perplexity-research

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

perplexity-research — Brain-Augmented Web Research

perplexity-research — 大脑增强型网页研究

Convention: see conventions/quality.md for citation rules; every claim from web research lands with a verifiable citation, not a paraphrase.

Convention: see conventions/brain-first.md for the lookup chain. This skill ENFORCES brain-first by sending brain context as part of the Perplexity prompt — the web search focuses on the delta between brain knowledge and current web state.

约定： 引用规则请参阅conventions/quality.md；网页研究得出的每一项结论都需附带可验证的引用，而非转述。

约定： 查找链规则请参阅conventions/brain-first.md。本技能通过将大脑上下文作为Perplexity提示词的一部分，强制遵循“大脑优先”原则——网页搜索将聚焦于大脑知识库与当前网页状态之间的差异。

What this does

功能说明

Combines existing brain knowledge with Perplexity's web search. The agent sends brain context about a topic into a Perplexity query; Perplexity searches + reads + synthesizes multiple pages with citations, focused on what's NEW relative to the supplied context.

The key insight: Perplexity doesn't just search — it reads and synthesizes with citations. By sending brain context in the instructions, it knows what you already know, so it surfaces the delta instead of repeating settled fact.

将现有大脑知识库与Perplexity的网页搜索功能相结合。Agent会将某一主题的大脑上下文发送至Perplexity查询；Perplexity会进行搜索、读取并综合多个网页内容，同时附上引用，重点呈现相对于提供的上下文的新增内容。

核心亮点： Perplexity不仅能搜索——它还能读取内容并结合引用进行综合分析。通过在指令中发送大脑上下文，它能了解你已掌握的信息，从而呈现差异内容，而非重复已确定的事实。

When to use this vs other tools

工具选择指南

Need	Use
Deep research with citations	This skill — Perplexity + Opus
Quick URL content	`web_fetch`
Brain-only lookup	`gbrain query` / `gbrain search`
Real-time social monitoring	external X / social-media collectors
Structured data lookup against a tracker	`skills/data-research/SKILL.md`

需求	适用工具
带引用的深度研究	本技能 — Perplexity + Opus
快速获取URL内容	`web_fetch`
仅基于大脑的查询	`gbrain query` / `gbrain search`
实时社交媒体监控	外部X/社交媒体收集工具
针对追踪器的结构化数据查询	`skills/data-research/SKILL.md`

Output structure

输出结构

The research output lands as a brain page under

research/<slug>.md

with this structure:

markdown

---
title: "[Topic] — Research [YYYY-MM-DD]"
type: research
date: YYYY-MM-DD
brain_context_slugs: ["pages whose context was sent to Perplexity"]
recency_filter: "[hour|day|week|month|none]"
---

研究结果将以大脑页面的形式保存至

research/<slug>.md

，结构如下：

markdown

---
title: "[主题] — 研究报告 [YYYY-MM-DD]"
type: research
date: YYYY-MM-DD
brain_context_slugs: ["发送至Perplexity的上下文页面slug"]
recency_filter: "[hour|day|week|month|none]"
---

[Topic] — Research [YYYY-MM-DD]

[主题] — 研究报告 [YYYY-MM-DD]

Executive summary: 2-3 sentences on the delta between brain knowledge and current web state.

执行摘要：用2-3句话说明大脑知识库与当前网页状态的差异。

Key New Developments

核心新进展

What's changed since the brain was last updated on this topic.

自大脑知识库最后更新以来，该主题出现的变化。

Confirming Signals

验证信号

Web evidence validating existing brain knowledge.

验证现有大脑知识库内容的网页证据。

Contradictions or Updates

矛盾或更新内容

Things that conflict with the brain — these need a closer look.

与大脑知识库冲突的内容——这些需要进一步核查。

Recommended Brain Updates

Citations

引用

Source title — accessed YYYY-MM-DD
Source title — accessed YYYY-MM-DD
...

undefined

来源标题 — 访问时间 YYYY-MM-DD
来源标题 — 访问时间 YYYY-MM-DD
...

undefined

Invocation

调用方式

The skill is markdown agent instructions; the agent uses Perplexity's API directly (or a host-provided

perplexity

CLI if installed):

bash

undefined

本技能为Markdown格式的Agent指令；Agent直接调用Perplexity的API（或已安装的主机提供的

perplexity

CLI）：

bash

undefined

1. Pull brain context

1. 获取大脑上下文

gbrain get <slug> # or gbrain query "<topic keywords>"

gbrain get <slug> # 或 gbrain query "<主题关键词>"

2. Compose the Perplexity query with brain context inline:

2. 结合大脑上下文编写Perplexity查询语句：

"""

Topic: <topic>

主题: <主题>

Brain context (what we already know): <embedded gbrain content>

大脑上下文（已掌握信息）: <嵌入的gbrain内容>

Find: what's NEW since 2026-MM-DD that the brain doesn't reflect.

查找内容：2026-MM-DD以来大脑知识库未涵盖的新增信息。

Cite every claim.

每项结论需附带引用。

"""

3. Call Perplexity API or the host's perplexity binary:

3. 调用Perplexity API或主机的perplexity二进制文件：

curl https://api.perplexity.ai/chat/completions \

-H "Authorization: Bearer $PERPLEXITY_API_KEY" \

-H "Content-Type: application/json" \

-d '{"model": "sonar-pro", "messages": [{"role":"user","content":"..."}]}'

4. Write the structured research page via put_page:

4. 通过put_page操作写入结构化研究页面：

gbrain put_page research/<slug> # via the put_page operation

gbrain put_page research/<slug> # 调用put_page操作

5. Cross-link entities mentioned (people, companies) per Iron Law.

5. 按照Iron Law对提及的实体（人物、公司）进行交叉链接。

undefined

undefined

Models

模型选择

Model	Cost / query	Use when
Perplexity sonar-pro	~$0.04	Deep analysis, entity enrichment, deal research
Perplexity sonar	~$0.007	Quick lookups, bulk monitoring, briefing pipelines

Default to sonar-pro. Drop to sonar for bulk / cron contexts where cost matters more than depth.

模型	单次查询成本	适用场景
Perplexity sonar-pro	~$0.04	深度分析、实体信息补充、交易研究
Perplexity sonar	~$0.007	快速查询、批量监控、简报流水线

默认使用sonar-pro。在批量/定时任务场景中，若成本优先级高于分析深度，可切换为sonar。

Integration patterns

集成模式

Entity enrichment

实体信息补充

Called by

skills/enrich/SKILL.md

when an entity page (person, company) needs current web context:

bash

BRAIN=$(gbrain get people/<slug> 2>/dev/null)

当实体页面（人物、公司）需要当前网页上下文时，由

skills/enrich/SKILL.md

调用本技能：

bash

BRAIN=$(gbrain get people/<slug> 2>/dev/null)

Send <slug>'s page content as brain_context to Perplexity, get current

将<slug>的页面内容作为brain_context发送至Perplexity，获取最新新闻/职位/上下文，然后更新大脑页面中的新增内容。

news / role / context, then update the brain page with what's new.

—

undefined

undefined

Deal / company monitoring (cron)

交易/公司监控（定时任务）

For each active item under

deals/

companies/

bash

undefined

针对

deals/

或

companies/

下的每个活跃项目：

bash

undefined

Weekly: pull recent news per company; flag changes for review.

每周执行：获取每家公司的近期新闻；标记变化以供审核。

undefined

undefined

Morning briefing

晨间简报

Replace raw

web_fetch

calls in briefing pipelines with this skill so the agent doesn't re-narrate already-known facts.

在简报流水线中用本技能替代原始的

web_fetch

调用，避免Agent重复叙述已掌握的事实。

Recency filter

新鲜度过滤器

Pass

recency_filter

to Perplexity:

hour | day | week | month

. Useful for news-cycle topics; omit for evergreen research.

可向Perplexity传递

recency_filter

参数：

hour | day | week | month

。适用于新闻类主题；常青研究可省略该参数。

Anti-Patterns

反模式

❌ Sending NO brain context. Then it's just a search — use
```
web_fetch
```
instead.
❌ Truncating the brain context. The whole point is "knows what you know." Send dense context.
❌ Discarding citations. Every claim in the output must have a URL.
❌ Skipping the cross-link step when entities are mentioned. Iron Law.

❌ 不发送任何大脑上下文。此时它仅为普通搜索——请改用
```
web_fetch
```
。
❌ 截断大脑上下文。本技能的核心是“了解你已掌握的信息”，需发送完整的上下文内容。
❌ 丢弃引用。输出中的每一项结论都必须附带URL。
❌ 提及实体时跳过交叉链接步骤。违反Iron Law。

Environment

环境要求

```
PERPLEXITY_API_KEY
```
set in the agent's environment (or in
```
~/.gbrain/.env
```
).
Optional: install Perplexity's official CLI for richer streaming output.

需在Agent环境中设置
```
PERPLEXITY_API_KEY
```
（或在
```
~/.gbrain/.env
```
中配置）。
可选：安装Perplexity官方CLI以获得更丰富的流式输出。

Related skills

Contract

契约

This skill guarantees:

Routing matches the canonical triggers in the frontmatter.
Output written under the directories listed in
```
writes_to:
```
(when applicable).

Conventions referenced (

quality.md

brain-first.md

_brain-filing-rules.md

) are followed.

Privacy contract preserved: no real names, no fork-specific filesystem path literals, no upstream-fork references.

The full behavior contract is documented in the body sections above; this section exists for the conformance test.

本技能保证：

路由匹配前置元数据中的标准触发条件。
输出写入
```
writes_to:
```
中列出的目录（如有）。

遵循引用的约定（

quality.md

、

brain-first.md

、

_brain-filing-rules.md

）。

遵守隐私契约：不包含真实姓名、不包含特定分支的文件系统路径字面量、不包含上游分支引用。

完整的行为契约已在上述主体部分中记录；本节为一致性测试而设。

Output Format

输出格式

The skill's output shape is documented inline in the body sections above (see "Output", "Brain page format", or equivalent). The literal section header here exists for the conformance test (

test/skills-conformance.test.ts

本技能的输出格式已在上述主体部分中内嵌说明（请参阅“输出”、“大脑页面格式”或等效章节）。本节的字面标题为一致性测试（

test/skills-conformance.test.ts

）而设。

perplexity-research

Original

Translation

perplexity-research — Brain-Augmented Web Research

perplexity-research — 大脑增强型网页研究

What this does

功能说明

When to use this vs other tools

工具选择指南

Output structure

输出结构

[Topic] — Research [YYYY-MM-DD]

[主题] — 研究报告 [YYYY-MM-DD]

Key New Developments

核心新进展

Confirming Signals

验证信号

Contradictions or Updates

矛盾或更新内容

Recommended Brain Updates

推荐更新的大脑内容

Citations

引用

Invocation

调用方式

1. Pull brain context

1. 获取大脑上下文

2. Compose the Perplexity query with brain context inline:

2. 结合大脑上下文编写Perplexity查询语句：

"""

"""

Topic: <topic>

主题: <主题>

Brain context (what we already know): <embedded gbrain content>

大脑上下文（已掌握信息）: <嵌入的gbrain内容>

Find: what's NEW since 2026-MM-DD that the brain doesn't reflect.

查找内容：2026-MM-DD以来大脑知识库未涵盖的新增信息。

Cite every claim.

每项结论需附带引用。

"""

"""

3. Call Perplexity API or the host's perplexity binary:

3. 调用Perplexity API或主机的perplexity二进制文件：

curl https://api.perplexity.ai/chat/completions \

curl https://api.perplexity.ai/chat/completions \

-H "Authorization: Bearer $PERPLEXITY_API_KEY" \

-H "Authorization: Bearer $PERPLEXITY_API_KEY" \

-H "Content-Type: application/json" \

-H "Content-Type: application/json" \

-d '{"model": "sonar-pro", "messages": [{"role":"user","content":"..."}]}'

-d '{"model": "sonar-pro", "messages": [{"role":"user","content":"..."}]}'

4. Write the structured research page via put_page:

4. 通过put_page操作写入结构化研究页面：

5. Cross-link entities mentioned (people, companies) per Iron Law.

5. 按照Iron Law对提及的实体（人物、公司）进行交叉链接。

Models

模型选择

Integration patterns

集成模式

Entity enrichment

实体信息补充

Send <slug>'s page content as brain_context to Perplexity, get current

将<slug>的页面内容作为brain_context发送至Perplexity，获取最新新闻/职位/上下文，然后更新大脑页面中的新增内容。

news / role / context, then update the brain page with what's new.

Deal / company monitoring (cron)

交易/公司监控（定时任务）

Weekly: pull recent news per company; flag changes for review.

每周执行：获取每家公司的近期新闻；标记变化以供审核。

Morning briefing

晨间简报

Recency filter

新鲜度过滤器

Anti-Patterns

反模式

Environment

环境要求

Related skills

相关技能

Contract

契约