Back to Details

survey

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Survey

调研

Gather sources from the web, papers, social media, and industry on a specific topic, and produce an indexed Markdown report.
This skill follows the shared sourced-writing conventions defined in 
documenting-with-sources
. Read 
documenting-with-sources
before drafting.
从网页、论文、社交媒体和行业渠道收集特定主题的资料，并生成一份带索引的Markdown报告。
本技能遵循
documenting-with-sources
中定义的共享来源写作规范。撰写前请阅读
documenting-with-sources
。

Quality criteria

质量标准

Apply to every source.
  • Prefer trustworthy sources (peer-reviewed papers > official blogs > major industry media > personal blogs).
  • If the author is an individual, list their affiliation and role. If unknown, look it up.
  • For papers, in addition to bibliographic info (authors, affiliations, venue, year), include citation count.
  • Always attach a URL.
  • Always attach a date.
  • Treat official documentation and third-party articles as different reliability tiers. Do not mix them; the reader must be able to tell which is which.
适用于所有资料来源：
  • 优先选择可信来源（同行评审论文 > 官方博客 > 主流行业媒体 > 个人博客）。
  • 若作者为个人，需列出其所属机构和职位；若未知，则需查找确认。
  • 对于论文，除了文献信息（作者、所属机构、发表场所、年份）外，还需包含引用量。
  • 始终附上URL链接。
  • 始终附上日期。
  • 将官方文档与第三方文章视为不同可信度层级，不可混淆；读者必须能够区分两者。

Prose structure: Assertion-Evidence form

行文结构：主张-证据形式

Write the body in Assertion-Evidence form — claim first, then evidence.
  1. Prose: the writer states the claim or summary in their own words first.
  2. Immediately after, a code-block quotation from the source backs up the claim, formatted per 
    writing-quotation
    .
  3. On the line after the closing fence, place the source reference 
    [source-name (YYYY/MM)]
    .
The reader grasps "what is being said" first, then checks "what is the basis". The reverse order (quotation first, claim later) is forbidden — the reader cannot tell what the quotation is for until they have read past it.
Bad example (quotation first):
The standard recipe of pretraining on huge corpora and then running classical preference-label RLHF is now widely treated as obsolete.
[industry-tracker (2026/03)]
The mainstream has shifted to a modular post-training stack.
Good example (claim first):
The classical RLHF pipeline (human preference labels → reward model → PPO) is no longer used in leading models; it has been replaced by a modular stack that separates concerns.
The standard recipe of pretraining on huge corpora and then running classical preference-label RLHF is now widely treated as obsolete. Every leading model released in the past year uses a different post-training stack.
[industry-tracker (2026/03)]
正文采用主张-证据形式写作——先提出观点，再给出证据。
  1. 正文：作者先用自己的话陈述主张或总结。
  2. 紧随其后，用代码块引用来源内容来支持主张，格式遵循
    writing-quotation
    规范。
  3. 在代码块结束符的下一行，标注来源引用
    [source-name (YYYY/MM)]
    。
读者应先理解“内容是什么”，再查看“依据是什么”。禁止采用相反顺序（先引用后主张）——读者在读完引用内容前无法理解其用途。
反面示例（先引用）：
The standard recipe of pretraining on huge corpora and then running classical preference-label RLHF is now widely treated as obsolete.
[industry-tracker (2026/03)]
主流已转向模块化的后训练架构。
正面示例（先主张）：
经典RLHF流程（人类偏好标签→奖励模型→PPO）已不再用于领先模型；取而代之的是分离关注点的模块化架构。
The standard recipe of pretraining on huge corpora and then running classical preference-label RLHF is now widely treated as obsolete. Every leading model released in the past year uses a different post-training stack.
[industry-tracker (2026/03)]

Source-reference label

来源引用标签

Within the 
[label (YYYY/MM), location]
structure defined in 
documenting-with-sources
, the survey skill fills the label slot with the publication or source name (media name, site name, etc.). The location is omitted when it cannot be pinned down.
在
documenting-with-sources
定义的
[label (YYYY/MM), location]
结构中，调研技能将标签部分填写为出版物或来源名称（媒体名称、网站名称等）。若无法确定位置，则省略该部分。

Heading-content alignment

标题-内容匹配

Section headings and the items placed under them must match exactly.
  • If a heading is "human-side guardrails", only human conduct and discipline goes underneath. Tooling and CI/CD belong under a separate heading.
  • If a heading is "failure cases", do not mix in success stories or recommendations.
  • If a source spans multiple angles, either split it across the relevant sections, or place it under the most appropriate one and add an explicit note about the other angles.
  • Before finalising, walk every heading and check that everything underneath it actually belongs there.
章节标题与其下的内容必须完全匹配：
  • 若标题为“人工侧防护措施”，则仅放置人为行为和规范相关内容；工具和CI/CD内容应放在单独标题下。
  • 若标题为“失败案例”，则不可混入成功案例或建议内容。
  • 若某一来源涉及多个角度，可将其拆分到相关章节，或放置在最适合的章节下，并明确标注其他角度的内容。
  • 定稿前，逐一检查每个标题，确保其下所有内容确实属于该标题范畴。

Output destination

输出目标

Write the deliverable to 
{CWD}/reports/
as a 
.md
file. Create the directory if it does not exist. Sub-agents that emit intermediate artefacts use the same directory.
将交付成果写入
{CWD}/reports/
目录下的
.md
文件。若目录不存在则创建。生成中间产物的子Agent使用同一目录。

Workflow

工作流程

  1. From the user's request, identify the claim or hypothesis and the collection scope.
  2. Design search queries for the scope (in multiple languages where appropriate).
  3. Dispatch sub-agents to investigate (one per angle, in parallel).
  4. Consolidate the sub-agent outputs; the main agent assembles the final version.
  5. Write out the deliverable to 
    {CWD}/reports/
    as a 
    .md
    file.
  1. 从用户请求中识别主张或假设，以及收集范围。
  2. 针对该范围设计搜索查询（适当时使用多种语言）。
  3. 分派子Agent进行调查（每个角度一个Agent，并行处理）。
  4. 整合子Agent的输出；主Agent组装最终版本。
  5. 将交付成果写入
    {CWD}/reports/
    目录下的
    .md
    文件。

Sub-agent delegation rules

子Agent委派规则

When delegating to sub-agents, follow these.
  • Split by angle and dispatch in parallel (e.g. "papers & academia", "media & blogs", "social media", "industry signals").
  • Give each sub-agent the quality criteria and the conventions from 
    documenting-with-sources
    . Re-emphasise "no fabricated associations or interpretations" specifically — sub-agents are particularly prone to drifting toward the calling-conversation context and inventing connections.
  • Sub-agent output is not the final deliverable. The main agent performs:
    • Deduplication.
    • Information completion (filling in missing affiliations, citation counts, etc. via additional lookups).
    • Structural unification (tables, consistent section structure).
    • Separation of criticism from supporting evidence.
    • Explicit listing of investigation limits (information that could not be retrieved, unverified URLs, etc.).
    • Removal of fabricated associations (see the corresponding section in 
      documenting-with-sources
      ).
    • Heading-content alignment check (see above).
委派子Agent时需遵循以下规则：
  • 按角度拆分并并行分派（例如“论文与学术”、“媒体与博客”、“社交媒体”、“行业动态”）。
  • 向每个子Agent传达质量标准和
    documenting-with-sources
    中的规范。特别强调“不得编造关联或解读”——子Agent尤其容易偏离对话上下文并编造关联。
  • 子Agent的输出并非最终交付成果。主Agent需执行以下操作：
    • 去重。
    • 信息补全（通过额外查找补充缺失的所属机构、引用量等信息）。
    • 结构统一（表格、一致的章节结构）。
    • 将批评内容与支持证据分离。
    • 明确列出调查限制（无法获取的信息、未验证的URL等）。
    • 删除编造的关联（参见
      documenting-with-sources
      中的对应章节）。
    • 标题-内容匹配检查（见上文）。

Deliverable structure

交付成果结构

undefined
undefined

Survey of {topic}

Survey of {topic}

Date: YYYY-MM-DD Scope: {scope description}
Date: YYYY-MM-DD Scope: {scope description}

Table of Contents

Table of Contents

  1. {angle 1}
  2. {angle 2} ... N. Criticism & concerns N+1. Overall assessment N+2. Investigation limits
  1. {angle 1}
  2. {angle 2} ... N. Criticism & concerns N+1. Overall assessment N+2. Investigation limits

1. {angle 1} (e.g. academic papers)

1. {angle 1} (e.g. academic papers)

2. {angle 2} (e.g. media coverage)

2. {angle 2} (e.g. media coverage)

3. {angle 3} (e.g. social-media reactions)

3. {angle 3} (e.g. social-media reactions)

4. {angle 4} (e.g. industry signals)

4. {angle 4} (e.g. industry signals)

N. Criticism & concerns

N. Criticism & concerns

N+1. Overall assessment

N+1. Overall assessment

N+2. Investigation limits

N+2. Investigation limits


Adjust the section layout for the topic.

可根据主题调整章节布局。

Table-of-contents requirements

目录要求

Always place a table of contents at the top of the report, directly after the metadata block and before the body. Writing the report without a ToC is forbidden.
  • If there are ten or more sections, or fifteen or more individual items (papers, articles, etc.), use a two-level ToC. Level 1 is the section name; level 2 is the section's main items (paper titles, article headlines, ...).
  • For short reports (five or fewer sections, few items per section) a single-level ToC is fine.
  • Provide anchor links. Use the renderer's slug rules (lowercased, spaces → hyphens, special characters dropped) for the link targets.
  • Even when the slug rule is uncertain, write the link rather than dropping it; let the renderer slugify.
  • ToC entries and section headings must match word for word. No abbreviation or paraphrase.
报告顶部必须放置目录，紧跟元数据块之后、正文之前。禁止撰写无目录的报告：
  • 若章节数量达到10个及以上，或单个条目（论文、文章等）达到15个及以上，使用二级目录。一级为章节名称；二级为章节的主要条目（论文标题、文章标题等）。
  • 对于简短报告（5个及以下章节，每个章节条目较少），使用一级目录即可。
  • 提供锚点链接。链接目标遵循渲染器的slug规则（小写，空格替换为连字符，移除特殊字符）。
  • 即使不确定slug规则，也要写入链接而非省略；由渲染器处理slug转换。
  • 目录条目与章节标题必须完全一致，不得缩写或改写。