review

Use when the user asks to review CURRENT uncommitted changes (staged, unstaged, or branch diff) as QA + lead engineer before committing — verdict on task completion, code quality, architecture, cleanup, plus ephemeral regression probes (pass-on-parent / fail-on-diff). Requires an existing diff. Do NOT trigger without a diff or on post-merge review of historical commits.

Quality

92%

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.

The body is highly actionable with an explicit, well-validated multi-step workflow and concrete commands. Its main weakness is progressive disclosure: a skill this long inlines detailed reference material (JiT subset, FR audit, report template) that would benefit from being split into separate bundle files.

Suggestions

Extract the JiT subset mechanics (Steps 8a/8b, Rules 10-12) and the FR Coverage Audit (Step 4a) into separate reference files (e.g. JIT.md, FR-COVERAGE.md) and link to them from the main body to improve progressive disclosure.

Tighten the manifest-detection enumeration in Step 2 and the multi-clause degradation rules (Rules 10-11) to reduce verbosity without losing the decision logic.

Move the full report section template in Step 10 into a short reference or keep only a concise structural summary inline, pointing to the complete template externally.

Dimension	Reasoning	Score
Conciseness	Information-dense and assumes Claude's competence (git, worktrees, subagents, manifests) without padding, but the 322-line body has some sections (manifest-detection enumeration, Rule 10/11 degradation clauses) that could be tightened.	4 / 5
Actionability	Copy-paste-ready commands throughout ('git diff --stat', 'git worktree add <SCRATCH>/jit-parent-<sid> <parent-sha>', 'grep -qE ... .gitignore', 'deno run -A scripts/check-fr-coverage.ts FR-<ID>'), exact severity tags, and a fixed report section order.	5 / 5
Workflow Clarity	Clearly sequenced 11-step workflow with explicit validation checkpoints (Empty Diff Guard, 2a/2b baseline-green verification, blocking FR Coverage Audit, dual-run + flaky/zero-kill filter) and feedback loops for the risky test-synthesis/worktree operations.	5 / 5
Progressive Disclosure	Organized via XML tags and headers, but at 322 lines substantial reference-style content (the JiT subset mechanics, FR Coverage Audit, the full report template) is inlined rather than split into one-level-deep bundle files, and no external references exist.	3 / 5
	Total	17 / 20 Passed

Description

100%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 is exemplary: concrete actions, natural trigger terms, explicit what-and-when guidance, and a negative boundary that sharply distinguishes it from adjacent skills. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'verdict on task completion, code quality, architecture, cleanup, plus ephemeral regression probes (pass-on-parent / fail-on-diff)' — giving comprehensive coverage of the review scope.	5 / 5
Completeness	Explicitly answers both what (QA + lead engineer verdict and regression probes) and when ('Use when the user asks to review CURRENT uncommitted changes... before committing'), plus a negative boundary.	5 / 5
Trigger Term Quality	Natural trigger phrases a user would say — 'review', 'uncommitted changes', 'staged', 'unstaged', 'branch diff', 'before committing' — with synonyms for each diff type.	5 / 5
Distinctiveness Conflict Risk	Clear niche (current uncommitted-change review) with explicit anti-triggers ('Do NOT trigger without a diff or on post-merge review of historical commits'), distinct from whole-project maintenance/audit.	5 / 5
	Total	20 / 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
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: korchasa/flowai-plugins
Path: plugins/flowai/skills/review/SKILL.md
Commit: b4ba256

Reviewed: ~22 hours 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.