refine-prompt

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Chinese

Element	Check
Task	Is the core action explicit and unambiguous?
Constraints	Are length, format, tone, and scope defined?
Output format	Does it specify the expected structure?
Context	Does the model have enough background to act?
Examples	Would a demonstration clarify the expected output?
Edge cases	Are failure modes and boundary conditions addressed?

Rewrite — Transform into specification language: precise, imperative, no filler. Treat the prompt as a spec, not conversation.
Validate — Check the rewrite against the assessment table. Every gap identified in step 1 must be addressed.

Length: 0.75x–1.5x the original. Conciseness is a feature — add only what's missing, cut what's vague.
Never invent — only use information present in the original prompt or conversation context. If critical info is missing, ask instead of assuming.
Instruction hierarchy — order sections by priority: task → constraints → examples → input data → output format. Place the most important instruction first.
Progressive complexity — start with the simplest prompt that could work. Add few-shot examples, chain-of-thought, or role framing only when the task demands it, not by default.
Specific verbs — replace vague actions ("analyze", "process", "handle") with measurable ones ("list the top 3", "classify as A/B/C", "return JSON with keys X, Y").
One output format — specify exactly one format (JSON schema, markdown template, numbered list). Ambiguous format expectations cause inconsistent results.
No meta-commentary — output only the refined prompt as markdown. No preamble ("Here's an improved version..."), no explanation of changes unless explicitly requested.

长度：为原Prompt的0.75-1.5倍。简洁是核心优势——仅补充缺失的内容，删除模糊表述。
禁止编造——仅使用原Prompt或对话语境中存在的信息。若关键信息缺失，应询问而非自行假设。
指令优先级——按重要性排序内容：任务→约束条件→示例→输入数据→输出格式。将最重要的指令放在最前面。
渐进式复杂度——从最简单的可用Prompt开始。仅当任务需要时才添加few-shot examples、chain-of-thought或角色设定，而非默认添加。
具体动词——将模糊动作（如「analyze」「process」「handle」）替换为可衡量的动作（如「列出前3项」「分类为A/B/C」「返回包含X、Y键的JSON」）。
单一输出格式——明确指定一种格式（JSON schema、markdown模板、编号列表）。模糊的格式要求会导致结果不一致。
无元注释——仅输出markdown格式的优化后Prompt。除非明确要求，否则不要添加开场白（如「这是优化后的版本...」）或更改说明。

Problem	Fix
Vague verbs ("look into", "deal with")	Replace with concrete actions ("list", "compare", "extract")
Missing output spec	Add explicit format section with example structure
Examples contradict instructions	Align examples to match every stated rule
Over-engineered from the start	Strip to simplest working version, then add complexity only where output quality requires it
Prompt exceeds context with examples	Limit to 2–3 diverse examples; use one simple, one edge case

问题	修复方案
模糊动词（如「look into」「deal with」）	替换为具体动作（如「列出」「对比」「提取」）
缺失输出规范	添加带有示例结构的明确格式说明
示例与指令矛盾	调整示例以符合所有已说明的规则
初始过度设计	简化为最简单的可用版本，仅当输出质量需要时再增加复杂度
示例导致Prompt超出上下文限制	限制为2-3个多样化示例；包含一个简单示例和一个边缘案例