CtrlK
BlogDocsLog inGet started
Tessl Logo

omni-providers

Manage provider connections, API keys, OAuth flows, and connection tests via the REST API. List, add, update, remove, and test AI provider integrations (OpenAI, Anthropic, Gemini, and 160+).

63

Quality

73%

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-providers/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 body is highly actionable — every endpoint ships a complete curl example — but it reads as a flat reference catalog rather than a guided workflow, with no validation checkpoints and most API detail kept inline instead of progressively disclosed. Minor repetition across curl blocks and a duplicated Overview slightly reduce conciseness.

Suggestions

Move the per-endpoint detail into a separate reference file (e.g. references/providers-api.md) and keep SKILL.md as an overview that links to it, improving progressive disclosure.

Add a short workflow for common multi-step tasks — e.g. create a provider, then call /test to verify, then /refresh on token expiry — with an explicit validation/checkpoint step.

De-duplicate curl examples by stating the common Authorization header once and showing per-endpoint only the differing method/path/body, and drop the verbatim Overview that repeats the description.

DimensionReasoningScore

Conciseness

Each endpoint is a lean one-line description plus an executable curl command with no conceptual padding, but the ~22 near-identical curl blocks repeat the Authorization header verbatim and the Overview duplicates the frontmatter description, so it could be tightened.

2 / 3

Actionability

Every endpoint provides a complete, copy-paste-ready curl command with method, full URL, headers, and body placeholder — fully executable guidance rather than pseudocode.

3 / 3

Workflow Clarity

Endpoints are catalogued with some grouping and an OpenAPI pointer, but there is no multi-step sequence (e.g. create -> test -> validate) and no validation/verification steps for batch (import-bulk up to 50) or destructive operations, capping workflow clarity at 2.

2 / 3

Progressive Disclosure

The body is a ~250-line inline API catalog that could live in a separate reference file; although the 'See the full OpenAPI specification at docs/openapi.yaml' pointer is a clear one-level signal, the bulk of detail remains inline rather than split out.

2 / 3

Total

9

/

12

Passed

Description

82%

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 distinctive, naming concrete actions and natural trigger terms with a clear niche. Its main weakness is the absence of an explicit 'Use when...' clause, leaving the activation trigger only implied.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to add, test, or troubleshoot AI provider connections or manage API keys / OAuth credentials.'

Consider natural trigger variations users might say — 'add an API key', 'connect OpenAI/Anthropic/Gemini', 'test a provider connection' — to improve keyword reach.

Keep the current concrete action list; it is the strongest part of the description.

DimensionReasoningScore

Specificity

Enumerates multiple concrete actions — 'List, add, update, remove, and test' plus 'Manage provider connections, API keys, OAuth flows, and connection tests' — matching the anchor for listing several specific concrete actions.

3 / 3

Completeness

Clearly states what the skill does but has no explicit 'Use when...' trigger clause, so 'when' is only implied; per the guidelines, a missing explicit trigger caps completeness at 2 rather than 3.

2 / 3

Trigger Term Quality

Uses natural terms a user managing providers would say — 'API keys', 'OAuth flows', 'connection tests', 'REST API' — alongside named providers 'OpenAI, Anthropic, Gemini', giving good keyword coverage.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche — managing AI provider integrations and credentials via REST API with named providers — making it unlikely to trigger for unrelated skills.

3 / 3

Total

11

/

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.