audit

Perform comprehensive audit of interface quality across accessibility, performance, theming, and responsive design. Generates detailed report of issues with severity ratings and recommendations.

1.51x

Quality

62%

Does it follow best practices?

Impact

100%

1.51x

Average score across 6 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./archived/legacy-companion/.agents/skills/audit/SKILL.md

Quality

Content

65%Weight 40%Scale 1-3

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

The body is highly actionable with concrete thresholds and a clear report template, and is reasonably well-structured, but it carries redundant command lists, lacks explicit validation checkpoints in its workflow, and keeps all content inline rather than progressively disclosing the lengthy report format. It sits at a solid mid-to-high level across dimensions.

Suggestions

De-duplicate the suggested-command list, which appears in both 'Detailed Findings' and 'Suggested Commands for Fixes'.

Add an explicit checkpoint after the diagnostic scan (e.g. 'Verify all five dimensions were checked before writing the report') to strengthen workflow clarity.

Consider moving the detailed report template into a references file (e.g. REPORT_TEMPLATE.md) and summarizing it in SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient structured checklists with useful specifics (4.5:1 contrast, 44px touch targets), but the suggested-command list is repeated in two sections and the closing 'NEVER'/'Remember' blocks pad the tail, fitting 'mostly efficient but could be tightened' rather than the lean score-3 anchor.	2 / 3
Actionability	Provides concrete, executable guidance for an instruction-only skill: specific thresholds, a per-issue report template (Location/Severity/Category/Impact/WCAG/Recommendation), and explicit command mappings, meeting the 'specific examples, copy-paste ready' bar without needing code.	3 / 3
Workflow Clarity	The scan-then-report sequence is present and ordered ('First', 'Diagnostic Scan', 'Generate Comprehensive Report'), but there are no explicit validation checkpoints confirming scan completeness before reporting, fitting 'sequence present but checkpoints missing or implicit'.	2 / 3
Progressive Disclosure	Content is well-organized into clear sections with no nested references, but everything is inline in a ~118-line SKILL.md with no bundle files; the long report template could be split out, fitting 'some structure but content that could be separate is inline'.	2 / 3
	Total	9 / 12 Passed

Description

60%Weight 40%Scale 1-3

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 is specific and concrete about what the skill does across four quality dimensions, but it omits any explicit 'Use when...' trigger guidance and does not clearly distinguish itself from adjacent frontend review skills. This caps both completeness and distinctiveness at the mid level.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to audit, review, or check UI/interface quality, accessibility, contrast, or responsive design.'

Include common trigger variations like 'a11y', 'design review', and 'WCAG' to improve natural keyword coverage.

Differentiate from sibling skills by stating the audit is documentation-only (e.g. 'documents issues without fixing them').

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('Perform comprehensive audit', 'Generates detailed report of issues with severity ratings and recommendations') across four explicit dimensions, matching the 'lists multiple specific concrete actions' anchor rather than the score-2 'some actions' anchor.	3 / 3
Completeness	Clearly answers 'what' (audit + generate severity-rated report) but provides no 'Use when...' or equivalent explicit 'when' guidance, so per the judging guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	Contains relevant natural keywords ('audit', 'accessibility', 'performance', 'theming', 'responsive design') but misses common variations users might say ('a11y', 'contrast', 'UI review', 'design review') and lacks an explicit trigger clause, fitting 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	The interface-quality audit niche is somewhat specific, but the description does not differentiate from sibling frontend skills (e.g. critique/review), fitting 'somewhat specific but could still overlap with similar skills' rather than a clearly distinct niche.	2 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: The-Vibe-Company/companion
Path: archived/legacy-companion/.agents/skills/audit/SKILL.md
Commit: 90804d3

Reviewed: 18 days 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.