CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

omni-api-keys

Create, list, rotate, and revoke OmniRoute API keys. Control per-key scopes, spending limits, and expiration. Keys gate access to all proxy and management endpoints.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/omni-api-keys/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 is a well-structured, machine-generated API catalog: every endpoint has a concrete curl example, and a few (import, access, groups PUT) carry genuinely useful behavioral detail. However, most mutation examples have empty '{}' bodies with no payload fields, destructive operations lack verification steps, and the bulk endpoint reference is inlined rather than split into a reference file, leaving all dimensions at the midpoint.

Suggestions

Replace the empty -d '{}' bodies on POST/PATCH/PUT endpoints with realistic example payloads (e.g., a named key with scope and spending limit), or inline one complete create-key example per resource type.

Add a short multi-step workflow for key rotation (create replacement, migrate consumers, verify, revoke old key) and a verification step before DELETE, e.g. checking the key's usage via GET /api/keys/{id} first.

Move the bulk endpoint catalog to a references/ file (e.g., references/endpoints.md) and keep SKILL.md to an overview, authentication notes, and the most common operations.

DimensionReasoningScore

Conciseness

Per-endpoint content is lean (one-line description plus curl), but there is padding: "POST keys › <id> › regenerate"-style breadcrumb headings duplicate the endpoint headings, the Overview repeats the frontmatter description verbatim, and roughly a dozen endpoints carry no real description at all. This is mostly efficient but could be tightened, matching anchor 3 rather than the trimmable-minor-instances of anchor 4.

3 / 5

Actionability

Concrete curl commands exist for every endpoint and the import example shows a full payload, but most mutation endpoints use empty bodies (-d '{}') with no field guidance, and POST /api/keys with '{}' would trigger the documented 422 for blocking missing references. The examples are concrete yet missing key executable details, matching anchor 3 rather than the minor-gaps level of anchor 4.

3 / 5

Workflow Clarity

Each single operation is unambiguous and conflict semantics (409, 422) are documented for several endpoints, but destructive operations like DELETE /api/keys/{id} have no verification guidance, and the rotation task promised in the description is never sequenced. Per the rubric, missing validation for destructive operations caps workflow clarity at 3.

3 / 5

Progressive Disclosure

The body is well-sectioned (## Endpoints, ## Payloads, per-endpoint ### headers) and clearly signals the authoritative OpenAPI spec ("See the full OpenAPI specification at GET /api/openapi/spec or docs/openapi.yaml"), but ~320 lines of API reference are inlined in SKILL.md with no bundle files, matching anchor 3 (content that should be separate is inline) rather than anchor 4.

3 / 5

Total

12

/

20

Passed

Description

75%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, action-oriented, and clearly scoped to a distinct niche, with strong natural trigger terms for the key-management domain. Its main weakness is the absence of any explicit "Use when..." trigger guidance, which caps completeness, and it omits common synonyms like "token" or "credential".

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to create, rotate, revoke, or manage OmniRoute API keys, or mentions key scopes, spending limits, or key expiration."

Include natural synonyms such as "token", "credential", or "access key" so the description matches more varied user phrasings.

DimensionReasoningScore

Specificity

"Create, list, rotate, and revoke OmniRoute API keys. Control per-key scopes, spending limits, and expiration" lists multiple concrete actions with comprehensive coverage of the key lifecycle (CRUD plus rotation and policy control). This matches the anchor for comprehensive concrete actions; score 4 would require noticeable coverage gaps, which are absent.

5 / 5

Completeness

The description clearly answers "what" (create/list/rotate/revoke keys, control scopes/limits/expiration) but contains no "Use when..." clause or equivalent trigger guidance; "Keys gate access to all proxy and management endpoints" only weakly implies when. Per the rubric guideline, a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Terms like "API keys", "rotate", "revoke", "scopes", "spending limits", and "expiration" are natural phrases users would say, giving good keyword coverage. Common synonyms such as "token", "credential", or "access key" are missing, so it falls short of the comprehensive-synonyms anchor at 5.

4 / 5

Distinctiveness Conflict Risk

"OmniRoute API keys" carves out a clear product-specific niche with distinct triggers (key management, scopes, spending limits), so conflict with other skills is minimal. It clearly matches the clear-niche anchor rather than the minor-overlap anchor at 4.

5 / 5

Total

17

/

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/omni-api-keys/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.