CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cli-keys

Create, list, rotate, and revoke OmniRoute API keys from the CLI. Manage OAuth flows for provider authentication and inspect key scopes and expiration.

Quality

68%

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-keys/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 a cleanly structured but mechanical CLI listing: commands and flags are cataloged, yet every example merely restates the usage signature, a duplicated "keys list" section is present, and destructive operations carry no validation or workflow guidance. The entire reference is inlined where a lean overview plus a separate reference file would serve better.

Suggestions

Replace placeholder examples with concrete executable invocations (e.g., "omniroute keys add openai sk-..." and "omniroute keys rotate key_abc123 --grace-period 3600000") and briefly state what each flag does.

Remove the duplicated "keys list" section (lines 40 and 148 define it with conflicting flag sets) and have examples show actual expected output or behavior.

Add validation guidance for destructive operations (remove/revoke/rotate), such as checking "omniroute keys show <id>" before revoking, and clarify when to use regenerate vs rotate vs revoke.

Trim the body to a concise overview plus quick-install and common workflows, moving the full flag-level reference into a references/ file linked from SKILL.md.

DimensionReasoningScore

Conciseness

There is no concept over-explanation, but every "Example" block just repeats the command signature verbatim (e.g., "omniroute keys add <provider> [apiKey]") adding no information, and the "keys list" section appears twice with different flags. This is mostly efficient with clear unnecessary repetition that could be tightened, matching the 3 anchor; it is not 4 because the redundant example blocks and duplicated section are real token waste across ~230 lines.

3 / 5

Actionability

Real commands and flags are enumerated, but all examples are placeholder invocations (<id>, <provider>, [apiKey]) rather than executable, concrete usages, and no flag semantics, valid provider names, or expected outputs are given. This fits the 'some concrete guidance but incomplete; missing key details' anchor; it is not 4 because nothing shown is copy-paste executable.

3 / 5

Workflow Clarity

The body only provides an install step followed by a flat command catalog: no sequencing for multi-step tasks and no validation or confirmation guidance for destructive operations (keys remove, keys revoke, keys rotate) despite their --yes flags. Per the scoring notes, destructive operations without validation cap workflow_clarity at 3; it is not 2 because the catalog itself is coherently organized and the install entry point is clear.

3 / 5

Progressive Disclosure

The full ~230-line CLI API reference is inlined in SKILL.md with no separate reference files (no references/ bundle exists), matching the anchor of a couple hundred lines of API reference that belongs in a separate file. It is not 2 because the content is well-sectioned with clear per-subcommand headers, making navigation reasonable.

3 / 5

Total

12

/

20

Passed

Description

70%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, third-person description with strong product-level distinctiveness, but it lacks any 'Use when...' trigger guidance, which both caps completeness and limits its usefulness for skill routing. Natural trigger keywords are good though missing a few common variants like 'login' or 'auth'.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks to create, rotate, or revoke OmniRoute API keys, set up provider OAuth/login, or check key scopes, rate limits, or expiration."

Broaden trigger coverage with natural synonyms users would say, such as 'login', 'auth', 'tokens', and 'delete key', to raise trigger-term quality.

Mention the policy-setting capabilities (rate limits, cost caps, allowed models) so the 'what' covers the full command surface shown in the body.

DimensionReasoningScore

Specificity

The description lists several concrete actions ("Create, list, rotate, and revoke OmniRoute API keys", "Manage OAuth flows", "inspect key scopes and expiration"), matching the anchor for several specific actions with minor gaps; it omits capabilities present in the body such as usage stats, rate-limit/cost policy setting, and key reveal. It falls short of the 5 anchor because coverage of the actual command surface is incomplete.

4 / 5

Completeness

The 'what' is clear and concrete, but there is no 'Use when...' clause or equivalent trigger guidance, and the judging guideline explicitly caps completeness at 3 when such a clause is missing. It is not a 2 because the 'what' is specific and well-articulated rather than vague.

3 / 5

Trigger Term Quality

Good natural keyword coverage: "API keys", "rotate", "revoke", "OAuth", "CLI", "scopes", "expiration" are phrases users would plausibly say. A few common natural terms are missing (e.g., "login", "auth", "token", "delete key"), so it fits the 'good coverage, a few natural terms missing' anchor rather than the comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

The description is tied to a specific product ("OmniRoute") and a distinct niche (CLI API-key lifecycle and OAuth provider authentication), so conflict risk with other skills is minimal. It clearly matches the 'clear niche with distinct triggers' anchor.

5 / 5

Total

16

/

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-keys/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.