CtrlK
BlogDocsLog inGet started
Tessl Logo

nv-worktree-create

Create a sibling git worktree and a new branch with the same name, copy local `.env*` files, initialize the enterprise submodule, wire enterprise symlinks, and move the agent into the worktree. Use when the user asks for a worktree, parallel branch checkout, or `/worktree` with a branch name.

73

Quality

90%

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

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, highly actionable skill file: concrete commands, explicit preflight validation, user-confirmation checkpoints, and graceful fallback behavior. Its main weakness is that the env-copy rsync recipe, path sanitization rules, and submodule troubleshooting all live in files outside this bundle, so those steps cannot be executed from the bundle alone.

Suggestions

Inline the .env* copy command (or a one-line rsync) in step 3 so the copy step is executable without nv-worktree-commands.

State the sanitized-name rule for the worktree path inline (or as a short formula), since step 2's <worktree-path> otherwise depends on an external file.

If nv-worktree-commands and nv-worktree-cleanup are meant to be part of this skill's bundle, include them under references/; if they are separate skills, note that explicitly so navigation expectations are unambiguous.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — a terse goal statement, an input table, and step commands with no git-concept explanations; warnings carry real signal ('it regenerates encryption keys'). Every token earns its place, matching the 5 anchor rather than 4 because there is no over-explanation left to trim.

5 / 5

Actionability

Mostly executable: 'git worktree add -b <branch> <worktree-path> [<base-ref>]', the preflight command trio, the submodule block, and 'pnpm symlink:submodules || echo "WARN: ..."' are concrete. Two executable details — the .env* 'rsync recipe' and the sanitized-name path rule — are deferred to nv-worktree-commands rather than given inline, so it is not fully copy-paste ready from this file alone.

4 / 5

Workflow Clarity

Six clearly sequenced steps with explicit validation ('abort if the target path already exists', dirty-tree warning with user confirmation), error-recovery fallbacks ('warn and continue in OSS mode — do not block the worktree'), and a final confirm checklist. This matches the 5 anchor; it is above 4 because checkpoints are explicit and complete rather than mostly present.

5 / 5

Progressive Disclosure

The SKILL.md is a well-structured overview that defers detail one level deep with clearly signaled references ('For git command details and path naming, read nv-worktree-commands. For cleanup, read nv-worktree-cleanup.'). However, none of the referenced files (nv-worktree-commands, nv-worktree-cleanup, enterprise-submodule) exist in this bundle — there is no references/ directory — so the deferred details are not reachable from the bundle itself, a minor organization gap that fits the 4 anchor.

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: concrete, comprehensive action list in third-person imperative voice with an explicit multi-trigger 'Use when' clause covering natural user phrasings including the slash command. The only weakness is slightly thin synonym coverage in the trigger terms.

DimensionReasoningScore

Specificity

The description lists multiple specific concrete actions — 'Create a sibling git worktree and a new branch with the same name, copy local .env* files, initialize the enterprise submodule, wire enterprise symlinks, and move the agent into the worktree' — with comprehensive coverage of the skill's behavior. This matches the 5 anchor; it is not 4 because there are no meaningful gaps in the action coverage.

5 / 5

Completeness

It explicitly answers both what (the full concrete action list) and when ('Use when the user asks for a worktree, parallel branch checkout, or /worktree with a branch name') with concrete trigger phrases. This matches the 5 anchor; it is not 4 because the when-clause is already explicit and multi-trigger.

5 / 5

Trigger Term Quality

Good natural keyword coverage: 'worktree', 'parallel branch checkout', and '/worktree with a branch name' are phrases users would plausibly say. A few natural variations are missing (e.g. 'git worktree', 'new worktree', 'check out a branch in parallel'), which fits the 4 anchor rather than the 5 anchor's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (worktree creation plus .env copying, enterprise submodule wiring, and agent handoff) with distinct triggers including a slash-command trigger, so the risk of firing for the wrong skill is minimal. Matches the 5 anchor.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.