CtrlK
BlogDocsLog inGet started
Tessl Logo

omni-settings

Read and update global application settings: system prompts, thinking budget, IP filters, payload rules, combo defaults, and require-login configuration.

58

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/omni-settings/SKILL.md
SKILL.md
Quality
Evals
Security

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 content is a compact, well-organized API reference with concrete curl examples and no token waste. It falls short on actionability for write operations (empty payloads, externalized schemas) and lacks validation guidance for destructive endpoints.

Suggestions

Replace the empty `-d '{}'` bodies on write endpoints with minimal representative payloads or inline the key fields for at least the most common updates so the examples are executable as written.

Add explicit validation/verification steps and warnings for destructive operations (e.g. purge-request-history, purge-usage-history), such as confirming scope before calling and re-GETting to verify the result.

Consider splitting the long endpoint listing into grouped reference files (e.g. memory.md, qdrant.md, proxy.md) referenced one level deep from SKILL.md to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is a lean endpoint reference: each endpoint gets a one-line description and a curl example with no padding or explanation of concepts Claude already knows, so every token earns its place.

3 / 3

Actionability

GET endpoints are copy-paste ready, but every PUT/PATCH/POST uses an empty `-d '{}'` body and request schemas are deferred to an external OpenAPI spec, leaving the write operations incomplete rather than fully executable.

2 / 3

Workflow Clarity

Endpoints are clearly listed, but destructive operations (purge-request-history, purge-usage-history, require-login toggle, ip-filter) carry no validation checkpoints or verify-before-proceeding guidance, capping workflow clarity at 2.

2 / 3

Progressive Disclosure

Sections are well-organized by endpoint and schema detail is deferred to the OpenAPI spec, but the body is a long monolithic inline listing (~30 endpoints) rather than content split across one-level-deep bundle references.

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 distinct, clearly stating what the skill does and naming concrete setting categories. Its main weakness is the missing explicit "Use when..." trigger guidance, which limits completeness and natural trigger-term coverage.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to read or change global application settings such as system prompts, thinking budget, IP filters, payload rules, combo defaults, or require-login."

Soften internal jargon like "combo defaults" and "payload rules" with more natural user-facing phrasings to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

"Read and update global application settings: system prompts, thinking budget, IP filters, payload rules, combo defaults, and require-login configuration" names two concrete actions and enumerates six specific setting categories, matching the multiple-specific-actions anchor.

3 / 3

Completeness

The "what" is clearly stated, but there is no "Use when..." or equivalent explicit trigger guidance for when Claude should invoke the skill, which caps completeness at 2 per the guidelines.

2 / 3

Trigger Term Quality

Terms like "application settings," "system prompts," and "IP filters" are reasonably natural, but jargon such as "combo defaults" and "payload rules" and the absence of common user phrasings leave coverage partial rather than comprehensive.

2 / 3

Distinctiveness Conflict Risk

The enumerated settings (thinking budget, payload rules, require-login, etc.) carve out a clear niche tied to this application's global settings, making it unlikely to trigger for an unrelated skill.

3 / 3

Total

10

/

12

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.