CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sensory-instructions

Use when reviewing rendered HTML, interactive components, or design-system patterns related to Avoid sensory-only instructions. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.

Quality

76%

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/sensory-instructions/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 tight, well-structured review skill whose Check/Fix sections give genuinely actionable before/after examples and whose single reference to references/rule.md is exemplary progressive disclosure. The main cost is redundancy — the intro and Explain sections duplicate the same who-is-affected explanation Claude already knows — and verification guidance stays generic instead of naming concrete tooling.

Suggestions

Merge the intro sentence and the Explain section into one — both restate the same color-blind/screen-reader/deaf-user explanation, which is a concept Claude already knows.

Deduplicate the 'combine multiple cues' advice that appears in both Quick Reference and Fix, keeping it only in Fix where the worked example lives.

Replace "browser accessibility tooling or assistive tech" in the Code Review section with a concrete verification step, e.g. tab through the component with a keyboard and confirm the instruction is announced with its text label by a screen reader (or run axe on the markup).

DimensionReasoningScore

Conciseness

Mostly efficient, but redundant: the intro sentence ("Color-blind users can't see 'click the red button,' screen reader users can't perceive 'the menu on the right,' and deaf users miss audio cues") explains accessibility basics Claude already knows, and the Explain section ("Explain how color-blind users cannot distinguish color-only cues, screen reader users cannot perceive location or shape...") restates it almost verbatim. "Combine multiple cues" advice also appears in both Quick Reference and Fix. Not a 2 because the body is short and the Check/Fix sections are tight.

3 / 5

Actionability

Concrete, instruction-only guidance with explicit before/after examples: "Instead of 'click the green button', use 'click the Submit button (green)'" and named violation patterns ("color ('click the red button'), shape ('the circular icon'), location ('the menu on the right'), or sound ('when you hear the beep')"). Not a 5 because verification guidance stays vague ("browser accessibility tooling or assistive tech" names no specific tool or technique) and no inline code example is given despite the rule being markup-adjacent.

4 / 5

Workflow Clarity

Clear Check → Fix → Explain sequence with a concrete review step ("Review instructions and verify they don't rely only on color, shape, location, or sound") and a fix step with a worked example; the Code Review section adds "note how to verify the fix with browser accessibility tooling". Not a 5 because the verification checkpoint is mentioned but never made explicit — no specific tool, command, or check to confirm the fix; sequence otherwise unambiguous for a simple skill.

4 / 5

Progressive Disclosure

Short, well-sectioned overview (Quick Reference, Check, Fix, Explain, Code Review) with one clearly signaled, one-level-deep reference — "For full implementation details, code examples, and framework-specific guidance, see `references/rule.md`" — and the referenced file exists in the bundle and contains exactly that (implementation details, code examples). Matches the anchor for a clear overview with well-signaled one-level-deep references and easy navigation.

5 / 5

Total

16

/

20

Passed

Description

71%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.

The description answers both what and when with mostly concrete language, but it is assembled from generic accessibility-review boilerplate that would equally describe any sibling accessibility rule, with the actual rule name pasted in awkwardly. Distinctiveness is the main weakness; trigger coverage is good but misses the natural vocabulary users would use for this specific issue.

Suggestions

Rewrite the trigger around this rule's actual subject so it doesn't read as shared boilerplate: e.g. 'Use when instructions in rendered HTML or interactive components rely only on color, shape, position, or sound (e.g. "click the red button") and need text or multi-modal alternatives.'

Drop the pasted rule-title phrasing ('related to Avoid sensory-only instructions') in favor of natural trigger terms users would say: accessibility, a11y, color-only cues, WCAG 1.4.1.

Keep the inspection checklist only if it is specific to this rule; otherwise trim it so it doesn't collide with sibling accessibility skills' descriptions.

DimensionReasoningScore

Specificity

Lists several concrete actions — "Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output" — plus the domain ("reviewing rendered HTML, interactive components, or design-system patterns"). Not a 5 because the action list is generic review boilerplate rather than actions specific to sensory-only instructions, and "where relevant" hedges coverage.

4 / 5

Completeness

Both parts are present: 'what' ("Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output") and 'when' ("Use when reviewing rendered HTML, interactive components, or design-system patterns"). Falls short of the 5 anchor because the trigger condition "related to Avoid sensory-only instructions" is an awkward rule-name paste rather than concrete trigger phrases, and "where relevant" weakens the specification.

4 / 5

Trigger Term Quality

Good natural keywords: "rendered HTML", "interactive components", "screen-reader output", "keyboard behavior", "sensory-only instructions". Not a 5 because common variations users would actually say are missing — e.g. "accessibility", "a11y", "color-only", "color as the only indicator", "WCAG" — and "related to Avoid sensory-only instructions" reads as a pasted rule title rather than a natural trigger phrase.

4 / 5

Distinctiveness Conflict Risk

The only differentiator from sibling accessibility skills is the rule name "Avoid sensory-only instructions"; the rest — "Use when reviewing rendered HTML, interactive components, or design-system patterns" and "Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output" — is generic accessibility-review language that would match nearly any frontendchecklist accessibility rule, so overlap with similar skills is real. Better than 2 because the sensory-instructions niche is named at all.

3 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

thedaviddias/Front-End-Checklist

Path

skills/sensory-instructions/SKILL.md

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.