Content
68%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is a compact, well-structured prompt template with a concrete output schema, but it omits explicit validation steps and a worked example. Adding a validation checkpoint and a sample filled output would raise workflow clarity and actionability.
Suggestions
Add an explicit validation checkpoint after generation, e.g. "Verify the output is valid JSON and that every step is traceable to a claim in {context}; if not, revise before returning."
Include one fully worked example (a completed JSON object) so the expected output shape is unambiguous.
Remove the redundant 注意事项 bullets that restate Strict Grounding and "Avoid generic advice" to tighten token efficiency.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The prompt template is mostly lean with a concrete schema and concrete protocol examples; the only redundancy is that 注意事项 restates constraints already given under Strict Grounding and Philosophy, which is a minor trim opportunity. | 4 / 5 |
Actionability | A copy-paste JSON output schema plus explicit constraints ("Do X for Y mins", grounded-only, valid JSON) give mostly executable guidance; the main gap is the absence of a worked, filled-in example output. | 4 / 5 |
Workflow Clarity | The single-purpose generation flow is clear from the prompt structure, but there are no explicit validation checkpoints for JSON validity or for verifying that every step traces to the provided context, leaving validation implicit. | 3 / 5 |
Progressive Disclosure | Content is well organized into clearly headed sections with no external references needed and protocol lists appropriately inline; at ~62 lines it sits just outside the simple-skill exception and has minor redundancy, so a 4 fits. | 4 / 5 |
Total | 15 / 20 Passed |