CtrlK
BlogDocsLog inGet started
Tessl Logo

nv-review-local-changes

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-review-local-changes.

79

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

A well-engineered, command-heavy workflow skill: concise, fully actionable, with a clearly sequenced five-step process and explicit validation/feedback loops around its destructive git operations, and clean section organization with no needless nested references.

DimensionReasoningScore

Conciseness

Lean and command-driven throughout — it never explains git concepts Claude already knows (worktrees, HEREDOCs, fast-forward) and every command earns its place; the short overview paragraph and 5-step checklist serve as a rewarded overview rather than padding, so it sits at the score-3 anchor rather than the score-2 "could be tightened" case.

3 / 3

Actionability

Fully executable, copy-paste-ready guidance: exact commands like `git worktree add -b review/<branch>-<BASE_SHA:0:7> ../review-<BASE_SHA:0:7> <BASE_SHA>`, a HEREDOC commit message, `git merge --ff-only`, and a complete subagent prompt template with literal placeholders — matching the score-3 anchor of specific executable examples.

3 / 3

Workflow Clarity

The five steps are explicitly sequenced with checkboxes, and the destructive/batch operations carry validation checkpoints — step 4's "Verify before deleting: confirm each dead-code/redundancy claim with Grep", ReadLints on touched files, Grep for stale identifiers, plus the step-5 `--ff-only` failure fallback — giving the explicit validation and error-recovery loops the score-3 anchor requires.

3 / 3

Progressive Disclosure

No bundle files exist (references/scripts/assets absent) and the skill is self-contained; the body is cleanly organized into Workflow, numbered steps, Guardrails, and Related-skills sections with one-level-deep pointers to sibling skills, so it meets the score-3 bar for a well-organized self-contained skill rather than a monolithic wall.

3 / 3

Total

12

/

12

Passed

Description

100%

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 tight, third-person description that names multiple concrete actions and pairs them with explicit, natural-language trigger guidance, fully covering both what the skill does and when to use it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "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" — matching the score-3 anchor of several specific concrete actions, not just a named domain.

3 / 3

Completeness

Explicitly answers both what (the commit→worktree→review→refactor→land sequence) and when via a clear "Use when the user asks to review their local/uncommitted changes for AI slop and redundant code, or invokes nv-review-local-changes" clause, satisfying the score-3 anchor for both what AND when.

3 / 3

Trigger Term Quality

Natural user-facing terms are well covered: "review their local/uncommitted changes", "AI slop", "redundant code", plus the explicit invocation name "nv-review-local-changes" — phrases a user would actually say, with no jargon-only triggers; voice is third person throughout.

3 / 3

Distinctiveness Conflict Risk

A clear niche — a baseline-commit + review-worktree + nuclear-review + separate refactor-commit pipeline — with distinct triggers ("AI slop", "redundant code", the skill's own name) that make overlap with generic review/deslop skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 suspicious

Warning

Total

15

/

16

Passed

Repository
novuhq/novu
Reviewed

Table of Contents

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.