CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

61%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.

A reasonably lean and well-sectioned CLI reference, but it reads like raw generated output: duplicated sections, placeholder-only examples, and undocumented flag semantics leave Claude unable to actually execute most commands without guessing. Sequencing and validation guidance are absent for what includes a destructive remove operation.

Suggestions

Remove the duplicate 'compression list' section (it appears twice in the body).

Replace placeholder examples with realistic executable ones, e.g. 'omniroute compression set caveman-aggressive' and 'omniroute compression preview --file prompt.txt', and show the '--file' flag in the preview example.

Document flag semantics: accepted values for '--engine', units/defaults for '--rtk-budget' and '--caveman-aggressiveness', and what '--pattern/--action/--replacement' accept in 'compression add'.

Add a short recommended workflow (configure, preview on a real prompt, verify with stats) and a caution/validation note before 'compression remove'.

DimensionReasoningScore

Conciseness

The body is a lean command catalog with no explanations of concepts Claude already knows — no padding, no library background. It misses a 5 because the duplicated 'compression list' section and placeholder flags (e.g. '--engine <e>') waste tokens without adding information.

4 / 5

Actionability

Real commands are present, but examples use literal placeholders ('omniroute compression set <name>', 'compression remove <id>') rather than executable values, flags have no semantics ('--engine <e>' never says what engines exist, '--rtk-budget <n>' has no units), and the 'compression preview' example omits its own '--file' flag. This is concrete but missing key details — anchor 3, not 4.

3 / 5

Workflow Clarity

The body is a flat subcommand catalog with no sequencing of a typical flow (configure, then preview with a real prompt, then verify via stats), and the destructive 'compression remove <id>' operation has no validation/confirmation guidance beyond a bare '--yes' flag, which caps workflow clarity at 3 per the rubric.

3 / 5

Progressive Disclosure

Content is well-organized with one section per subcommand, and with no bundle files present the inline compact reference is appropriate. It is not a 5 because the duplicate 'compression list' section is a clear organization defect and the auto-generated layout offers no navigation aids beyond the headers.

4 / 5

Total

14

/

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.

A specific, third-person description with good trigger vocabulary for its niche, undermined by the complete absence of a 'when to use this' clause. Adding explicit trigger guidance and a few more capability mentions would raise it substantially.

Suggestions

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

Mention remaining capabilities (viewing stats, adding/removing custom rules, language packs) so the 'what' coverage is comprehensive.

Add natural synonym phrasing such as 'compress prompts' or 'reduce prompt tokens' to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

The description lists several concrete actions ('Configure and test prompt compression from the CLI', 'Manage RTK filters, Caveman rules, stacked compression modes', 'preview compression output with real prompts') with named domain objects, and uses third-person voice. It falls short of a 5 because several capabilities shown in the body (stats, language-packs, add/remove rules) are unmentioned, but it goes well beyond the 1-2 actions of a 3.

4 / 5

Completeness

The 'what' is clear: configure and test prompt compression, manage filters, rules, and modes, and preview output. However, there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Natural trigger terms are present: 'prompt compression', 'compression', 'CLI', 'RTK filters', 'Caveman rules', 'preview' — phrases a user of this tool would actually say. Not a 5 because common variations like 'compress prompts', 'shorten prompts', or 'token budget/reduction' are missing; not a 3 because coverage is broad rather than just 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

The niche vocabulary (RTK filters, Caveman rules, stacked compression modes, prompt compression) makes it mostly distinct from other skills. It is not a 5 because the bare word 'compression' carries minor overlap risk with unrelated file/archive compression skills.

4 / 5

Total

15

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

diegosouzapw/OmniRoute

Path

skills/cli-compression/SKILL.md

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.