Back to Details

workbench-research

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Workbench Research

Workbench Research

Use this skill for research, architecture discovery, vendor docs, benchmark reading, and unknown-system analysis.

使用此skill进行研究、架构探索、厂商文档查阅、基准测试解读以及未知系统分析。

Research Standard

研究标准

Read the real system first when local state exists.
Prefer primary sources, live commands, local files, and official docs.
Separate confirmed facts, source claims, and inference.
Treat current software behavior, API shape, prices, versions, and docs as drift-prone.
Cite file paths, command names, issue/comment IDs, or source URLs when they support a claim.
Use targeted reads first: indexes,
```
rg
```
,
```
jq
```
, table summaries, and exact IDs before full documents or full histories.
Summarize large sources before handing them to another agent.

当存在本地状态时，优先读取实际系统。
优先选择一手资料、实时命令、本地文件和官方文档。
区分已确认的事实、来源声明和推论。
将当前软件行为、API形态、价格、版本和文档视为易发生变化的内容。
当文件路径、命令名称、问题/评论ID或来源URL支持某一结论时，需加以引用。
优先进行针对性读取：在读取完整文档或完整历史记录之前，先查看索引、
```
rg
```
、
```
jq
```
、表格摘要和精确ID。
在将大型资料交付给其他Agent之前，先进行总结。

Research Output

研究输出

Return:

```
QUESTION
```
: what was investigated.
```
CONFIRMED
```
: facts with evidence.
```
UNCERTAIN
```
: assumptions or unresolved gaps.
```
OPTIONS
```
: viable paths with tradeoffs.
```
RECOMMENDATION
```
: the smallest next action.
```
SOURCES
```
: local paths, commands, issue IDs, or URLs used.

返回：

```
QUESTION
```
: 研究的问题是什么。
```
CONFIRMED
```
: 带有证据的事实。
```
UNCERTAIN
```
: 假设或未解决的空白。
```
OPTIONS
```
: 带有权衡的可行方案。
```
RECOMMENDATION
```
: 最小化的下一步行动。
```
SOURCES
```
: 使用的本地路径、命令、问题ID或URL。

Research Boundaries

研究边界

Do not present speculation as fact.
Do not copy secrets or private tokens into reports.
Do not rewrite working architecture while researching it.
If source material conflicts, explain the conflict and prefer live runtime evidence.
Stop if the next read would be broad and low-yield; report the smaller evidence query needed instead.

不得将推测当作事实呈现。
不得将机密信息或私有令牌复制到报告中。
在研究过程中不得重写正在运行的架构。
如果资料存在冲突，需解释冲突情况并优先选择实时运行时证据。
如果下一步读取范围过广且收益低下，请停止操作；转而报告所需的更精准的证据查询需求。