omni-compression

Configure RTK (command output), Caveman (prose), and stacked compression modes. Manage language packs, custom rules, and test prompt compression reducing tokens by 60–90%.

Quality

58%

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-compression/SKILL.md

Quality

Content

57%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 curated half of the body is actionable and well-structured with executable curl examples, but the auto-generated endpoint stub block adds padding and inlines API reference content that should live in a separate file. Removing the stub block and adding an explicit configure→preview→enable workflow with validation would improve the score.

Suggestions

Delete or relocate the auto-generated endpoint stub block (empty `-d '{}'` examples and "POST compression › compare" one-liners) since it duplicates the OpenAPI pointer and adds padding.

Add an explicit sequenced workflow (e.g., 1. preview compression, 2. enable mode, 3. verify via settings GET) with a validation checkpoint before applying a config change.

Move the inlined API endpoint reference into a separate reference file and keep SKILL.md as a concise overview with one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The curated section is lean, but the auto-generated endpoint block (empty `-d '{}'` payloads and stub one-liners like "POST compression › compare") is padding that largely defers to the OpenAPI spec anyway.	3 / 5
Actionability	The curated section provides concrete, copy-paste-ready curl commands with real payloads (RTK, stacked pipeline, caveman config, preview sample, language packs, disable) plus error codes; the generated stub section's empty payloads are a minor gap.	4 / 5
Workflow Clarity	The body is a reference of independent operations with an implicit "preview before enabling" checkpoint, but it lacks a clearly sequenced multi-step workflow with explicit validation/feedback loops for config changes.	3 / 5
Progressive Disclosure	No bundle files exist and section headers are clear with signaled references (OpenAPI spec, entry-point SKILL), but the inlined endpoint stub block is content that belongs in a separate file rather than inline in SKILL.md.	3 / 5
	Total	13 / 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 is specific and third-person with concrete actions, but it lacks any explicit "Use when" trigger guidance and over-relies on product jargon for trigger terms. Adding a trigger clause and more natural synonyms would raise completeness and trigger quality.

Suggestions

Append an explicit "Use when..." clause naming natural triggers (e.g., "Use when reducing token usage, compressing prompt output, or configuring OmniRoute compression engines").

Add user-natural synonyms beyond engine jargon, such as "save tokens", "token reduction", or "prompt compression".

Clarify the vague phrases "custom rules" and "test prompt compression" into concrete, enumerable actions.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("Configure RTK... Caveman... and stacked compression modes", "Manage language packs, custom rules, and test prompt compression") with minor gaps in coverage such as the vague "custom rules" and "test prompt compression" phrasing.	4 / 5
Completeness	The description gives a clear "what" but includes no "Use when..." clause or equivalent trigger guidance, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	Contains relevant keywords ("compression", "tokens", "reducing tokens by 60–90%") but leans on product-specific jargon (RTK, Caveman) and omits common natural synonyms like "save tokens" or "token reduction".	3 / 5
Distinctiveness Conflict Risk	The named engines (RTK, Caveman, stacked) carve a clear niche with distinct triggers, but the absence of a product name and the generic term "compression" leave minor overlap risk with other compression skills.	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-compression/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.