nv-implement

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

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills/nv-implement/SKILL.md

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 highly actionable, well-sequenced workflow with explicit validation checkpoints and feedback loops, written densely with almost no wasted tokens. Its only structural limitation is that everything lives inline in SKILL.md with no progressive-disclosure layer, which is acceptable given the absence of bundle files.

Dimension	Reasoning	Score
Conciseness	Dense and operational — checklist, exact commands with env vars, per-step 'Done when' criteria — with only minor trimmable redundancy (Guardrails repeats step 2's branch-reuse rule; step 5's fallout rationale is explanatory padding).	4 / 5
Actionability	Fully executable throughout: 'git worktree add -b <feature-branch>-<seam> ../wt-<seam> HEAD', 'git merge --no-ff <feature-branch>-<seam> -m "merge: <slice summary>"', a complete mocha invocation with all required env vars, and 'pnpm exec nest build'. Concrete alternatives cover the common cases (fresh vs. existing feature branch).	5 / 5
Workflow Clarity	Six clearly sequenced steps each with an explicit 'Done when' checkpoint, validation throughout (typecheck, re-run touched specs, full suite once), and feedback loops ('a subagent that skipped review or left tests red gets resumed, not merged'; 'Fix valid findings… re-run touched specs after') — the batch-operation validation cap does not apply because validation is present.	5 / 5
Progressive Disclosure	No bundle files exist; the body is well-organized (Workflow, Commands, Guardrails) with a clearly-signaled 'Related skills' section of one-level-deep links. Anchor 4 rather than 5 because the ~120-line body is entirely inline with no layering of the longer operational detail.	4 / 5
	Total	18 / 20 Passed

Description

63%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 specific, action-dense description that clearly conveys the workflow, but it lacks any 'use when' trigger guidance and leans on internal jargon rather than natural user phrases. It is distinctive within its ecosystem yet somewhat broad at the open.

Suggestions

Add an explicit trigger clause, e.g. 'Use when a plan/spec/ticket has been agreed and it's time to implement it across multiple slices' — this would lift completeness from 3 to 5.

Replace or gloss internal jargon ('pre-agreed seams', 'nv-park-and-review') with natural phrases users would say, such as 'implement the agreed plan' or 'slice-by-slice implementation with review', to improve trigger-term quality.

Sharpen the opening beyond the generic 'Implement planned work' (e.g. 'Fan out planned implementation work…') to reduce overlap with other implementation skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions spanning the full workflow — 'fanning out parallel subagents on isolated worktrees', 'TDD at pre-agreed seams', 'per-slice nv-park-and-review', 'merge back', 'full suite once at the end' — with comprehensive coverage.	5 / 5
Completeness	The 'what' is clear and concrete, but no 'Use when…' clause or equivalent trigger guidance appears; the 'when' is only weakly implied by 'planned work', which caps completeness at 3.	3 / 5
Trigger Term Quality	Some natural keywords exist ('implement planned work', 'merge', 'full suite') but the description leans on project-specific jargon ('pre-agreed seams', 'nv-park-and-review') that users would not naturally say, and misses common variations.	3 / 5
Distinctiveness Conflict Risk	The worktree-fanout workflow and named sub-skills give it a distinct niche, but the opening 'Implement planned work' is broad enough to overlap with generic implementation skills.	4 / 5
	Total	15 / 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-implement/SKILL.md
Commit: 320a0ce

Reviewed: 5 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.