nv-implement

Implement planned work by fanning out parallel subagents on isolated worktrees — TDD at pre-agreed seams, per-slice nv-review-local-changes, merge back, full suite once at the end.

Quality

83%

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

100%

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 workflow with executable commands, explicit validation checkpoints and feedback loops, and cleanly signaled references to related skills.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it does not explain what a worktree or TDD is, and every section earns its tokens with concrete instruction rather than padding.	3 / 3
Actionability	Provides copy-paste-ready, executable commands (git worktree add, ln -s for node_modules, the full mocha invocation) and concrete per-step guidance rather than pseudocode.	3 / 3
Workflow Clarity	A clear 6-step sequence, each with an explicit 'Done when' checkpoint, plus validation (typecheck, run touched specs) and a feedback loop (subagents that skipped review or left red tests get resumed, not merged).	3 / 3
Progressive Disclosure	Well-organized overview sections with clearly signaled, one-level-deep links to related skills (/tdd, /nv-review-local-changes, novu-prepare-pr, nv-worktree-commands); no nested or buried references.	3 / 3
	Total	12 / 12 Passed

Description

67%

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 specific, distinctive description that names concrete actions, but it lacks an explicit 'when to use' trigger clause and leans on internal jargon over natural user keywords.

Suggestions

Add an explicit 'Use when…' clause stating when Claude should invoke this skill (e.g., implementing a multi-file plan that can be split into disjoint slices).

Soften or gloss the internal jargon ('seams', 'nv-review-local-changes') and include natural trigger terms users would actually say.

Lead with the user-facing trigger before the process detail so the 'when' is as clear as the 'what'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'fanning out parallel subagents on isolated worktrees', 'TDD at pre-agreed seams', 'per-slice nv-review-local-changes', 'merge back', 'full suite once' — rather than vague language.	3 / 3
Completeness	It clearly states what the skill does, but offers no explicit 'Use when…' trigger clause telling Claude when to invoke it, which caps completeness at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	'Implement planned work' is a natural user phrase, but the rest leans on internal/technical jargon ('seams', 'worktrees', 'nv-review-local-changes') and omits common phrasings a user might actually say.	2 / 3
Distinctiveness Conflict Risk	The parallel-subagent/worktree/TDD-slice workflow is a distinct niche with specific triggers, making it unlikely to fire for an unrelated skill.	3 / 3
	Total	10 / 12 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-implement/SKILL.md
Commit: d921755

Reviewed: about 13 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.