omni-context-rtk

Configure RTK filters, context engineering rules, and context relay settings. Test compression with real prompt samples and manage context transformation pipelines.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/omni-context-rtk/SKILL.md

Quality

Content

68%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, mostly executable API reference with sensible external pointers, but it lacks validation/verification steps for destructive config mutations and ships placeholder request payloads.

Suggestions

Add a validation/verification step after mutating calls (e.g., re-GET /api/context/rtk/config to confirm a PUT took effect) to lift workflow clarity.

Replace the empty '-d "{}"' payloads in PUT/POST examples with minimal representative request bodies so commands are copy-paste ready.

Replace placeholder endpoint descriptions ('GET context › rtk › discover') with one-line explanations of what each endpoint returns.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean curl examples with little over-explanation, but the Overview section repeats the frontmatter description verbatim, a minor redundancy. Not a 5 because of that duplicated overview; clearly above 3 which expects noticeable padding.	4 / 5
Actionability	Each endpoint ships a concrete, mostly executable curl command, but the PUT/POST examples use empty '-d "{}"' payloads, so they are not truly copy-paste ready. Not a 5 because the request bodies are placeholders; above 3 which expects only pseudocode.	4 / 5
Workflow Clarity	Endpoints are enumerated but there are no sequencing or validation checkpoints for the destructive PUT (update config) and POST (import filter) operations, which per the rubric caps workflow clarity at 3. Not a 4 because no verification step exists before or after mutating calls.	3 / 5
Progressive Disclosure	Clear section structure (Overview, Authentication, Endpoints, Payloads) with a one-level pointer to the OpenAPI spec for detailed schemas, and no bundle files to misreference. Not a 5 because the discover/learn endpoint descriptions are vague ('GET context › rtk › discover') and bulk endpoint reference is fully inlined.	4 / 5
	Total	15 / 20 Passed

Description

58%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 does across several concrete actions but omits any 'when to use' trigger guidance, which caps its completeness. Trigger terms lean technical rather than natural, limiting discoverability.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when managing context compression, RTK filters, or context relay settings').

Soften jargon with more common synonyms so users searching for 'context compression' or 'prompt compression' land on this skill.

Clarify what 'context engineering rules' concretely means to lift specificity toward a 5.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Configure RTK filters', 'context engineering rules', 'context relay settings', 'Test compression', 'manage context transformation pipelines') but the actions stay somewhat abstract without enumerating specifics. Not a 5 because the actions are high-level rather than fully concrete, clearly above 3 which expects only 1-2 actions.	4 / 5
Completeness	The 'what' is clear (configure/test/manage context settings) but there is no 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 3. Not a 4 because the 'when' is entirely absent rather than merely implicit.	3 / 5
Trigger Term Quality	Keywords like 'RTK filters', 'context relay', and 'context transformation pipelines' are domain jargon rather than the natural phrases a user would say, and common synonyms/variations are missing. Not a 4 because the term set is technical and lacks natural user vocabulary.	3 / 5
Distinctiveness Conflict Risk	The RTK/context-relay niche is fairly specific and distinguishable from generic skills, with only minor overlap risk against other context-management skills. Not a 5 because 'context engineering' framing could still overlap with adjacent context tooling.	4 / 5
	Total	14 / 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-context-rtk/SKILL.md
Commit: c3945a7

Reviewed: 3 days 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.