CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

nv-worktree-commands

Git worktree command reference: path naming, create/remove/prune, `.env` copy and cleanup. Use when implementing or debugging worktree setup — not as the primary user-facing workflow (see nv-worktree-create).

Quality

91%

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

93%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.

An exemplary lean command reference: fully executable commands, concrete measured rationale for the tricky env-copy pipeline, explicit safety guidance around destructive remove/install operations, and well-organized single-file structure. The only gap is the absence of an explicit post-create verification step in the workflow.

DimensionReasoningScore

Conciseness

The body is lean and every token earns its place: it conveys only non-obvious, repo-specific knowledge (gitignored-file behavior, measured timings "~11s vs ~0.1s", the STORE_ENCRYPTION_KEY trap in setup-env-files.js) and never explains concepts Claude already knows. It is not 4 because there are no sections that could be trimmed without losing decision-relevant information.

5 / 5

Actionability

Commands are copy-paste ready and cover the common cases: `git worktree add -b <branch> <worktree-path>`, the `git ls-files -z -o -i --exclude-standard --directory | rsync -a --from0 --files-from=-` pipeline, and the --lite loop. The only pseudocode, `sanitize(BRANCH)`, is immediately defined ("lowercase; `/` → `-`"), so this fully matches the executable anchor.

5 / 5

Workflow Clarity

Sections follow a logical create→inspect→copy→remove sequence with real checkpoints ("Abort if `WORKTREE` already exists", "report the list that was sent", "use `--force` only when the user explicitly asks" guarding the destructive remove). It is not 5 because there is no explicit post-create verification step or error-recovery loop, and not 3 because validation guidance for the risky operations is explicitly present.

4 / 5

Progressive Disclosure

This is a ~100-line single-use reference correctly kept in one file with well-organized sections and no content that belongs in a separate file; navigation is easy and cross-references to sibling skills (nv-worktree-create, nv-worktree-cleanup) are clearly signaled. There are no bundle files to misplace, and nothing is buried.

5 / 5

Total

19

/

20

Passed

Description

87%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 concise, specific description that states concrete capabilities, gives an explicit use-when clause with two trigger scenarios, and includes negative boundary guidance to avoid conflicting with the sibling end-to-end skill. Its only weaknesses are slightly incomplete action coverage and a narrow set of trigger-term variations.

DimensionReasoningScore

Specificity

"path naming, create/remove/prune, `.env` copy and cleanup" lists several concrete capabilities, matching the anchor for several specific actions with minor gaps; it falls short of 5 because the description omits actions the body covers (inspect, remove guidance, anti-patterns).

4 / 5

Completeness

"Git worktree command reference: path naming, create/remove/prune, `.env` copy and cleanup" clearly states what it does, and "Use when implementing or debugging worktree setup" explicitly states when, with concrete trigger scenarios; it exceeds anchor 4 because the when-clause is explicit and specific rather than improvable.

5 / 5

Trigger Term Quality

"git worktree" and "worktree setup" are exactly the natural phrases a user would say when needing this skill, giving good keyword coverage; a few natural variations (e.g., "add/remove a worktree") are missing, keeping it below the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

It carves out a clear niche (worktree command reference) and actively disambiguates against the sibling skill with "not as the primary user-facing workflow (see nv-worktree-create)", minimizing conflict risk.

5 / 5

Total

18

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

novuhq/novu

Path

.cursor/skills/nv-worktree-commands/SKILL.md

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.