CtrlK
BlogDocsLog inGet started
Tessl Logo

prompt-optimizer

Transform vague prompts into precise, well-structured specifications using EARS (Easy Approach to Requirements Syntax) methodology. This skill should be used when users provide loose requirements, ambiguous feature descriptions, or need to enhance prompts for AI-generated code, products, or documents. Triggers include requests to "optimize my prompt", "improve this requirement", "make this more specific", or when raw requirements lack detail and structure.

87

1.62x
Quality

81%

Does it follow best practices?

Impact

96%

1.62x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 well-structured methodology skill with a clear six-step workflow, concrete EARS patterns, and excellent progressive disclosure through four real reference files. Main weakness is conciseness — the transformation checklist and Do's/Don'ts section overlap, and a few sections restate earlier content.

Suggestions

Consolidate the Step 2 transformation checklist with the Quick Reference Do's/Don'ts to remove overlapping guidance on measurable criteria and avoiding vague language.

Drop or shorten the 'Four-layer enhancement process' overview since it restates the Six-Step Optimization Workflow that immediately follows.

Trim the methodology-attribution aside ('Methodology inspired by...') or move it to a reference file, as it does not aid execution.

DimensionReasoningScore

Conciseness

Largely efficient and well-organized, but includes redundancy — the Step 2 transformation checklist and the Quick Reference Do's/Don'ts overlap, and the four-layer enhancement process restates the six-step workflow — plus the methodology-attribution aside adds padding; not 4 due to this redundancy, not 2 because most content earns its place.

3 / 5

Actionability

Provides concrete EARS patterns with syntax, a before/after example, domain mappings, and a reusable Role/Skills/Workflows/Examples/Formats output template; not 5 because the templates rely on placeholders rather than fully concrete end-to-end examples, and not 3 because the guidance is executable rather than pseudocode.

4 / 5

Workflow Clarity

The six-step workflow (Analyze → EARS Transform → Domain Theories → Examples → Generate → Present) is clearly sequenced with a Step 2 transformation checklist as a checkpoint; not 5 because there is no explicit validation/feedback loop (acceptable for a non-destructive generation skill), and not 3 because the sequence and checkpoints are well-defined.

4 / 5

Progressive Disclosure

SKILL.md is a concise overview pointing to four real one-level-deep reference files (ears_syntax.md, domain_theories.md, examples.md, advanced_techniques.md), with an explicit 'When to load references' section signaling when each file should be consulted; matches the score-5 anchor.

5 / 5

Total

16

/

20

Passed

Description

91%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 the skill's purpose and provides concrete, naturally phrased trigger terms. It explicitly covers both what the skill does and when to use it, with only minor overlap risk against generic prompt-improvement skills.

DimensionReasoningScore

Specificity

Names the EARS methodology and concrete actions ('Transform vague prompts into precise, well-structured specifications', 'enhance prompts for AI-generated code, products, or documents') with minor coverage gaps; not a score of 5 because it does not enumerate multiple discrete granular actions, and not 3 because more than 1-2 actions are named alongside the methodology.

4 / 5

Completeness

Explicitly answers both 'what' (transform vague prompts into precise EARS specifications) and 'when' with concrete trigger phrases ('This skill should be used when...', 'Triggers include...'), matching the score-5 anchor.

5 / 5

Trigger Term Quality

Quoted natural trigger phrases ('optimize my prompt', 'improve this requirement', 'make this more specific') plus synonyms ('loose requirements', 'ambiguous feature descriptions', 'enhance prompts') give comprehensive coverage of terms a user would actually say.

5 / 5

Distinctiveness Conflict Risk

The EARS-based requirement-transformation niche with distinct triggers is mostly distinguishable from generic writing skills, though minor overlap risk remains with general prompt-improvement or requirement-engineering skills.

4 / 5

Total

18

/

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
daymade/claude-code-skills
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.