CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.codex/skills/team-visual-a11y/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%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.

The body is a well-structured router/orchestrator document with strong sequencing, validation loops, and concrete agent-API examples. Its two real weaknesses are redundant spawn examples that inflate token cost, and a progressive-disclosure structure that points to role and spec files that are missing from the bundle entirely.

Suggestions

Include the referenced bundle files (roles/<role>/role.md for all six roles and the five specs/*.md files) or remove the links — every reference currently resolves to a nonexistent file.

Collapse the three near-identical auditor spawn blocks into one parameterized example (spawn loop over [color, typo, focus] descriptors) to cut ~50 lines.

Move the detailed coordinator procedure (spawn templates, model selection guide, session directory layout) into roles/coordinator/role.md, keeping SKILL.md as a lean routing overview.

DimensionReasoningScore

Conciseness

Mostly efficient (dense tables, shared constants, delegation lock matrix), but the "Parallel Fan-in Spawn" section repeats the generic Worker Spawn Template as three near-identical ~20-line spawn_agent blocks that a single parameterized example would replace. Not 2: the padding is localized rather than spread through several sections.

3 / 5

Actionability

Concrete executable guidance: spawn_agent calls with real task IDs, wait_agent({ timeout_ms: 1800000 }), close_agent({ target: "COLOR-001" }), and a specific timeout cascade (STATUS_CHECK, 3 min, FINALIZE with interrupt). Not 5: the Audit-to-Remediation spawn block is truncated (drops the Role Assignment fields), and ccw cli invocations are named but never shown with actual arguments.

4 / 5

Workflow Clarity

The pipeline is fully sequenced (analyze -> 3 parallel auditors -> remediation-planner -> fix-implementer -> re-audit) with explicit routing rules, the Delegation Lock table as a pre-tool checklist, a re-audit validation loop capped at 2 GC rounds, timeout recovery, and an error-handling table with user escalation. Explicit validation steps and error-recovery feedback loops are both present.

5 / 5

Progressive Disclosure

References to roles/<name>/role.md and specs/*.md are clearly signaled and one level deep, but none of those files exist in the bundle (the skill directory contains only SKILL.md), so all 11 links are broken. Additionally, ~100 lines of detailed coordinator procedure (spawn examples, model selection guide) arguably belong in roles/coordinator/role.md rather than the router.

3 / 5

Total

15

/

20

Passed

Description

83%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 description that clearly states capabilities and provides explicit trigger guidance in third person. Its main weakness is trigger coverage: the listed phrases are narrow and miss the most natural terms a user would say (WCAG, contrast, a11y variations), and "accessibility audit" is broad enough to risk overlap with generic accessibility skills.

Suggestions

Add natural trigger synonyms users would actually say, e.g. "WCAG audit", "contrast check", "a11y", "Section 508 compliance".

Replace or supplement the command-like "team visual a11y" trigger with a phrase a user would naturally utter when they need this skill.

Narrow the broad "accessibility audit" trigger (e.g. "visual accessibility audit") to reduce conflict risk with general accessibility skills.

DimensionReasoningScore

Specificity

Lists several specific concrete actions ("OKLCH color contrast, typography readability, focus management, WCAG AA/AAA audit at rendered level") covering the domain. Not 5 because "Uses team-worker agent architecture" is implementation framing rather than a capability, and what "rendered level" entails is left implicit.

4 / 5

Completeness

Explicitly answers both what ("OKLCH color contrast, typography readability, focus management, WCAG AA/AAA audit") and when ("Triggers on 'team visual a11y', 'accessibility audit', 'visual a11y'") with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

"accessibility audit" and "visual a11y" are natural user phrases with good coverage. Not 5: "team visual a11y" reads as a command rather than a natural request, and common terms users would actually say ("WCAG", "contrast check", "a11y", "Section 508") are missing.

4 / 5

Distinctiveness Conflict Risk

Visual accessibility QA with OKLCH contrast and rendered-level WCAG audit is a clear niche with distinct triggers. Not 5 because the generic phrase "accessibility audit" could overlap with a broader accessibility or general-audit skill.

4 / 5

Total

17

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.