check

Reviews code diffs, PRs, issue queues, release readiness, commits, pushes, publishing, and project audits. Use when users ask in any language for code review, issue or PR triage, release gates, publishing follow-through, or project audits. Not for debugging root causes or prose review.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%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 highly actionable, well-structured multi-mode review skill with explicit validation checkpoints and clean progressive disclosure. The main weakness is operational redundancy across safety/verification sections rather than any lack of substance.

Suggestions

Consolidate the repeated 're-read HEAD and git status before acting' guidance, which appears in Worktree Safety, Get the Diff, Autofix, and Verification, into one canonical rule with cross-references.

Merge the 'dirty or multi-agent checkout' warning, currently restated in Worktree Safety, Verification, and Get the Diff, into a single shared caution.

Tighten the Hard Stops lockfile sub-bullets into one sentence plus the regen command, rather than the current multi-paragraph treatment.

Dimension	Reasoning	Score
Conciseness	Dense and assumes Claude's competence with no basic-concept padding, but the 're-read HEAD/status before acting' rule and the 'dirty/multi-agent checkout' warning each recur across three to four sections and could be consolidated.	3 / 5
Actionability	Copy-paste-ready commands throughout ('git status --short --branch -uall', 'gh run view <id> --json status,conclusion', 'pnpm update <pkg> --lockfile-only', 'cargo update -p <pkg> --precise <v>'), plus concrete depth/autofix tables and a filled sign-off template.	5 / 5
Workflow Clarity	Sequenced mode flow with explicit validation checkpoints and feedback loops ('If the script exits non-zero... halt', 'If HEAD moved... stop and report') and a completion-ledger checklist, fully covering the destructive/batch operations the skill handles.	5 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references (all eight referenced files exist under references/), content appropriately split into mode/catalog files, and a mode-picker table for easy navigation.	5 / 5
	Total	18 / 20 Passed

Description

92%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, specific description that clearly states capabilities, trigger conditions, and out-of-scope cases in third person. Trigger-term coverage is solid though a few natural phrases are deferred to when_to_use.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete review surfaces — 'code diffs, PRs, issue queues, release readiness, commits, pushes, publishing, and project audits' — giving comprehensive coverage of what the skill acts on.	5 / 5
Completeness	Explicitly answers both what ('Reviews code diffs, PRs, issue queues...') and when ('Use when users ask in any language for code review...') with concrete trigger phrases, plus a negative-scope clause.	5 / 5
Trigger Term Quality	Includes natural terms ('code review', 'issue or PR triage', 'release gates', 'publishing follow-through', 'project audits') with good coverage, but several natural phrasings users say ('before merge', 'rate my code', 'audit scorecard') live in when_to_use rather than the description itself.	4 / 5
Distinctiveness Conflict Risk	Clear review/release/audit niche with explicit exclusions ('Not for debugging root causes or prose review'), minimizing conflict with adjacent skills.	5 / 5
	Total	19 / 20 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: tw93/Waza
Path: plugins/waza/skills/check/SKILL.md
Commit: f902996

Reviewed: 1 day 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.