cli-compression

Configure and test prompt compression from the CLI. Manage RTK filters, Caveman rules, stacked compression modes, and preview compression output with real prompts.

Quality

56%

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/cli-compression/SKILL.md

Quality

Content

47%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 lean but largely uninformative command catalog: real commands with no semantics, no workflow sequencing, and no validation for the destructive remove operation. The duplicate 'compression list' section signals auto-generation without review.

Suggestions

Add a one-line description of what each subcommand does and give example values for flags (e.g. '--engine rtk --caveman-aggressiveness 3').

Group subcommands by purpose (configuration, inspection, rule management) and note any required ordering, e.g. configure engine before preview.

Remove the duplicate 'compression list' section and add a validation step before the destructive 'compression remove <id>' (e.g. run 'compression list' first to confirm the id).

Dimension	Reasoning	Score
Conciseness	It avoids over-explaining concepts Claude knows, but the duplicate 'compression list' section and repetitive 'Example:' scaffolding around bare commands waste tokens that could be a tighter list.	3 / 5
Actionability	Commands are copy-paste runnable, but key details are missing: no description of what each subcommand does, no example flag values, and flags like '--engine <e>' and '--caveman-aggressiveness <n>' are listed without explanation.	3 / 5
Workflow Clarity	There is no sequence or workflow guidance (e.g. configure before status, set engine before preview), and the destructive 'compression remove <id>' with '--yes' has no validation checkpoint, so this falls below the midpoint.	2 / 5
Progressive Disclosure	Content is well-organized into one section per subcommand with no external references needed for a CLI reference, but the duplicate 'compression list' section and lack of subcommand grouping (configure vs query vs management) are minor organization gaps.	4 / 5
	Total	12 / 20 Passed

Description

66%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 conveys concrete capabilities with distinctive, domain-specific terminology, but omits any explicit 'Use when' trigger guidance, which caps completeness. Adding a trigger clause would lift the weakest dimension.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user wants to compress prompts, reduce token usage, or tune RTK/Caveman compression settings from the CLI.'

Add a few natural synonyms users might say ('reduce tokens', 'shrink prompt', 'save context budget') to broaden trigger term coverage.

Mention the remaining subcommand families (stats, combos, language-packs, add/remove rules) for more comprehensive capability coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Configure and test prompt compression', 'Manage RTK filters, Caveman rules, stacked compression modes', 'preview compression output' — with only minor gaps (stats, combos, add/remove rules not named).	4 / 5
Completeness	The 'what' is clear, but there is no 'Use when...' clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	'prompt compression', 'CLI', and 'compression output' are natural user terms with good coverage, but common synonyms like 'reduce tokens' or 'save tokens' and any file extensions are missing.	4 / 5
Distinctiveness Conflict Risk	Niche terminology ('RTK filters', 'Caveman rules', 'stacked compression modes') makes it mostly distinct with only minor overlap risk against other compression-related skills.	4 / 5
	Total	15 / 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/cli-compression/SKILL.md
Commit: ea0cdc5

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.