CtrlK
BlogDocsLog inGet started
Tessl Logo

cds-accessibility

Reviews already-written Coinbase Design System (CDS) UI for accessibility: verifying documented accessibility props (e.g. accessibilityLabel, accessibilityState), confirming the chosen CDS primitives cover the right assistive technology behavior, and checking usage against official CDS documentation—not generic web ARIA tutorials. Use this skill to review CDS UI for screen reader, keyboard, and labeled control requirements after the code has been written.

65

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/cds-accessibility/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 review methodology with a clear sequenced workflow, explicit conditional gating, and concrete props/heuristics to check. Its main weakness is conciseness: the central 'read the official doc, don't guess' directive is repeated far more than necessary across every section.

Suggestions

Consolidate the repeated 'load docs via cds-docs / don't guess ARIA / keep web and RN separate' directive into a single stated-once rule in Doc discipline, then reference it instead of restating it in every Part 1 step, Part 2 subsection, and Anti-pattern.

Move the Common props mental-map table and the Anti-patterns list into a references/ file (e.g. references/quick-checks.md) and link to it from Part 3, reducing the inline SKILL.md footprint and sharpening progressive disclosure.

In Part 1, collapse Steps 3 and 4's overlapping component-choice guidance into a single step with a decision checklist, since both currently restate 'smallest component whose doc covers the interaction'.

DimensionReasoningScore

Conciseness

Accurate and free of basic-concept filler, but the core directive (load docs via cds-docs, don't guess ARIA, keep web/RN separate) is restated dozens of times across When-to-use, Prerequisites, Success criteria, every Part 1 step, Part 2, and Anti-patterns; the pervasive redundancy could be cut substantially without losing meaning, so it sits below the 'minor instances' bar of a 4.

3 / 5

Actionability

Names exact props to verify (accessibilityLabel, accessibilityHint, accessibilityState, accessibilityRole, as, role, aria-*, htmlFor) and gives concrete heuristics ('smallest component whose doc fully covers the interaction') plus a mental-map table; for an instruction-only review skill the guidance is actionable, though the actual prop tables are delegated to the external cds-docs skill.

4 / 5

Workflow Clarity

Part 1 is a clearly sequenced Setup + Steps 1-7 workflow with explicit conditional gating (Step 5 only for focus-managed components, with skip logic) and verification/checklist steps (Step 6 Verify, Step 7 final checklist tied to Success criteria); some checkpoints are 'note that...' acknowledgements rather than hard gates, keeping it just short of a 5.

4 / 5

Progressive Disclosure

Well-organized into clearly headed sections (When to use, Prerequisites, Success criteria, Part 1/2/3) with one-level-deep, clearly signaled links to the cds-docs and cds-code skills; no bundle files exist so everything is inlined in ~210 lines, and the Part 2 patterns partially restate Part 1, which is a minor organization gap rather than a structural problem.

4 / 5

Total

15

/

20

Passed

Description

87%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: third-person voice, concrete review actions, explicit what-and-when trigger guidance, and a clearly bounded niche distinct from sibling CDS skills. The only gaps are a few missing accessibility synonyms and slightly less granular action enumeration than the top anchor.

DimensionReasoningScore

Specificity

Lists several concrete review actions ('verifying documented accessibility props (e.g. accessibilityLabel, accessibilityState)', 'confirming the chosen CDS primitives cover the right assistive technology behavior', 'checking usage against official CDS documentation') rather than vague language; not quite a 5 because the actions are review-verbs rather than enumerated granular operations.

4 / 5

Completeness

Explicitly answers both what ('Reviews already-written CDS UI for accessibility: verifying... confirming... checking...') and when ('Use this skill to review CDS UI for screen reader, keyboard, and labeled control requirements after the code has been written') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural terms a user would say ('accessibility', 'screen reader', 'keyboard', 'labeled control'); a few common synonyms (e.g. 'a11y', 'VoiceOver/TalkBack') are absent from the description though they appear in the body.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (CDS accessibility review post-build) and explicitly distinguishes itself from cds-code (build) and cds-docs (load docs), with an explicit 'not generic web ARIA' boundary; minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
coinbase/cds
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.