CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cli-mcp

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

Quality

71%

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

Quality

Content

61%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.

A clean, well-organized CLI reference with real install instructions and executable commands for most subcommands, but it stops short of being fully actionable: the central 'mcp call' feature has only a placeholder example with ambiguous flag usage, two subcommands lack descriptions, and no cross-command workflow or verification steps are shown. Redundant placeholder examples slightly dilute token efficiency.

Suggestions

Replace the 'mcp call' placeholder with a concrete executable example, e.g. 'omniroute mcp call weather {"city":"Paris"} --scope default', and clarify when to use '--args' vs the positional '[argsJson]'.

Add one-line descriptions for the bare 'mcp' and 'mcp enable' subcommands so every section explains what the command does, and demonstrate at least one non-trivial flag (e.g. 'mcp status --json', 'mcp scopes --tool <name>').

Trim redundant 'Example' blocks that merely restate the heading, and add a short verification note such as running 'mcp status' after 'mcp restart' to confirm the server came back up.

DimensionReasoningScore

Conciseness

The body is a lean generated reference with no explanation of concepts Claude already knows, but the Overview duplicates the description verbatim and each 'Example' block merely repeats the subcommand placeholder (e.g. 'omniroute mcp call <tool> [argsJson]'), adding tokens without new information.

4 / 5

Actionability

Most commands (status, restart, disable, scopes) are copy-paste ready, but the flagship 'mcp call' example is an unexpanded placeholder with ambiguous argument passing ('--args <json>' vs positional '[argsJson]'), and 'mcp' and 'mcp enable' have no description of what they do — missing key details rather than minor gaps.

3 / 5

Workflow Clarity

Sections are organized per subcommand and individually unambiguous, but there is no sequencing across commands (e.g. install → check status → call a tool) and no validation guidance, such as verifying server status after 'mcp restart' or confirming a call succeeded.

3 / 5

Progressive Disclosure

A single, well-sectioned self-contained file with clear headers per subcommand and no bundle files to reference; appropriately inlined for its size, though the placeholder-example redundancy could be tightened and the file sits just past the under-50-lines simple-skill threshold.

4 / 5

Total

14

/

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.

A concrete, third-person description that names four specific capabilities with a clear CLI framing, but it is missing an explicit 'Use when...' trigger clause and omits the restart/enable/disable management operations shown in the body. It reads as a solid capability summary rather than a complete discovery-oriented description.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to check or restart the MCP server, invoke or test an MCP tool, or inspect tool scopes from the command line.'

Mention the management operations the CLI actually supports (restart, enable, disable) so the description's coverage matches the body's subcommands.

Add common synonyms such as 'Model Context Protocol' and 'call an MCP tool' to widen natural trigger-term coverage.

DimensionReasoningScore

Specificity

The description lists several concrete actions — 'Inspect the MCP server status, list registered tools and scopes, run tool invocations, and manage MCP audit logs from the CLI' — but omits the body's restart/enable/disable capabilities, leaving minor gaps that fall short of the comprehensive anchor.

4 / 5

Completeness

The 'what' is clear and specific, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Natural domain terms like 'MCP server', 'tools', 'scopes', 'tool invocations', 'audit logs', and 'CLI' are present and would plausibly be said by users, but synonyms and variations (e.g. 'Model Context Protocol', 'call an MCP tool') are missing.

4 / 5

Distinctiveness Conflict Risk

The niche — managing an MCP server and invoking tools from the omniroute CLI — is mostly distinct, with only minor overlap risk against generic MCP tooling skills.

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-mcp/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.