CtrlK
BlogDocsLog inGet started
Tessl Logo

cli-chat

Send chat completions, stream responses, and start an interactive REPL session from the CLI. Supports all OmniRoute providers, combo routing, and system prompt configuration.

56

Quality

63%

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

Quality

Content

67%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 clean, well-organized CLI reference that stays concise, but its examples are non-executable placeholders that reduce actionability. Structure and navigation are solid for a self-contained skill of this size.

Suggestions

Replace placeholder examples with real, runnable invocations that combine common flags (e.g., 'omniroute chat --model gpt-4o --system "You are helpful" --stream "Explain recursion"').

Drop or repurpose the Overview section since it duplicates the frontmatter description verbatim, saving tokens.

Add brief one-line purpose statements per subcommand so the intent of each command is clear beyond its flag list.

DimensionReasoningScore

Conciseness

The body is lean with concise flag lists and no padding, though the Overview section repeats the frontmatter description verbatim, a minor redundancy that could be trimmed.

4 / 5

Actionability

Concrete flag names are listed per subcommand, but the examples are placeholder-only ('omniroute chat [prompt]') with no real invocations combining flags, leaving key execution details missing.

3 / 5

Workflow Clarity

Subcommands are clearly organized with consistent flag and example sections, giving an unambiguous single-action-per-command structure with only minor gaps in usage guidance.

4 / 5

Progressive Disclosure

Content is well structured with clear section headers and no external bundle files needed, though the entire flag reference is inlined in one file rather than split out.

4 / 5

Total

15

/

20

Passed

Description

58%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 clearly conveys the skill's concrete capabilities in third person but omits any explicit 'when to use' trigger guidance, capping completeness. Trigger terms are relevant but lean technical and lack natural synonyms.

Suggestions

Add an explicit 'Use when...' clause naming natural user phrases (e.g., 'Use when the user wants to chat with an OmniRoute model, stream a response, or run an interactive session from the command line').

Broaden trigger terms with natural synonyms users would actually say, such as 'chat with a model', 'stream output', or 'interactive prompt'.

Clarify 'combo routing' with a plainer phrase so the description is not gated on OmniRoute-specific jargon.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Send chat completions, stream responses, and start an interactive REPL session') plus supporting features (combo routing, system prompt configuration), with only minor gaps in coverage.

4 / 5

Completeness

It clearly states what the skill does but provides no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Relevant terms like 'chat completions', 'stream responses', 'REPL session', and 'CLI' are present, but several are technical jargon ('OmniRoute providers', 'combo routing') and common natural synonyms are missing.

3 / 5

Distinctiveness Conflict Risk

The OmniRoute-specific framing plus distinct triggers ('REPL session', 'combo routing') make it mostly distinguishable from other skills, with only minor overlap risk.

4 / 5

Total

14

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
diegosouzapw/OmniRoute
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.