CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

add-clidash

Add clidash — a zero-dependency, read-only web dashboard that derives its tabs and tables at runtime from any CLI that lists resources as JSON. Ships pre-wired for NanoClaw's ncl CLI (agent groups, sessions, channels, users, roles), plus message-activity charts, a log tail, and a read-only file viewer for group skills/CLAUDE.md/profiles.

Quality

81%

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 strong, highly actionable body: numbered install/configure/test/verify steps, copy-paste-ready commands with explicit verification and troubleshooting, and bulk configuration detail appropriately deferred to the shipped README and example config. The only trimmable material is a modest amount of explanatory prose and the inline config-key table that overlaps the referenced README.

DimensionReasoningScore

Conciseness

The body is command- and table-driven with no re-teaching of concepts Claude already knows, but a few passages could be trimmed ('Why it's safe' narrative prose and the /add-dashboard contrast paragraph), matching 'efficient; minor instances of over-explanation' rather than the lean 5.

4 / 5

Actionability

Fully executable, copy-paste-ready guidance throughout: 'mkdir -p tools / cp -R .claude/skills/add-clidash/add/tools/clidash tools/clidash', 'cp clidash.config.example.json clidash.config.json', 'npm test', 'node server.js', curl verification commands, and a complete systemd unit cover the common cases.

5 / 5

Workflow Clarity

Steps 1–5 are clearly sequenced with explicit validation checkpoints — tests in step 3 ('All tests should pass'), curl and browser verification in step 4 ('confirm it's live and that ncl discovery worked') — plus a troubleshooting section for error recovery; the operations are read-only, so no destructive/batch cap applies.

5 / 5

Progressive Disclosure

Good structure with bulk detail correctly deferred one level deep and clearly signaled ('see tools/clidash/README.md and clidash.config.example.json for the full shape', 'See [REMOVE.md](REMOVE.md)'), but the inline 12-row configuration-key table is reference material that partially duplicates the pointed-to README, keeping it just short of the cleanly split 5 anchor.

4 / 5

Total

18

/

20

Passed

Description

66%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, concrete, third-person description that clearly states what clidash does and names its panels and target CLI. Its main weakness is the complete absence of a 'Use when...' trigger clause, and its keyword set lacks common synonyms a user might say. Distinctive within the NanoClaw ecosystem, though the sibling /add-dashboard skill is only disambiguated in the body.

Suggestions

Append a trigger clause, e.g. 'Use when the user wants a read-only web dashboard or monitor for ncl/NanoClaw resources, or wants to visualize any CLI that outputs JSON resource lists.'

Add natural synonyms users would say — 'monitor', 'browse', 'view status', 'server overview' — to improve trigger-term coverage.

Add a short disambiguator in the description (e.g. 'unlike /add-dashboard, this pushes nothing and adds no npm dependencies') so model-side skill selection doesn't confuse the two.

DimensionReasoningScore

Specificity

Names the domain and several concrete capabilities ('derives its tabs and tables at runtime', 'message-activity charts, a log tail', 'read-only file viewer'), but coverage has minor gaps (nothing about installation or configuration), matching the 'several specific actions; minor gaps' anchor rather than the comprehensive 5.

4 / 5

Completeness

The 'what' is clear and concrete, but there is no 'Use when...' clause or any equivalent explicit trigger guidance, which the rubric requires to be capped at 3; the 'when' is absent rather than merely underspecified, so 4 does not apply.

3 / 5

Trigger Term Quality

Good natural keywords ('web dashboard', 'log tail', 'charts', 'read-only', 'CLI', 'JSON'), but common user phrasings like 'monitor', 'browse', 'view status', or 'server health' are missing, so it stops short of the comprehensive synonym coverage of the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

'clidash' plus 'NanoClaw's ncl CLI' and its specific panels carve a distinct niche, but the description alone does not disambiguate from the closely related /add-dashboard skill (that comparison lives only in the body), leaving minor overlap risk — the 4 anchor rather than 5.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

nanocoai/nanoclaw

Path

.claude/skills/add-clidash/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.