CtrlK
BlogDocsLog inGet started
Tessl Logo

compress-prompt

Compress a Rosetta KB prompt artifact (skill · workflow · phase · rule · agent · template · generic) by stripping structural tautology and ineffective scaffolding while preserving every importance-bearing token. Use when the user asks to compress, shorten, tighten, densify, or reduce a prompt / skill / workflow / phase / rule file.

68

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 lean, well-structured methodology skill that practices its own compression discipline, with an explicitly ordered transform loop and a subagent-verified HITL workflow including validation before destructive writes. Minor redundancy in the CUT section and the absence of executable code keep conciseness and actionability just below the top anchors.

DimensionReasoningScore

Conciseness

The body is aggressively terse with dense bullets, CAPS importance markers, and unicode connectives (→ · ⇒ ≠), assuming Claude's competence; a few CUT-section lines ('Cut the fluff', 'Restated the same thing in different ways', 'Everything obvious or already known') are mildly redundant and could merge, keeping it just below the every-token-earns-its-place anchor 5.

4 / 5

Actionability

As an instruction-only methodology skill it provides concrete, specific guidance — ordered passes, a hard cap (<10 words), and a worked transformation example ('ONE PHASE AT A TIME: read file, execute, update state, advance' → 'ONE PHASE AT A TIME. READ JIT.') — but has no executable code/commands, fitting 'mostly executable guidance; minor gaps' rather than the copy-paste-ready anchor 5.

4 / 5

Workflow Clarity

The TRANSFORM section gives an explicit ordered pass sequence (CUT → GROUP+REPHRASE → COMPRESS → HARD CAP → ↺ loop to fixpoint) and the HITL process has explicit validation (subagent verify OLD vs NEW) with a feedback loop (verify → critically evaluate → adjust) and approval gates before the destructive write, matching anchor 5's explicit-validation-with-feedback-loops.

5 / 5

Progressive Disclosure

The skill is a single well-sectioned file (Mental model, KEEP verbatim, CUT, COMPRESS, NEVER, TRANSFORM, Process, Lessons learned) with its only external references (KB schemas) clearly listed; with no bundle files to split and good internal organization it sits at 'good structure; minor organization gaps' rather than the multi-reference anchor 5.

4 / 5

Total

17

/

20

Passed

Description

83%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 strong description that clearly states a distinctive niche and concrete trigger verbs with an explicit 'Use when' clause. Minor gaps in action breadth and a slight generic-verb overlap risk keep specificity and distinctiveness just below the top anchors.

DimensionReasoningScore

Specificity

Names the domain (Rosetta KB prompt artifacts, 7 enumerated types) and two concrete actions — 'stripping structural tautology and ineffective scaffolding' and 'preserving every importance-bearing token' — but the actions are somewhat abstract rather than a long list of distinct operations, fitting 'several specific actions; minor gaps' rather than the comprehensive 5.

4 / 5

Completeness

Explicitly answers both 'what' (compress a KB prompt artifact by stripping tautology/scaffolding while preserving importance-bearing tokens) and 'when' (Use when the user asks to compress/shorten/tighten/densify/reduce a prompt/skill/workflow/phase/rule file) with concrete trigger phrases, matching anchor 5.

5 / 5

Trigger Term Quality

Provides strong natural-verb coverage ('compress, shorten, tighten, densify, or reduce') plus artifact-type keywords, but lacks file extensions and a few common variations, landing just below the comprehensive synonym+extension coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The 'Rosetta KB prompt artifact' framing carves a clear niche and the triggers are scoped to prompt/skill/workflow/phase/rule files, but the verbs (compress/shorten/tighten/reduce) are somewhat generic and could overlap with general condense/summarize skills, so it sits below the minimal-conflict anchor 5.

4 / 5

Total

17

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
griddynamics/rosetta
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.