CtrlK
BlogDocsLog inGet started
Tessl Logo

node-inspect-debugger

Debug Node.js via --inspect + Chrome DevTools Protocol CLI.

60

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/software-development/node-inspect-debugger/SKILL.md
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.

The body is highly actionable and well-structured, with executable code, numbered workflows, a verification checklist, and an error-recovery pitfalls section that assume Claude's competence. The main improvement is splitting the longer inline code references into bundle files to fully realize progressive disclosure.

DimensionReasoningScore

Conciseness

The body is dense and purposeful — a REPL command table, copy-paste CDP driver, pitfalls, and recipes — and does not explain basics Claude already knows, matching anchor 4 (efficient, minor over-explanation that could be trimmed). Not a 5 because a few prose passages (e.g. the Overview and When-to-Use bullets) could be tightened; not a 3 because it is markedly leaner than the 'mostly efficient with some unnecessary explanation' anchor.

4 / 5

Actionability

Provides fully executable, copy-paste-ready guidance across the common cases: 'node inspect path/to/script.js', a complete chrome-remote-interface driver, 'kill -SIGUSR1 <pid>' attach flow, and vitest-under-debugger commands, matching anchor 5. Not a 4 because examples are complete rather than having minor gaps.

5 / 5

Workflow Clarity

Multi-step flows are explicitly numbered (e.g. '1. Send SIGUSR1... 2. Attach the debugger CLI'), a dedicated 'Verification Checklist' provides validation checkpoints, and 'Common Pitfalls' gives error-recovery feedback loops, matching anchor 5. Debugging is not a destructive/batch operation, so the 3-cap does not apply; not a 4 because checkpoints and recovery guidance are explicit rather than minor.

5 / 5

Progressive Disclosure

Content is well-organized with clear section headers (Quick Reference, Attaching, Programmatic CDP, Pitfalls, Recipes) and no broken or nested references — there are no bundle files, so all content is inline but structured, fitting anchor 4 (good structure, well-placed content). Not a 5 because some long inline blocks (the full CDP driver, the CPU/heap profiler snippets) could arguably be split into reference files, and the skill exceeds the under-50-line simple-skill exception.

4 / 5

Total

18

/

20

Passed

Description

53%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.

The description is concise and names a clear, distinct niche (Node.js debugging via --inspect and CDP), but it omits any explicit 'Use when...' trigger guidance and lists only the single action 'Debug', leaving completeness and trigger-term coverage mid-range.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when a Node.js test fails and you need breakpoints, stepping, scope inspection, or CPU/heap profiling beyond console.log.'

Enumerate concrete capabilities (set breakpoints, step in/over/out, inspect closure scope, capture CPU profiles and heap snapshots) to lift specificity and trigger-term coverage.

Include natural synonyms users say ('breakpoints', 'step through', 'node inspect', 'pause') to improve trigger-term quality.

DimensionReasoningScore

Specificity

Quotes 'Debug Node.js via --inspect + Chrome DevTools Protocol CLI' — names the domain (Node.js) and the concrete mechanism (inspect flag + CDP), but the only action verb is 'Debug' with no enumeration of capabilities, matching anchor 3 (domain + 1-2 concrete actions, not comprehensive). It is above anchor 2 because the mechanism is concrete rather than generic, and below anchor 4 because no multiple specific actions are listed.

3 / 5

Completeness

It clearly states 'what' (debug Node.js via inspect + CDP CLI) but provides no 'Use when...' or equivalent trigger guidance, so per the missing-trigger clause completeness is capped at 3, matching anchor 3 exactly. Not a 4 because there is no explicit 'when'.

3 / 5

Trigger Term Quality

Natural term 'Debug Node.js' is present, plus technical terms '--inspect' and 'Chrome DevTools Protocol', but common variations users say (breakpoints, stepping, node inspect, pause) are absent, fitting anchor 3 (some relevant keywords, missing common synonyms). Not a 4 because natural synonyms are largely missing; not a 2 because 'Debug Node.js' is a phrase users actually say.

3 / 5

Distinctiveness Conflict Risk

The phrase 'Debug Node.js via --inspect + Chrome DevTools Protocol CLI' carves a narrow niche (Node.js + CDP), with only minor overlap risk against generic or language-agnostic debugging skills, matching anchor 4. Not a 5 because general debugging skills (e.g. systematic-debugging) still partially overlap; not a 3 because it is far more specific than 'Works with document files'.

4 / 5

Total

13

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
NousResearch/hermes-agent
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.