CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

53

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/cli-compression/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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 flat, reasonably lean CLI command reference, but it offers little beyond restating each subcommand and lacks real flag usage, workflow sequencing, and validation for destructive operations. A duplicated section further signals loose organization.

Suggestions

Remove the duplicated "compression list" section and give examples real flag values (e.g. `omniroute compression configure --engine caveman --caveman-aggressiveness 3`) instead of bare command restatements.

Add a short sequenced workflow (configure → preview → status/stats) with an explicit validation/confirmation checkpoint for the destructive `compression remove` command.

Move the full per-subcommand reference into a separate reference file and keep SKILL.md as a concise overview with a clearly signaled link.

DimensionReasoningScore

Conciseness

The body is mostly lean and avoids explaining concepts Claude knows, but it includes a duplicated "compression list" section (lines 83 and 111) and examples that merely restate the heading command, so not every token earns its place.

2 / 3

Actionability

Commands are real and executable-looking, yet examples show bare invocations with no flag values (e.g. `omniroute compression configure` despite listing `--engine`, `--caveman-aggressiveness` flags), leaving key details missing.

2 / 3

Workflow Clarity

Subcommands are listed but there is no sequence for the implied configure→preview→status workflow, and the destructive `compression remove <id>` operation has no validation or confirmation guidance beyond a `--yes` flag, capping clarity at 2.

2 / 3

Progressive Disclosure

Sections are labeled, but the body is a ~150-line inline command reference that reads as a monolithic dump (with a duplicate section) rather than an overview pointing to a separate reference file.

2 / 3

Total

8

/

12

Passed

Description

67%

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 distinctive, clearly conveying a niche CLI compression capability with multiple concrete actions. Its main weakness is the absence of an explicit "Use when..." trigger clause and reliance on product jargon over natural user phrasing.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "Configure and test prompt compression from the CLI", "Manage RTK filters, Caveman rules, stacked compression modes", and "preview compression output with real prompts" — matching the anchor for listing multiple specific concrete actions.

3 / 3

Completeness

It clearly states what the skill does but provides no "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

"prompt compression" is a natural user term, but "RTK filters", "Caveman rules", and "stacked compression modes" are product-specific jargon with missing common variations, so it lands at "some relevant keywords but missing common variations" rather than full coverage.

2 / 3

Distinctiveness Conflict Risk

The narrow focus on omniroute CLI prompt compression with distinctive terms (RTK filters, Caveman rules) gives it a clear niche unlikely to trigger for unrelated skills.

3 / 3

Total

10

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
diegosouzapw/OmniRoute
Reviewed

Table of Contents

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.