promptify
Transform user requests into detailed, precise prompts for AI models. Use when users say 'promptify', 'promptify this', or explicitly request prompt engineering or improvement of their request for better AI responses.
89
Quality
87%
Does it follow best practices?
Impact
89%
1.58xAverage score across 3 eval scenarios
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-structured description with explicit 'Use when' guidance and distinctive trigger terms. The main weakness is the lack of specific concrete actions beyond the general 'transform into detailed, precise prompts' - it could benefit from listing specific prompt engineering techniques or outputs.
Suggestions
Add 2-3 specific concrete actions to improve specificity, such as 'adds context and constraints', 'structures with examples', or 'optimizes for clarity and completeness'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (prompt engineering) and a general action ('Transform user requests into detailed, precise prompts'), but lacks specific concrete actions like 'add context', 'structure with examples', 'clarify ambiguities', or 'optimize for specific models'. | 2 / 3 |
Completeness | Clearly answers both what ('Transform user requests into detailed, precise prompts for AI models') and when ('Use when users say promptify, promptify this, or explicitly request prompt engineering or improvement'). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'promptify', 'promptify this', 'prompt engineering', 'improvement of their request', and 'better AI responses'. These cover both the custom command and natural language variations. | 3 / 3 |
Distinctiveness Conflict Risk | The unique trigger term 'promptify' and the specific focus on prompt engineering for AI models creates a clear niche that is unlikely to conflict with other skills like general writing or editing skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with clear workflow steps and actionable guidance. The four-block pattern reference and concrete examples strengthen usability. Minor verbosity in troubleshooting and writing guidelines sections could be trimmed, but overall the skill effectively teaches prompt transformation without over-explaining concepts Claude already knows.
Suggestions
Remove or significantly condense the Troubleshooting section - these are generic debugging patterns Claude already understands
Consolidate Writing Guidelines into a more compact checklist format to reduce token usage
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary sections like the troubleshooting block which explains generic debugging concepts Claude already understands. The writing guidelines section could be more condensed. | 2 / 3 |
Actionability | Provides concrete, executable guidance with a clear 5-step workflow, specific structural patterns (four-block pattern), explicit formatting rules, and concrete examples of trigger vs non-trigger scenarios. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (Analyze → Structure → Refine → Output → Deliver) with explicit steps and decision points. The Deliver step offers clear branching options with specific actions for each path. | 3 / 3 |
Progressive Disclosure | Appropriately references external file `rules/structure-four-block-pattern.md` for detailed pattern guidance while keeping the main skill focused. Content is well-organized with clear section headers and logical grouping. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 10 / 11 Passed | |
- 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.