CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

verify-in-box

Verify a change end to end on the Novu Box, a full Novu Cloud stack in one container on Cloudflare. Use when a change to apps/, libs/, packages/, enterprise/ or playground/ needs proof that it works, or when asked to check, verify, demo or reproduce something on the box.

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

96%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.

Excellent operational content: fully executable commands, a numbered workflow with explicit done-when checkpoints, error-recovery loops, and guardrails on destructive operations, all written with near-zero token waste. The only structural gap is that detail (e.g. the Accounts section, the intro command listing) is inlined rather than split into one-level-deep reference files, though the reliance on --help and README keeps that gap minor.

DimensionReasoningScore

Conciseness

The body is dense and lean throughout — 'A step is done when its check passes; what it proves goes in your report' — with no explanation of concepts Claude already knows and no padding; every line carries an operational fact (e.g. 'sync stops over 25 MB and names the biggest changed files'). This matches anchor 5: every token earns its place, and it is clearly above anchor 4's 'minor instances of over-explanation'.

5 / 5

Actionability

Fully executable, copy-paste-ready guidance throughout: 'node docker/box/src/cli/main.ts up/sync/doctor', 'mail to:<recipient> (or subject:<text>, tag:sms)', 'logs --errors', and API key retrieval via 'exec -- cat /data/bridge/secret-key' with 'Authorization: ApiKey <key>'. Specific commands cover the common cases, matching anchor 5 and exceeding anchor 4's 'minor gaps'.

5 / 5

Workflow Clarity

A clearly numbered sequence (1. Launch, 2. Doctor, 3. Drive, 4. Proof bar, 5. Cleanup) with explicit validation checkpoints per step — 'Done when sync exits 0 and ends with applied sync <branch> at <sha>', 'Done when it prints "ok": true' — plus feedback loops for recovery ('if it isn't, logs --errors says why'; 'an unfinished apply is fixed by syncing again') and a guardrail on the destructive operation ('Ask the user before delete'). This is the anchor 5 pattern with validation and error-recovery built in.

5 / 5

Progressive Disclosure

The body is well-sectioned and delegates exhaustive detail one level deep to '--help' and 'docker/box/README.md' ('the reference for every command and flag'), which is good structure with clear references — anchor 4. It falls short of anchor 5 because everything else is inlined in a ~105-line file with some redundancy between the intro command block and the per-step commands, rather than being an overview split across well-signaled reference files.

4 / 5

Total

19

/

20

Passed

Description

82%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 with an explicit and specific 'Use when' clause, natural trigger verbs, and a clearly staked-out niche. The only weakness is that it names just one concrete action (verify end to end) rather than enumerating the skill's several concrete capabilities, and it misses the common natural term 'test'.

Suggestions

Enumerate 2-3 concrete capabilities alongside 'verify' (e.g. 'Launch a full Novu Cloud stack with your checkout, run health checks, exercise the change via dashboard/API/email, capture proof') to raise specificity.

Add 'test' (and optionally 'e2e' or 'end-to-end') to the trigger verbs so the description matches the most common natural phrasing for this need.

DimensionReasoningScore

Specificity

Names the domain precisely ('the Novu Box, a full Novu Cloud stack in one container on Cloudflare') with one concrete action ('Verify a change end to end'), matching anchor 3: domain plus 1-2 concrete actions but not comprehensive. It does not list several specific actions (launch, doctor, drive, capture proof), which keeps it below anchor 4.

3 / 5

Completeness

It explicitly answers both: what ('Verify a change end to end on the Novu Box, a full Novu Cloud stack in one container on Cloudflare') and when, with concrete trigger phrases ('Use when a change to apps/, libs/, packages/, enterprise/ or playground/ needs proof that it works, or when asked to check, verify, demo or reproduce something on the box'). This matches anchor 5; the 'when' clause is explicit and specific, so no lower anchor fits.

5 / 5

Trigger Term Quality

Natural user phrasings are present ('check, verify, demo or reproduce', 'needs proof that it works') plus concrete repo-path triggers ('apps/, libs/, packages/, enterprise/ or playground/'), giving good keyword coverage. It stops short of anchor 5's comprehensiveness because common natural terms like 'test' or 'e2e' are absent.

4 / 5

Distinctiveness Conflict Risk

The niche is unambiguous — 'Novu Box', 'Novu Cloud stack', 'Cloudflare', and named repo directories — so trigger overlap with other skills is minimal. This is the anchor 5 pattern (clear niche with distinct triggers), well above anchor 4's 'minor overlap risk'.

5 / 5

Total

17

/

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

Path

.cursor/skills/verify-in-box/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.