luma-content-research

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Luma Content Research

Luma 内容调研

Use this skill when the user wants to find short-video topics, analyze references, export search results, or prepare a keyword table for later script writing with Luma / 拾光.

Read

../luma-shared/SKILL.md

first for common auth, project, and artifact rules.

当用户想要借助Luma/拾光寻找短视频话题、分析参考案例、导出搜索结果，或为后续脚本创作准备关键词表格时，可使用本技能。

请先阅读

../luma-shared/SKILL.md

了解通用的认证、项目和工件规则。

When To Use

使用场景

The user wants topic ideas, competitor references, or viral angles.
The user provides a role/persona and asks what content to make.
The user asks for an Excel-style research table.

A workflow needs

step0_content_research.json

step0_content_research.csv

, or

step0_keywords.json

Do not use this skill for script rewriting after the topic is already selected. Use script or workflow skills for that step.

用户需要话题灵感、竞品参考或爆款角度。
用户提供角色/用户画像，并询问应制作何种内容。
用户需要Excel格式的调研表格。

工作流需要生成

step0_content_research.json

、

step0_content_research.csv

或

step0_keywords.json

文件。

请勿在已选定话题后使用本技能进行脚本改写，该步骤请使用脚本或工作流类技能。

Standard Flow

标准流程

Run backend content research:

bash

luma-cli research run --role "<role_or_persona_description>" --mode precise --date-range 7d --output step0_content_research.json

Export an Excel-friendly table:

bash

luma-cli research export --input step0_content_research.json --output step0_content_research.csv

Extract keywords and topic rows:

bash

luma-cli research keywords --input step0_content_research.json --output step0_keywords.json --csv step0_keywords.csv

运行后端内容调研：

bash

luma-cli research run --role "<role_or_persona_description>" --mode precise --date-range 7d --output step0_content_research.json

导出适用于Excel的表格：

bash

luma-cli research export --input step0_content_research.json --output step0_content_research.csv

提取关键词和话题条目：

bash

luma-cli research keywords --input step0_content_research.json --output step0_keywords.json --csv step0_keywords.csv

Persona Reuse

用户画像复用

Save a reusable persona when the user describes a stable account or role:

bash

luma-cli research persona save ai_founder --role "AI tool founder making short videos for operators"
luma-cli research run --persona ai_founder --output step0_content_research.json

当用户描述一个稳定的账号或角色时，保存可复用的用户画像：

bash

luma-cli research persona save ai_founder --role "AI tool founder making short videos for operators"
luma-cli research run --persona ai_founder --output step0_content_research.json

Agent Rules

Agent 规则

Keep the raw research JSON even when exporting CSV.
Use CSV for human inspection; use JSON for agent decisions.
Pick at most 3 high-potential references or one topic cluster explicitly before moving to rewrite.
Research results are discovery data, not source scripts. For viral remix workflows, only download and ASR references that are likely to contain reusable spoken copy; skip non-口播 or low-signal videos. See
```
../luma-workflow-viral-remix/SKILL.md
```
.
Do not fabricate metrics that are not present in the research result.
If research returns too few results, retry with
```
--mode expanded
```
or a broader role description.

即使导出CSV文件，也要保留原始调研JSON文件。
使用CSV供人工查看；使用JSON供Agent决策。
在进入改写步骤前，明确选择最多3个高潜力参考案例或一个话题集群。
调研结果是发现类数据，而非源脚本。对于爆款 remix 工作流，仅下载并进行ASR（自动语音识别）处理那些可能包含可复用口播内容的参考视频；跳过非口播或低信号视频。详情请查看
```
../luma-workflow-viral-remix/SKILL.md
```
。
不得编造调研结果中未包含的指标数据。
如果调研返回结果过少，使用
```
--mode expanded
```
参数或更宽泛的角色描述重试。