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

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

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

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 with complete executable curl examples and good deferral of schemas to the OpenAPI spec, but it is weakened by duplication between the generated and curated halves and the lack of an explicit sequenced workflow with validation checkpoints.

Suggestions

De-duplicate the generated and curated halves — the preview and settings/compression endpoints appear twice and the opening summary is repeated.

Frame the operations as an explicit sequence with a validation step, e.g. get current settings → preview → enable → re-check settings to confirm.

Move the inline endpoint reference list into the OpenAPI spec link or a separate reference file so SKILL.md stays a concise overview.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows and is mostly concrete, but the generated half and the curated half duplicate content — the preview and settings/compression endpoints each appear twice, and the opening "Configure RTK..." line is repeated — so it could be tightened.	2 / 3
Actionability	Every section provides complete, copy-paste-ready curl commands with full URLs, headers, and JSON payloads (e.g. enable RTK, stacked mode, language packs, preview, disable), matching the anchor for fully executable guidance.	3 / 3
Workflow Clarity	Operations are listed individually and "Preview compression before enabling" plus the "Errors" section act as partial checkpoints, but there is no explicit sequenced workflow with validation/feedback steps (e.g. re-check settings after enabling).	2 / 3
Progressive Disclosure	No bundle files exist and the body defers detailed schemas to the OpenAPI spec (one level deep), which is good; however the API reference is a monolithic inline block and the generated/curated halves create organizational redundancy that could be better split.	2 / 3
	Total	9 / 12 Passed

Description

60%

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-oriented but is missing an explicit "Use when..." trigger clause and relies on product jargon (RTK, Caveman) over natural user phrasing. It is distinguishable but not strongly anchored to its product niche.

Suggestions

Add an explicit trigger clause, e.g. "Use when configuring OmniRoute prompt compression or when the user wants to reduce token usage."

Replace or supplement jargon (RTK, Caveman) with natural terms users would say ("compress terminal output", "compress chat history", "reduce context tokens").

Anchor the description to the product name ("OmniRoute") to reduce overlap with other compression skills.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions: "Configure RTK (command output), Caveman (prose), and stacked compression modes", "Manage language packs, custom rules", and "test prompt compression reducing tokens by 60–90%" — matching the anchor that names several specific concrete actions rather than just a domain.	3 / 3
Completeness	It clearly answers "what does this do" but contains no "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	It includes some natural terms ("compression", "reducing tokens", "prompt compression") but leans heavily on product jargon ("RTK", "Caveman") that a user would not naturally say, and omits common variations like "save tokens" or "compress chat history".	2 / 3
Distinctiveness Conflict Risk	The named engines (RTK, Caveman, stacked) give it a distinct niche, but the generic term "compression" and the absence of a product anchor ("OmniRoute") mean it could still overlap with other compression-related skills.	2 / 3
	Total	9 / 12 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: 3070925

Reviewed: 2 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.