cli-mcp

Inspect the MCP server status, list registered tools and scopes, run tool invocations, and manage MCP audit logs from the CLI.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/cli-mcp/SKILL.md

Quality

Content

65%

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, executable CLI command reference with strong actionability, but it is monolithic and lacks workflow guidance for composing commands into real tasks. Splitting deeper detail into a reference file and adding a short common-usage workflow would improve the weaker dimensions.

Suggestions

Add a brief "Common workflows" section sequencing real multi-command flows (e.g. list tools -> inspect a tool's schema -> call it -> check `mcp tail` for output).

Reduce redundant example blocks that only restate the heading, or make them show real arguments (e.g. `omniroute mcp call search-tool --args '{"q":"hello"}'`).

Move detailed per-flag semantics and worked examples into a `references/` file and link to it from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The reference is lean and avoids over-explaining concepts Claude knows, but ~12 "Example" blocks merely restate the command heading verbatim (e.g. "### mcp status" then `omniroute mcp status`), adding redundancy that could be tightened.	2 / 3
Actionability	Provides exact, copy-paste-ready commands and flags (e.g. `omniroute mcp status`, `--args <json>`, `--stream`, `--scope <s>`) with no pseudocode, matching the score-3 executable anchor.	3 / 3
Workflow Clarity	It is a well-organized catalog of discrete commands, but offers no sequencing for common multi-command flows (e.g. list tools with `mcp tools` then call with `mcp call`) and no validation checkpoints, so it sits below the score-3 clear-workflow level.	2 / 3
Progressive Disclosure	No bundle files or external references exist; the ~140-line reference is entirely inline. Sections are clear, but content that could be progressively disclosed (detailed flag semantics, real-arg call examples) is not split out, so it is not the score-3 well-signaled-reference level.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 clearly occupies a distinct MCP-CLI niche, but it omits explicit trigger guidance and leans on technical phrasing rather than the natural verbs a user would say. Adding a "Use when..." clause and natural-language verbs would raise the weaker dimensions.

Suggestions

Add an explicit trigger clause, e.g. "Use when checking MCP server status, listing or calling MCP tools, or reviewing MCP audit logs from the CLI."

Replace jargon like "tool invocations" and "registered tools" with natural verbs users say, such as "call a tool" and "list tools".

Include common variation terms (e.g. "run", "call", "view") alongside "manage" to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Inspect the MCP server status", "list registered tools and scopes", "run tool invocations", "manage MCP audit logs" — matching the score-3 anchor of multiple specific concrete actions.	3 / 3
Completeness	Clearly states what the skill does but provides no "Use when..." clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Covers relevant domain nouns (MCP, server status, tools, scopes, audit logs, CLI) but leans on jargon ("tool invocations", "registered tools") and misses common verb variations a user would say ("call"/"run"/"view"), so it is not the full-coverage level 3.	2 / 3
Distinctiveness Conflict Risk	Targets a clear, narrow niche (MCP CLI management) with distinct terms unlikely to overlap with unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

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-mcp/SKILL.md
Commit: 3070925

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.