-patterns. Use on ui-design-brief or any which-style/palette/font/chart decision.

    event4u-app/agent-config · quality 100/100

    Review
  3. 03

    emil-design-eng

    Editorial pick

    This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

    nexu-io/open-design · quality 99/100

    Review
  4. 04

    agent-payment-x402

    Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol.

    affaan-m/ECC · quality 98/100

    Review
  5. 05

    dask

    Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.

    K-Dense-AI/scientific-agent-skills · quality 98/100

    Review
  6. 06

    higgsfield-generate

    Use when the user wants to generate an image or video via Higgsfield AI. Covers 30+ models: Soul V2, Seedance 2.0, Kling 3.0, Veo 3.1, GPT Image 2, Nano Banana 2. Also covers Marketing Studio — branded ad video/image with avatars and products. Use whenever: "generate an image", "make a video", "animate this photo", "image-to-video", "img2vid", "edit this image with AI", "produce a clip", "create an ad", "make a UGC video", "marketing video", "brand video", "TV spot", "import product from URL", "

    MoizIbnYousaf/marketing-cli · quality 98/100

    Review
  7. 07

    geofeed-tuner

    Use this skill whenever the user mentions IP geolocation feeds, RFC 8805, geofeeds, or wants help creating, tuning, validating, or publishing a self-published IP geolocation feed in CSV format. Intended user audience is a network operator, ISP, mobile carrier, cloud provider, hosting company, IXP, or satellite provider asking about IP geolocation accuracy, or geofeed authoring best practices. Helps create, refine, and improve CSV-format IP geolocation feeds with opinionated recommendations beyon

    github/awesome-copilot · quality 97/100

    Review
  8. 08

    subagent-driven-development

    Use when executing implementation plans with independent tasks in the current session

    obra/superpowers · quality 95/100

    Review

List limitation

These selections use source and editorial evidence and cannot replace testing in your environment. Entries change when sources, maintenance, or stronger alternatives change.