refine-prompt
refine-prompt is a Prompt design & optimisation skill for AI agents, published by penpot in the penpot repository on GitHub. Skillspace rates refine-prompt D (68/100) and it passed the safety scan; a judge model has also reviewed it.
Refine and improve a user-supplied prompt for maximum clarity and effectiveness using prompt-engineering best practices and Penpot project context. Outputs a rewritten prompt (and brief rationale); never executes the prompt.
- Grade
- D
- Quality
- 68 / 100
- Safety
- Passed
- GitHub stars
- 59,946
Placed #1 of 6 in the judged category final for Prompt design & optimisation.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 100 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
Judge review
Placed #1 of 6 in the judged category final for Prompt design & optimisation.
- Trigger
85 85 - Instructions
92 92 - Specificity
90 90 - Safety
88 88 - Disclosure
80 80 - Maintenance
68 68
A precise, well-bounded prompt-refinement skill with a genuine prompt-engineering-principles checklist and a strict never-execute-the-prompt boundary, the sharpest fit for this category's core task.
Not checked yet
- Category is a classifier prediction; no model has read this skill yet
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.