nv-park-and-review

Commit local changes as a baseline, hop into a lightweight review worktree, run a thermo-nuclear code quality review scoped to ONLY that commit, commit the resulting refactor as a separate follow-up commit, then land it back and tear the worktree down. Use when the user asks to review their local/uncommitted changes for AI slop and redundant code, or invokes nv-park-and-review.

Quality

90%

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

88%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, actionable skill body with a well-validated workflow and concrete commands throughout. The only mild gap is a handful of justifying sentences that restate the value proposition rather than instruct.

Suggestions

Trim non-instructional rationale lines (e.g. the 'Keeps the feature diff and the review-driven refactor separately reviewable…' opener) so every line drives an action.

Consider extracting the subagent prompt template into a references/ file if the skill grows, keeping SKILL.md as a pure overview.

The 'Related skills' links use relative paths outside the bundle; verify those targets resolve at runtime since no bundle files are present here.

Dimension	Reasoning	Score
Conciseness	Largely lean and assumes Claude's git competence, but a few sentences pad rather than instruct (e.g. 'Keeps the feature diff and the review-driven refactor separately reviewable, and frees the main checkout the moment the baseline is committed') and could be trimmed.	4 / 5
Actionability	Fully executable guidance throughout — copy-paste commands ('git worktree add -b review/<branch>-<BASE_SHA:0:7> ...', 'git show <BASE_SHA>', 'git merge --ff-only') plus a complete, fill-in-the-blank subagent prompt template covering the common case.	5 / 5
Workflow Clarity	A clearly sequenced 5-step checklist with explicit validation checkpoints ('Verify before deleting' via Grep, ReadLints on touched files, Grep for stale identifiers) and a feedback/recovery loop for the --ff-only failure case.	5 / 5
Progressive Disclosure	Well-sectioned body (Workflow, per-step subsections, Guardrails, Related skills) with one-level-deep links to sibling skills and no nested references; no bundle files exist, and the single-use subagent prompt template is reasonably kept inline rather than extracted.	4 / 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 description: it concretely lays out the full workflow and gives an explicit, natural-language trigger with the skill's invocation name. Slight headroom only in trigger-term synonym breadth.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the full workflow — 'Commit local changes as a baseline', 'hop into a lightweight review worktree', 'run a thermo-nuclear code quality review scoped to ONLY that commit', 'commit the resulting refactor as a separate follow-up commit', 'land it back and tear the worktree down' — with comprehensive stage coverage.	5 / 5
Completeness	Explicitly answers both what (the commit → worktree → review → refactor commit → land workflow) and when ('Use when the user asks to review their local/uncommitted changes for AI slop and redundant code, or invokes nv-park-and-review') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('review their local/uncommitted changes for AI slop and redundant code', 'nv-park-and-review'), but lacks synonyms or broader phrasings (e.g. 'clean up', 'refactor my diff') that would push it to comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (worktree-isolated single-commit review-then-refactor) with a unique invocation name and specific triggers, minimizing overlap with the related review/deslop skills it composes.	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
relative_links	Relative link issues: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: novuhq/novu
Path: .cursor/skills/nv-park-and-review/SKILL.md
Commit: dc9caee

Reviewed: 3 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.