ecosystem-research

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Ecosystem Research

生态研究

Quick Start

快速开始

Use this when a design or grilling decision depends on evidence that should be gathered and synthesized before acting.

当设计或 grilling 决策依赖于行动前应收集并综合的证据时，使用此 skill。

Source Modes

来源模式

```
ecosystem
```
: external systems, libraries, products, docs, public precedent, and technical writing.
```
internal
```
: repository history, Codex sessions, PRs, issues, ADRs, local docs, and project-specific evidence.
```
mixed
```
: internal evidence plus external precedent.

Default to

ecosystem

when the user asks how others solve a problem, compares products/libraries, or mentions ecosystem precedent. Default to

internal

for retrospectives, session analysis, project history, or repo-local pattern analysis. Use

mixed

when both would change the decision.

```
ecosystem
```
：外部系统、库、产品、文档、公开先例和技术写作。
```
internal
```
：仓库历史、Codex 会话、PR、issue、ADR、本地文档和项目特定证据。
```
mixed
```
：内部证据加外部先例。

当用户询问其他人如何解决某个问题、比较产品或库，或提到生态先例时，默认使用

ecosystem

。对于复盘、会话分析、项目历史或仓库内模式分析，默认使用

internal

。当内部和外部证据都会影响决策时，使用

mixed

。

Workflow

工作流

Form a concrete research question from the active design branch.
Choose a source mode:
```
ecosystem
```
,
```
internal
```
, or
```
mixed
```
.
Choose a research depth:
```
targeted
```
,
```
standard
```
, or
```
ambitious
```
.
Identify the absolute project root and create a persisted research brief.
Spawn subagents according to the depth and source-area split.
Have subagents write reports under the research folder.
Verify every expected report exists and meets the evidence bar before synthesis.
Synthesize the reports into a concise
```
synthesis.md
```
when findings are substantive.
Return decision-oriented findings to the active session and continue with one question.

Do not mutate the project repo. Research artifacts belong under the temporary directory of the user's OS, not the current workspace. Resolve it with the platform temp-dir API or environment, such as

$TMPDIR

on macOS/Linux or

%TEMP%

on Windows. If subagents are unavailable, state that and do a compact local fallback.

根据当前设计分支，形成一个具体的研究问题。
选择来源模式：
```
ecosystem
```
、
```
internal
```
或
```
mixed
```
。
选择研究深度：
```
targeted
```
、
```
standard
```
或
```
ambitious
```
。
确定项目的绝对根路径，并创建持久化的研究简报。
根据研究深度和来源领域拆分方式启动 subagents。
让 subagents 在研究文件夹下撰写报告。
在综合之前，验证每份预期报告都存在并达到证据标准。
当发现具有实质内容时，将报告综合为简明的
```
synthesis.md
```
。
将面向决策的发现返回当前活跃会话，并继续提出一个问题。

不得修改项目仓库。研究产物应位于用户操作系统（OS）的临时目录下，而不是当前工作区。通过平台临时目录 API 或环境变量确定该目录，例如 macOS/Linux 上的

$TMPDIR

或 Windows 上的

%TEMP%

。如果 subagents 不可用，应说明这一点，并采用精简的本地回退方案。

Research Depth

研究深度

Default to

standard

unless the user asks for "quick", "ambitious", "proper research", "deep research", or the decision is public API, security, data model, migration, pricing, irreversible architecture, or high-conflict.

```
targeted
```
: one narrow source area, at least one subagent, at least 5 authoritative sources, one report, synthesis optional.
```
standard
```
: 2-4 distinct source areas, 2-4 subagents when available, at least 12 authoritative sources total, synthesis required.
```
ambitious
```
: broad or high-stakes work, 4+ source areas, 4+ subagents when available or staged local passes, at least 20 authoritative sources total, synthesis required, explicit evidence-versus-inference table required.

If the user says the first pass was too shallow, immediately upgrade to

ambitious

. Do not repeat the same source area with a slightly longer prompt; add missing source areas and stronger completion checks.

除非用户要求“quick”、“ambitious”、“proper research”、“deep research”，或者该决策涉及 public API、安全、数据模型、迁移、定价、不可逆架构或高冲突情形，否则默认使用

standard

。

```
targeted
```
：一个狭窄的来源领域，至少一个 subagent，至少 5 个权威来源，一份报告，可选择是否进行综合。
```
standard
```
：2 至 4 个不同的来源领域，在可用时使用 2 至 4 个 subagents，总计至少 12 个权威来源，必须进行综合。
```
ambitious
```
：适用于广泛或高风险的工作，4 个以上来源领域，在可用时使用 4 个以上 subagents，或采用分阶段的本地执行轮次，总计至少 20 个权威来源，必须进行综合，并明确提供证据与推断对照表。

如果用户表示第一轮研究过于浅显，应立即升级到

ambitious

。不要使用略微扩展的提示词重复研究同一个来源领域；应补充缺失的来源领域，并采用更严格的完成度检查。

Artifact Layout

产物布局

Use this layout:

text

<os-temp-dir>/ecosystem-research/<project>/<topic>/
+-- brief.md
+-- sources/
+-- reports/
+-- synthesis.md

brief.md

should include the project/context name, absolute

project_root

, active design question, relevant conversation history, user concerns, resolved decisions, unresolved branches, research questions, source mode, chosen depth, source-area matrix, minimum source bar, report paths, and source priorities.

Because research artifacts live outside the project workspace, any project file reference in the brief, reports, synthesis, or subagent prompt must be absolute, such as

<absolute-project-root>/.agents/contexts/devtools/CONTEXT.md

. Never use repo-relative paths like

.agents/...

inside temporary artifacts unless they are paired with the absolute

project_root

Subagents should read

brief.md

For source-area matrices, report requirements, source-quality rules, and completion checks, use RESEARCH-RIGOR.md.

使用以下布局：

text

<os-temp-dir>/ecosystem-research/<project>/<topic>/
+-- brief.md
+-- sources/
+-- reports/
+-- synthesis.md

brief.md

应包括项目/上下文名称、绝对路径

project_root

、当前设计问题、相关对话历史、用户关注点、已确定的决策、未解决的分支、研究问题、来源模式、所选深度、来源领域矩阵、最低来源标准、报告路径和来源优先级。

由于研究产物位于项目工作区之外，因此 brief、报告、综合文档或 subagent 提示词中对项目文件的引用必须是绝对路径，例如

<absolute-project-root>/.agents/contexts/devtools/CONTEXT.md

。除非与绝对路径

project_root

配对使用，否则不得在临时产物中使用

.agents/...

等仓库相对路径。

Subagents 应读取

brief.md

。

有关来源领域矩阵、报告要求、来源质量规则和完成度检查，请参阅 RESEARCH-RIGOR.md。

Subagent Brief

Subagent 简报

Each subagent prompt should include the

brief.md

path, assigned source area, report path, chosen depth, source minimum for that area, whether source cloning into

sources/

is useful, a no-repo-mutation requirement, and a request for source links, trade-offs, patterns, disagreements, recommendations, and evidence-versus-inference separation.

Use at least one subagent. Use multiple subagents when source areas are meaningfully independent, such as framework ecosystems, product ecosystems, company technical writing, benchmarks, security literature, Codex session clusters, PR stacks, or repository history.

Subagents must write the requested report file. A progress message without a report is incomplete.

每个 subagent 提示词都应包括：

brief.md

路径、分配的来源领域、报告路径、所选深度、该领域的最低来源数量、是否适合将来源克隆到

sources/

中、禁止修改仓库的要求，以及对来源链接、权衡、模式、分歧、建议和区分证据与推断的要求。

至少使用一个 subagent。当来源领域之间存在实质性独立性时，应使用多个 subagents，例如框架生态、产品生态、公司技术写作、基准测试、安全文献、Codex 会话集群、PR 栈或仓库历史。

Subagents 必须写入所要求的报告文件。仅发送进度消息而没有报告，视为任务未完成。

Synthesis

综合

Write

synthesis.md

when reports contain substantive evidence. Keep it concise and decision-oriented:

consensus patterns
meaningful disagreements
applicability to this project
risks and trade-offs
evidence versus inference
finding verdicts:
```
SUPPORTED
```
,
```
CONTESTED
```
,
```
WEAK
```
, or
```
INCONCLUSIVE
```
source-area coverage and gaps
decision-changing evidence separated from background context
recommended decision wording
source links

If an ADR follows, tell the active grilling skill which learnings are worth carrying into the ADR. Do not write project ADRs directly from this skill.

当报告包含实质性证据时，编写

synthesis.md

。内容应简明且面向决策：

共识模式
重要分歧
对本项目的适用性
风险与权衡
证据与推断
发现结论：
```
SUPPORTED
```
、
```
CONTESTED
```
、
```
WEAK
```
或
```
INCONCLUSIVE
```
来源领域覆盖范围与缺口
将可能改变决策的证据与背景信息分开
建议的决策表述
来源链接

如果后续要编写 ADR，应告知当前 grilling skill 哪些经验值得纳入 ADR。不要直接通过此 skill 编写项目 ADR。

Output Shape

输出结构

Return a compact answer:

Research artifacts:
- Brief: <os-temp-dir>/ecosystem-research/<project>/<topic>/brief.md
- Synthesis: <os-temp-dir>/ecosystem-research/<project>/<topic>/synthesis.md

Findings:
- ...

Decision pressure:
- ...

Next grilling question:
...

返回一份简洁的答案：

Research artifacts:
- Brief: <os-temp-dir>/ecosystem-research/<project>/<topic>/brief.md
- Synthesis: <os-temp-dir>/ecosystem-research/<project>/<topic>/synthesis.md

Findings:
- ...

Decision pressure:
- ...

Next grilling question:
...