omni-mcp

Connect to the OmniRoute MCP server (107 tools, 3 transports: SSE/stdio/HTTP). Covers routing, cache, compression, memory, skills, providers, and audit tools across 32 permission scopes.

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

66%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 concise and largely actionable, with ready-to-use config snippets and a well-organized tool catalog that links one level deep to fuller docs. Its main weakness is workflow clarity: setup is shown via config fragments without an explicit ordered sequence or a verification step that the connection works.

Suggestions

Add an explicit numbered setup workflow: (1) set OMNIROUTE_URL and OMNIROUTE_KEY, (2) add the config block, (3) restart the client, (4) verify with a health check via omniroute_get_health.

Remove the duplicated description sentence in the Overview section and the 'manual edits will be overwritten' generator comment to tighten conciseness.

Add one concrete tool-invocation example (e.g. calling omniroute_get_health or omniroute_route_request) so users can confirm the connection end-to-end.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean — short transport bullets, compact config snippets, and a tight tool table — with only minor padding (the duplicated first line in Overview, the 'manual edits will be overwritten' comment) that could be trimmed.	4 / 5
Actionability	It provides copy-paste-ready Claude Desktop and Cursor/VS Code JSON configs, concrete endpoint URLs, and exact env var names; the only gap is that transport/connection steps are stated as bullets rather than a fully runnable sequence, and there is no executable invocation example.	4 / 5
Workflow Clarity	Setup is implied through the config snippets but there is no explicit step sequence (set env vars → add config → (re)start client → verify), and no validation/verification step that the server is reachable, which caps this dimension at 3.	3 / 5
Progressive Disclosure	The body is well-structured with clear sections and points one level deep to external docs (the GitHub MCP-SERVER.md and entry-point SKILL URLs) for detail; no bundle files exist to verify inline references, but the in-body structure and external links are clearly signaled.	4 / 5
	Total	15 / 20 Passed

Description

50%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 about its niche (OmniRoute MCP server, tool/transport/scope counts) and reasonably distinct, but it reads as a capability catalog rather than an action-oriented trigger. The main weakness is the missing 'Use when...' trigger guidance, which caps completeness and weakens natural keyword coverage.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when connecting to the OmniRoute MCP server, routing requests across providers, or managing OmniRoute cache/memory/scopes.'

Reframe coverage areas as concrete actions ('route requests', 'flush cache', 'manage memory', 'invoke skills') rather than noun lists to raise specificity.

Include the natural phrasings users would say ('OmniRoute', 'route LLM requests', 'MCP tool routing') alongside the technical jargon.

Dimension	Reasoning	Score
Specificity	The description names the concrete domain (MCP server with 107 tools, three transports, 32 permission scopes) and lists covered areas (routing, cache, compression, memory, skills, providers, audit), but it does not enumerate concrete actions a user can perform — it describes coverage rather than operations.	3 / 5
Completeness	The 'what' is clearly stated (connect to the OmniRoute MCP server across tools/transports/scopes), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	It includes some natural keywords a user might say ('MCP server', 'routing', 'cache', 'memory') but is dominated by technical jargon ('SSE/stdio/HTTP', 'permission scopes') and lacks the common phrasings a user would naturally utter to invoke this skill.	3 / 5
Distinctiveness Conflict Risk	The OmniRoute-specific naming and concrete tool/scope counts give it a fairly distinct niche with only minor overlap risk against other MCP-connection skills; it would not easily trigger for unrelated skills.	4 / 5
	Total	13 / 20 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/omni-mcp/SKILL.md
Commit: ea0cdc5

Reviewed: about 6 hours 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.