team-visual-a11y

Unified team skill for visual accessibility QA. OKLCH color contrast, typography readability, focus management, WCAG AA/AAA audit at rendered level. Uses team-worker agent architecture. Triggers on "team visual a11y", "accessibility audit", "visual a11y".

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/team-visual-a11y/SKILL.md

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable router skill body with concrete spawn code, a clear multi-agent workflow, and clean one-level-deep references. The main limitations are minor verbosity in the directory tree and that referenced role/spec files are not present in the bundle to confirm resolution.

Suggestions

Condense the Session Directory tree to the essential paths, or move the full layout into a referenced spec, to tighten conciseness.

Surface the key per-role validation/checkpoint steps (especially for the fix-implementer inner loop and re-audit GC) inline so the workflow's feedback loops are fully visible without opening role.md.

Ensure the referenced roles/<name>/role.md and specs/*.md files ship in the bundle so the progressive-disclosure links actually resolve.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational (tables, a real Agent spawn template, CLI commands) and avoids explaining concepts Claude already knows, though the full session-directory tree and ASCII architecture block could be trimmed slightly.	4 / 5
Actionability	Provides concrete, copy-paste-ready guidance — the Worker Spawn Template is real Agent(...) code with placeholders, the Role Registry maps roles to exact paths, and shared constants name specific CLI tools — with only minor gaps left to the referenced role files.	4 / 5
Workflow Clarity	The architecture diagram lays out a clear sequence (analyze → dispatch → parallel workers → remediation → fix inner_loop → re-audit) with a GC feedback loop and a max-rounds escalation, but some checkpoint detail lives in the referenced role.md files rather than inline.	4 / 5
Progressive Disclosure	Well-organized into overview, architecture, role registry, specs reference, and error handling with clearly signaled one-level-deep markdown links; no bundle files are present to verify the referenced roles/ and specs/ paths resolve, which keeps it off the top anchor.	4 / 5
	Total	16 / 20 Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that names concrete capabilities and includes explicit triggers, occupying a distinctive niche. Its main weakness is trigger phrasing that leans on skill-name tokens rather than the most natural user vocabulary.

Suggestions

Replace or supplement the skill-name-ish triggers ('team visual a11y', 'visual a11y') with natural phrases users would say, e.g. 'accessibility audit', 'check color contrast', 'WCAG audit', 'focus order check'.

Reframe capability areas as concrete actions where possible (e.g. 'Audits OKLCH color contrast' rather than just naming 'OKLCH color contrast') to lift specificity toward comprehensive coverage.

Add a one-line 'Use when...' framing to make the when-clause read as explicit user-facing guidance rather than a keyword list.

Dimension	Reasoning	Score
Specificity	Lists several concrete capability areas ('OKLCH color contrast', 'typography readability', 'focus management', 'WCAG AA/AAA audit at rendered level') rather than vague language, though they read as domains rather than discrete verbs, leaving minor coverage gaps.	4 / 5
Completeness	Clearly answers 'what' (visual accessibility QA with named capabilities) and includes an explicit trigger clause for 'when', but the trigger phrasing could be more explicit and natural to fully hit the top anchor.	4 / 5
Trigger Term Quality	Provides a 'Triggers on' clause with three phrases including the natural 'accessibility audit', but 'team visual a11y' and 'visual a11y' are skill-name-ish and omit common synonyms like 'contrast check' or 'WCAG audit'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (rendered-level visual a11y QA with OKLCH contrast) and pairs it with distinct trigger phrases, giving minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
relative_links	Relative link issues: 11 missing, 6 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: catlog22/Claude-Code-Workflow
Path: .claude/skills/team-visual-a11y/SKILL.md
Commit: 07491b0

Reviewed: 4 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.