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

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/omni-compression/SKILL.md

Quality

Content

65%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 highly actionable with copy-paste curl examples and a useful comparison table, but suffers from duplicated sections between the generated and curated halves, lacks a sequenced config workflow with verification steps, and inlines API reference content that could be split out.

Suggestions

Deduplicate the generated Endpoints section and the curated body (preview and language-pack examples appear twice); keep one canonical set.

Add a short sequenced workflow with a verification checkpoint, e.g. PUT settings then GET /api/settings/compression to confirm the change applied.

Move the bulk endpoint reference into a referenced file (the openapi spec) and keep SKILL.md as an overview pointing to it.

Dimension	Reasoning	Score
Conciseness	Mostly tight curl snippets, but the body duplicates content (the generated Endpoints/preview section and the curated 'Preview compression before enabling' and 'Language packs' sections overlap) and repeats the description verbatim in the Overview.	3 / 5
Actionability	Fully executable, copy-paste-ready curl commands cover the common cases (enable RTK/stacked/Caveman, preview, configure thresholds, disable) with concrete request bodies and error codes.	5 / 5
Workflow Clarity	Operations are listed as a menu rather than a sequenced workflow; there are no validation/verification checkpoints (e.g., check settings after a PUT) to confirm a configuration change took effect.	3 / 5
Progressive Disclosure	Has section headers and one clear external reference ('See the full OpenAPI specification... or docs/openapi.yaml'), but a large API reference is inlined in SKILL.md and the generated/curated halves duplicate structure rather than splitting cleanly.	3 / 5
	Total	14 / 20 Passed

Description

71%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 action-rich with a clear niche, but lacks any explicit 'when to use' trigger guidance and leans on product-specific jargon (RTK, Caveman) rather than broadly natural phrasing.

Suggestions

Add a 'Use when...' clause stating when Claude should invoke this skill (e.g., 'Use when reducing token usage for LLM requests or compressing command/chat output').

Soften product jargon by pairing RTK/Caveman with natural phrasing like 'compress terminal output' or 'compress chat history'.

Include common synonyms users actually say, such as 'save tokens' or 'trim context'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Configure RTK... Caveman... and stacked compression modes', 'Manage language packs, custom rules', and 'test prompt compression' — covering the domain comprehensively.	5 / 5
Completeness	Has a clear 'what' (configure modes, manage packs/rules, test compression) but no 'Use when...' trigger clause, capping completeness at 3 per the missing-trigger guidance.	3 / 5
Trigger Term Quality	Good natural keywords ('compression', 'reducing tokens', 'prompt compression', 'language packs'), but RTK/Caveman/stacked are product jargon and common synonyms like 'save tokens' or 'compress chat history' are missing.	4 / 5
Distinctiveness Conflict Risk	Specific to OmniRoute prompt compression with named engines (RTK, Caveman), giving a clear niche with only minor overlap risk against other token-reduction skills.	4 / 5
	Total	16 / 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: ea0cdc5

Reviewed: about 6 hours 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.