CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cli-providers

Manage provider connections from the CLI: list available/configured providers, add, test, test-all, validate, rotate API keys, and view per-provider metrics.

Quality

66%

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-providers/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 curated second half is genuinely strong — executable, well-commented commands plus concrete error-recovery guidance — but it is undermined by a generated first half that duplicates it with placeholder pseudo-examples and undescribed flag lists. The skill is also a monolithic 330-line inline catalog where destructive/batch operations (key rotation, test-all) get no validation workflow.

Suggestions

Remove or collapse the generated "Subcommands" section — it duplicates the curated catalog while replacing real examples with usage placeholders like `omniroute provider-cmd provider [subcommand]` — and fix the truncated "Manage provider connections (use" sentence.

Split the keys, oauth, nodes, combos, and compression catalogs into reference files (e.g. references/keys.md) linked one level deep from SKILL.md, keeping only the provider connection workflow inline.

Add a short validation workflow for risky operations, e.g. "run `providers rotate --dry-run` first, then rotate, then `providers test <id>` to confirm" — mirroring the good pattern already present in the Errors section.

DimensionReasoningScore

Conciseness

The generated "Subcommands" half duplicates the curated half almost command-for-command, pads each command with a Flags/Example block even when the "example" just restates the usage placeholder (e.g. `omniroute provider-cmd provider [subcommand]`), lists `--json` under nearly every command, and contains a truncated sentence ("Manage provider connections (use"), matching anchor 2's 'noticeably verbose; several padded sections' rather than anchor 3's mostly-efficient content.

2 / 5

Actionability

The curated half is copy-paste ready with concrete commands and comments (`providers available --search openai`, multi-line `keys policy set`, `combo create --strategy priority`) plus an Errors section with specific recovery steps, but several first-half subcommands (`rotate`, `status`, `metrics`) list flags with no description of what the command does, fitting anchor 4's 'concrete commands with minor gaps' rather than anchor 5.

4 / 5

Workflow Clarity

The body is a command catalog with no sequenced workflow, and the destructive `keys rotate` (revokes the old key) and batch `test-all` operations lack validation checkpoints — the listed `--dry-run`/`--skip-test` flags are never woven into guidance — so the batch/destructive cap holds it at 3 despite the partial feedback loops in the Errors section.

3 / 5

Progressive Disclosure

No bundle files exist, and a ~330-line command catalog is inlined entirely in SKILL.md with keys/oauth/nodes/combos/compression sections that are natural candidates for separate reference files; section headers provide reasonable structure and the two external skill links are clearly signaled and one level deep, matching anchor 3 rather than anchor 2's unstructured inline dump.

3 / 5

Total

12

/

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 action-oriented, listing the core CLI subcommands a user would invoke, with good natural trigger terms like "rotate API keys" and "test". Its main weakness is the complete absence of a 'Use when...' trigger clause, which caps completeness, and slightly terse action verbs like "add" and "test" that leave minor coverage gaps.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to add, test, or rotate API keys or provider connections, or check provider status/metrics from the CLI."

Clarify the terse verbs — "add" and "test" could read as "add a provider connection" and "test a connection" — and consider mentioning key/credential management since it is a major part of the skill's content.

Include a few synonyms users naturally say ("credentials", "connection") to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Enumerates several concrete actions ("list available/configured providers, add, test, test-all, validate, rotate API keys, and view per-provider metrics") but a few are terse ("add", "test") and coverage of the domain (keys, oauth, nodes) is partial, matching the 'several specific actions; minor gaps' anchor rather than the comprehensive anchor 5.

4 / 5

Completeness

The 'what' is clear and action-specific, but there is no 'Use when...' clause or any equivalent trigger guidance, which per the judging guidelines caps completeness at 3; it is not a 4 because 'when' is entirely absent rather than just imprecise.

3 / 5

Trigger Term Quality

Contains natural phrases users would say such as "rotate API keys", "test" providers, and "per-provider metrics", but misses common synonyms like "credentials" or "connections", fitting anchor 4 (good coverage, a few natural terms missing) rather than anchor 5's synonym-complete coverage.

4 / 5

Distinctiveness Conflict Risk

"Manage provider connections from the CLI" plus "rotate API keys" and "per-provider metrics" carves a distinct CLI niche with clear triggers; minor overlap risk remains with closely related sibling skills (models, combos, keys) referenced in the body, so anchor 4 fits better than 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-providers/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