clig-eval-prompt
Generate a concise Chinese evaluation prompt for DevOps CLI projects based on clig.onev.dev guidelines, with weights, thresholds, and hard gates. Use when a user asks to create or store a reusable CLI review prompt, a scoring rubric, or an evaluation checklist derived from CLI design guidelines.
When & Why to Use This Skill
This Claude skill streamlines the quality assessment of DevOps CLI projects by generating standardized evaluation prompts based on the clig.onev.dev guidelines. It provides a structured framework including weights, thresholds, and hard gates to ensure command-line tools adhere to professional design standards and usability best practices.
Use Cases
- Standardizing Internal Reviews: DevOps teams can generate consistent scoring rubrics to evaluate internal CLI tools, ensuring a uniform user experience across the organization.
- Automated Quality Assurance: Developers can use the generated prompts to create automated checklists for CI/CD pipelines to flag CLI tools that fail to meet essential design 'hard gates'.
- Open Source Benchmarking: Maintainers can produce clear, concise evaluation criteria to provide structured feedback for community contributions to CLI-based projects.
- Prompt Engineering for Tool Assessment: Users can quickly customize and store reusable evaluation templates for different CLI design dimensions like error handling, discoverability, and output formatting.
| name | clig-eval-prompt |
|---|---|
| description | Generate a concise Chinese evaluation prompt for DevOps CLI projects based on clig.onev.dev guidelines, with weights, thresholds, and hard gates. Use when a user asks to create or store a reusable CLI review prompt, a scoring rubric, or an evaluation checklist derived from CLI design guidelines. |
Clig Eval Prompt
Overview
Use this skill to produce the standardized evaluation prompt for reviewing DevOps CLI tools against clig.onev.dev. Keep output short, Chinese, and ready to copy-paste.
Workflow
- Load the canonical prompt from references/prompt.md.
- Output it verbatim unless the user requests modifications.
- If user requests changes (weights/thresholds/language/format), update only those parts and keep the rest intact.
- If the user asks for a shorter version, compress wording but preserve all hard gates, thresholds, and dimensions.
Output Rules
- Prefer the exact prompt text from references/prompt.md.
- Keep it in a single fenced code block.
- Do not add extra commentary unless asked.
- If user needs customization, ask one clarification question at a time.
Resources
- references/prompt.md: Canonical DevOps CLI evaluation prompt (Chinese, concise).