CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cli-health

Check server health, component status, and live metrics from the CLI. Run `health`, `health components`, and `health watch` for a real-time dashboard of circuit breakers and provider status.

Quality

79%

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/cli-health/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 an efficient, executable CLI reference with clear per-subcommand organization and unambiguous single-action workflows. Its main weaknesses are minor: duplicated overview text, undocumented flag semantics, and examples that don't exercise the flags they list.

Suggestions

Show flag usage in the examples (e.g. `omniroute health watch --interval 5`, `omniroute doctor --liveness-url <url>`) so documented flags are demonstrated.

Add a short purpose phrase for non-obvious flags (`--alerts-only`, `--no-liveness`, `--json`) instead of bare flag names.

Drop the verbatim repetition of the description in the Overview, or move per-subcommand flag detail into a references file to keep SKILL.md lean.

DimensionReasoningScore

Conciseness

Lean per-subcommand flag lists and one-line examples with no explanation of concepts Claude already knows. Minor trimmable material — the Overview repeats the description verbatim and flags like `--no-liveness`/`--alerts-only` are listed without purpose — keeps it just below 5.

4 / 5

Actionability

Every subcommand has a copy-paste-ready `omniroute ...` example plus a flags list. Minor gaps: examples never demonstrate the documented flags (e.g. `health watch --interval 5`) and flag semantics are unstated, so it falls short of fully covering common cases.

4 / 5

Workflow Clarity

A simple, single-purpose read-only skill: install, then run one unambiguous command per task, clearly organized per subcommand. No destructive or batch operations, so the validation cap does not apply, and the simple-skill exception holds.

5 / 5

Progressive Disclosure

Well-organized sections with no external files needed, and the content is small and self-contained. Falls short of 5 because the body (~85 lines) exceeds the under-50-line simple-skill threshold and per-subcommand flag documentation is a natural candidate for splitting into references.

4 / 5

Total

17

/

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.

The description is specific and command-oriented with good natural keywords, but it answers only "what" and not "when" — no explicit trigger guidance exists. Adding a "Use when..." clause and covering the `doctor`/`status` subcommands would raise it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks about server health, uptime, provider status, or circuit breakers, or wants a live metrics dashboard."

Include trigger synonyms users naturally say ("uptime", "diagnostics", "is the server up") to broaden keyword coverage.

Mention or summarize the `doctor` and `status` subcommands (or explicitly scope the skill to health checking only) so the description's coverage matches the body.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions with literal commands ("Check server health, component status, and live metrics", "Run `health`, `health components`, and `health watch`"). Not 5 because the `doctor` and `status` subcommands documented in the body are omitted, leaving minor gaps in coverage.

4 / 5

Completeness

Has a clear "what" but no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines; not 4 since the "when" is entirely absent rather than just imprecise.

3 / 5

Trigger Term Quality

Good natural keywords users would actually say: "server health", "component status", "live metrics", "dashboard", "circuit breakers", "provider status". Missing common synonyms/variants such as "uptime", "diagnostics", or "is the server up", so not 5.

4 / 5

Distinctiveness Conflict Risk

Tied to the omniroute CLI with niche terms ("circuit breakers", "provider status") making it mostly distinct from other skills; minor overlap risk with generic monitoring/status skills keeps it below 5.

4 / 5

Total

15

/

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

diegosouzapw/OmniRoute

Path

skills/cli-health/SKILL.md

Revision

5b3be70

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill