accesslint-diff

Diff a live page's accessibility violations against a baseline — by default compares uncommitted changes (stash-based), or pass --branch [<name>] to diff against a branch. Reports only new violations introduced, violations fixed, and pre-existing count. Use `scan` for a full audit with no diffing.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

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

A tight, highly actionable single-file skill with strong workflow validation and clean sectioning, docked only for a duplicated description block and minor explanatory padding.

Suggestions

Replace the verbatim-repeated description in 'When to Use' with a one-line trigger summary to avoid token waste.

Trim the rebuild/HMR explanatory aside in branch mode to the essential 'no HMR — use --wait-for to gate the rebuild'.

Keep the rest as-is; the executable commands and validation checkpoints are already exemplary.

Dimension	Reasoning	Score
Conciseness	Mostly lean and signal-dense with executable commands, but the 'When to Use' section duplicates the frontmatter description verbatim and a few asides (e.g. the rebuild/HMR explanation) could be tightened.	2 / 3
Actionability	Provides fully executable, copy-paste-ready bash for both stash and branch modes plus a concrete report-format template with explicit where/evidence/fix fields, matching the executable-code anchor.	3 / 3
Workflow Clarity	Clear Audit → Report → Tear down sequence with explicit validation checkpoints for destructive ops (stash-failure 'warn and exit', git check-ref-format / rev-parse --verify, refusing option-like branch names) and a re-run-to-verify feedback loop.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent), so per the simple-skill note this single well-organized SKILL.md with clearly labeled sections (When to Use, Audit, Report, Tear down, Gotchas, Limitations) qualifies for 3.	3 / 3
	Total	11 / 12 Passed

Description

82%

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 specific, distinctive description with strong trigger terms and a clear niche, weakened only by the absence of an explicit 'Use when...' clause capping completeness at 2.

Suggestions

Add an explicit trigger clause such as 'Use when you want to see which accessibility violations a code change introduced or fixed, versus a full audit.' to lift completeness to 3.

Optionally include the common alias 'a11y' alongside 'accessibility' to broaden natural trigger coverage.

Lead with the when/what pairing before the implementation modes (stash vs branch) so the trigger is front-loaded.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Diff a live page's accessibility violations against a baseline', 'compares uncommitted changes (stash-based)', 'diff against a branch', and 'Reports only new violations introduced, violations fixed, and pre-existing count' — matching the multi-action anchor.	3 / 3
Completeness	Clearly answers 'what' (diff a11y violations, report new/fixed/pre-existing) and contrasts with `scan`, but lacks any explicit 'Use when...' trigger clause; per the rubric, a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	Includes natural terms a user would say — 'accessibility violations', 'diff ... against a baseline', 'branch' — giving good coverage of likely phrasings, though it omits common variants like 'a11y'/'WCAG'.	3 / 3
Distinctiveness Conflict Risk	Carves a clear niche (diffing a11y violations against a baseline) and explicitly distinguishes itself from `scan` ('Use `scan` for a full audit with no diffing'), making wrong-skill triggering unlikely.	3 / 3
	Total	11 / 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: sickn33/antigravity-awesome-skills
Commit: 6e69f00

Reviewed: 5 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.