sermilion/bill-kmp-code-review-ux-accessibility
skills/kmp/bill-kmp-code-review-ux-accessibility/SKILL.md
Use when reviewing UX correctness and accessibility risks, delegating UI-framework-heavy checks to bill-kmp-code-review-ui. Use when user mentions UX review, accessibility, content description, screen reader, or localization review.
$ install --global
skillsauthnpx skillsauth add sermilion/mobile-development-plugin bill-kmp-code-review-ux-accessibilityInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 15, 2026, 6:09 AM34.9s1 file scanned
SKILL.md
- name:
- bill-kmp-code-review-ux-accessibility
- description:
- Use when reviewing UX correctness and accessibility risks, delegating UI-framework-heavy checks to bill-kmp-code-review-ui. Use when user mentions UX review, accessibility, content description, screen reader, or localization review.
UX & Accessibility Review Specialist
Review only user-impacting UX/accessibility issues.
Focus
- Broken/ambiguous UX states and recovery flows
- Accessibility semantics, labels, focus order, and keyboard/talkback usability
- Validation/error visibility and actionable feedback
- Read-only/editable behavior mismatches
- User-facing inconsistency with product intent
UI Delegation
- If KMP UI files are in scope, run
bill-kmp-code-review-uiand merge relevant findings.
Ignore
- Pure visual preference debates without usability impact
Project Overrides
If .agents/skill-overrides.md exists in the project root and contains a ## bill-kmp-code-review-ux-accessibility section, read that section and apply it as the highest-priority instruction for this skill. The matching section may refine or replace parts of the default workflow below.
If an AGENTS.md file exists in the project root, apply it as project-wide guidance.
Precedence for this skill: matching .agents/skill-overrides.md section > AGENTS.md > built-in defaults.
Project-Specific Rules
Localization
- All user-facing strings must use
stringResource(R.string.xxx)— no hardcoded strings - Never delete existing translations or
strings.xmlfiles - Check for existing matching strings before creating new ones — reuse
- When removing UI components, verify orphaned string resources are cleaned up
Previews
- Screens and components must have
@Previewannotations - Previews must use the project's theme composable
Error States
- Screens must handle loading, content, error, and empty states
- Error messages come from UI (string resources), not ViewModel
Output Rules
- Report at most 7 findings.
- Include user-visible consequence for each finding.
- Include
file:lineevidence for each finding. - Severity:
Blocker | Major | Minor - Confidence:
High | Medium | Low - Include a minimal, concrete fix.
Output Format
Every finding must use this exact bullet format for downstream tooling:
- [F-001] <Severity> | <Confidence> | <file:line> | <description>
Do NOT use markdown tables, numbered lists, or any other format for findings.
Related Skills
sermilion/bill-editorial-assignment-desk
development
VerifiedTrustedCommunity
Use when running a governed editorial assignment desk from Readian recommendations through candidate selection and source-backed story packs.
6SKILL.mdUpdated May 3, 2026
sermilion/bill-unit-test-value-check
testing
VerifiedTrustedCommunity
Use when reviewing unit tests in a file, current changes, or a commit to flag low-value, tautological, or coverage-only tests that do not validate real behavior. Use when user mentions check test quality, review tests, tautological tests, weak tests, or coverage-padding.
6SKILL.mdUpdated Apr 25, 2026
sermilion/bill-skill-remove
data-ai
VerifiedTrustedCommunity
Use when removing an existing skill or platform skill set and cleaning up agent installs, manifests, and supporting links.
6SKILL.mdUpdated Apr 25, 2026
sermilion/bill-quality-check
development
VerifiedTrustedCommunity
Use when you want a generic quality-check entry point that detects the dominant stack in scope and delegates to the matching stack-specific quality-check skill. Use when user mentions run checks, validate, lint, format, quality check, or run quality.
6SKILL.mdUpdated Apr 25, 2026