CtrlK
BlogDocsLog inGet started
Tessl Logo

omni-mcp

Connect to the OmniRoute MCP server (110 tools, 3 transports: SSE/stdio/HTTP). Covers routing, cache, compression, memory, skills, providers, and audit tools across 33 permission scopes.

48

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/omni-mcp/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 body provides concrete, executable curl and config examples and good navigation to external docs, but is padded with a duplicated overview, redundant breadcrumb lines, and repetitive curl blocks, and lacks an explicit connect-and-verify workflow. Structure is reasonable but inlines content that belongs in a separate reference file.

Suggestions

Remove the duplicated Overview paragraph (it repeats the frontmatter description verbatim) and the redundant 'GET mcp › audit' breadcrumb lines under each heading.

Collapse the eight near-identical curl examples into one parameterized template plus a compact endpoint table, moving the full per-endpoint detail to a separate references file.

Add a short numbered connect workflow with a validation step (e.g., call GET /api/mcp/status to confirm the token and transport before further requests).

DimensionReasoningScore

Conciseness

The body duplicates the frontmatter description in the Overview, repeats a redundant breadcrumb line under every endpoint heading, and inlines eight near-identical curl blocks, all noticeably padded; it does not over-explain concepts Claude knows, so it sits above 1 but below the midpoint.

2 / 5

Actionability

Copy-paste-ready curl commands and complete JSON config blocks for Claude Desktop and Cursor/VS Code give mostly executable guidance, with minor gaps such as empty `-d '{}'` payloads and a representative (not exhaustive) tool table.

4 / 5

Workflow Clarity

Authentication and transport/config sections imply a connect-then-call sequence, but there is no explicitly numbered workflow or validation checkpoint (e.g., verify the token works), and the operation is not destructive so the hard cap does not apply.

3 / 5

Progressive Disclosure

Sections are headed and point to external references (OpenAPI spec, full docs URL, live tools endpoint), but the eight-endpoint catalog and tool table are inlined rather than split into a separate reference file, and no bundle files exist to offset this.

3 / 5

Total

12

/

20

Passed

Description

53%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 states what the skill connects to and enumerates its tool surface, but lacks an explicit 'Use when' trigger clause and leans on technical jargon over natural user phrasing. It is specific to the OmniRoute niche with low conflict risk.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when routing requests through OmniRoute, managing MCP scopes, or debugging OmniRoute MCP connections').

Replace generic verbs ('Covers') with concrete user actions ('Route requests, flush cache, search memory, invoke skills').

Include natural synonyms and file/URL cues users might actually say (e.g., 'OmniRoute', 'MCP', 'stdio/SSE/HTTP transport').

DimensionReasoningScore

Specificity

Names the domain ('OmniRoute MCP server') and enumerates seven tool categories (routing, cache, compression, memory, skills, providers, audit), but only weakly action-oriented verbs ('Connect', 'Covers') rather than multiple concrete user actions, matching the 'names domain and 1-2 concrete actions' anchor.

3 / 5

Completeness

The 'what' is clear (connect to a 110-tool MCP server across these scopes) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant keywords are present (MCP server, SSE/stdio/HTTP, the tool category names) but the language is jargon-heavy and missing common variations or synonyms a user might naturally say, fitting the 'some relevant keywords but missing variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The OmniRoute product name plus specific transports and scope list make it mostly distinct with only minor overlap risk against generic MCP-server skills, fitting just above the 'somewhat specific' anchor.

4 / 5

Total

13

/

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.