Skip to content
SkillCheatSheet Sign in

ux-audit

An AI agent skill from lobehub/lobehub, scored 65 out of 100 by code.

65/ 100C

Code score by group

  • Spec20/20
  • Description12/20
  • Procedure10/15
  • Done criteria0/15
  • Resources9/10
  • Scripts5/8
  • Safety7/7
  • Upkeep2/5

It loses the most points in Done criteria (15), the group that checks whether there is a checklist and a step that verifies the work.

What the author says it does

Audit a page / surface against the Designing Interfaces pattern language + the ux skill checklists, then land findings. Three layers — static (code), visual (screenshots), dynamic (automated user journey + perf). Use to run a repeatable, standards-based UX review of one screen.

This is the description in the skill's own SKILL.md, written by its author, not by SkillCheatSheet.

Repository
lobehub/lobehub
Folder
.agents/skills/ux-audit
License
Not identified by GitHub
GitHub stars
85,123
SKILL.md lines
271
Other files
32

Add ux-audit to your agent

npx skills add lobehub/lobehub --skill ux-audit

The command uses the open skills CLI. A skill is instructions and scripts your agent will follow, so read it first: open the folder on GitHub at the commit that was scored. GitHub identifies no license for this repository, so check its terms before you use it.

More skills from lobehub/lobehub

  1. builtin-tool

    Use for LobeHub builtin agent tools: manifests, executors, runtimes, inspectors, renders, streaming and intervention.

    72B
  2. llm-generation

    Use for application prompts, generateObject/generateText, model selection and generation tracing. Excludes provider adapters and agent snapshots.

    72B
  3. testing

    Use for Vitest tests, mocks, coverage and failing-test diagnosis.

    72B
  4. acceptance

    Verify delivery outcomes on the real product, capture inspected evidence, and deliver an acceptance report with the lh CLI: published to LobeHub when signed in, or rendered as a l…

    71B
  5. alint-ruleset

    Maintain LobeHub's model-backed alint rule set in packages/alint: author a rule, calibrate its false positives against real source, decide its severity (warn vs error) from real P…

    71B
  6. desktop-security-update

    Inspect, mark, or revoke vulnerable LobeHub Desktop versions through the existing release workflow and signed R2 security policy. Use for forced security updates across Stable, Ca…

    71B
  7. docs-changelog

    Use for EN/ZH website product changelogs in docs/changelog/*.mdx. Excludes GitHub Release notes.

    71B
  8. full-text-search

    Use for product search: FtsSearchRepo, pg_search/pg_like/Elasticsearch, mapping migrations, projections, Outbox sync, reindexing and performance. Excludes agent web search.

    71B

All skills in lobehub/lobehub

Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.