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.
86
81%
Does it follow best practices?
Impact
94%
1.02xAverage score across 3 eval scenarios
Passed
No known issues
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 solid skill description with excellent trigger terms and completeness. The 'Use when' clause with the distinctive 'promptify' keyword makes it easy to select correctly. The main weakness is that the 'what' portion could be more specific about the concrete actions involved in prompt transformation.
Suggestions
Expand the capability description with more specific actions, e.g., 'adds constraints, specifies output formats, clarifies ambiguities, and structures instructions' to better convey what the transformation entails.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (prompt engineering) and one action ('Transform user requests into detailed, precise prompts'), but doesn't list multiple specific concrete actions like 'add constraints, specify output format, clarify ambiguities, add examples'. | 2 / 3 |
Completeness | Clearly answers both 'what' (transform user requests into detailed, precise prompts for AI models) and 'when' (explicit 'Use when' clause with specific trigger phrases like 'promptify', 'prompt engineering', 'improvement of their request'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'promptify', 'promptify this', 'prompt engineering', 'improvement of their request', 'AI responses', 'AI models'. These cover the natural ways users would invoke this skill. | 3 / 3 |
Distinctiveness Conflict Risk | The unique trigger term 'promptify' and the specific niche of prompt engineering/improvement make this highly distinctive and unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%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, concise skill that clearly communicates formatting and language constraints for prompt engineering. Its main weakness is the lack of concrete input/output examples showing a transformation, which would significantly improve actionability. The workflow steps are also somewhat generic and could benefit from explicit quality criteria or a validation step.
Suggestions
Add 1-2 concrete before/after examples showing a user request transformed into a promptified output to demonstrate the expected transformation quality and style.
Add explicit quality criteria or a brief checklist for self-validation before outputting (e.g., 'Verify: no invented information, length within 0.75X-1.5X, all formatting rules followed').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. Every section serves a purpose, there's no explanation of what prompts are or how AI models work, and it respects Claude's intelligence throughout. | 3 / 3 |
Actionability | The guidelines are specific (formatting rules, length ratio, language style) but lack concrete examples of input/output transformations. A before/after example of a promptified request would make this fully actionable. | 2 / 3 |
Workflow Clarity | The 3-step process is listed but is fairly generic (read, plan, rewrite). There are no validation checkpoints or criteria for evaluating whether the rewritten prompt meets quality standards before outputting. | 2 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines, the content is well-organized with clear sections (Core Task, Process, Writing Guidelines with subsections, Output). No external references are needed and the structure is easy to navigate. | 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- intellectronica/agent-skills
- Commit
9b0e00a
- 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.