agently-prompt-management

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Chinese

Use this skill when the core problem is how prompt state should be structured before one request or request family runs.

当核心问题是在单个请求或一类请求执行前如何构建提示词状态时，使用此技能。

prefer
```
input(...)
```
,
```
instruct(...)
```
,
```
info(...)
```
, and
```
output(...)
```
over concatenated prompt strings
move reusable prompt structure into prompt config or YAML instead of ad hoc literals
keep runtime variables as
```
${...}
```
placeholders in prompt files and inject them through mappings at load time
keep task-specific request contracts in prompt config, and keep only widely reused persona setup in small code-side factories
keep prompt composition separate from transport and orchestration
use config files as an editable bridge when UI or product teams need to adjust prompt-driven behavior without rewriting workflow code

do not flatten business context into one opaque string unless the task is trivial
do not rebuild prompt templates through ad hoc
```
.format(...)
```
or string concatenation when prompt mappings already fit
do not use prompt config files as a substitute for workflow state