accessibility-cleanup

accessibility-cleanup is an Android development skill for AI agents, published by chromium in the chromium repository on GitHub. Skillspace rates accessibility-cleanup C (74/100) and it passed the safety scan; a judge model has also reviewed it.

Finds common violations of the Android accessibility API in the Clank App Java code and attempts to address them (e.g. hardcoded state change announcements, missing events, focus moving, assertive live regions, etc).

Grade
C
Quality
74 / 100
Safety
Passed
GitHub stars
24,241

Placed #1 of 6 in the judged category final for Android development.

Not launch-quality. It is graded C with a clean safety verdict, but our quality filters exclude it: a model that read it found it written only for the repository it lives in. So it is not in our launch-quality set, the skills our MCP server searches and recommends. How launch-quality is decided

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubchromium/chromium

Our review

Architecture
88 / 100
Maturity
Structured: ships references or scripts
Security scan
No issues found
License
BSD-3-Clause
Adoption
Adopted by 0 other repositories, in 0 collections
Scope
Repo-internal: written for the repository it lives in. Fixes accessibility bugs in Chromium's own Clank Java code

Judge review

Placed #1 of 6 in the judged category final for Android development.

  • Trigger8282
  • Instructions9090
  • Specificity9090
  • Safety8585
  • Disclosure8888
  • Maintenance8585
A full code-health pipeline with a mandatory sub-agent review gate before verification and a shared hub of reference docs for discovery, review, and submission.

Not checked yet

  • No blind task eval yet
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Android development

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.