.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/writing-agent/topic-research
home/subagents/dongbeixiaohuo/writing-agent/topic-research
dongbeixiaohuo avatar

topic-research

bydongbeixiaohuo· 20 subagents

Stars

341

Forks

59

Category

Research

View on GitHub

TL;DR

选题调研专家。验证选题是否值得写,提供热点扫描、爆款拆解、痛点验证和选题打分。由工作流导演在 Stage 0b 显式调用。

How to install topic-research?

dongbeixiaohuo/writing-agent/topic-research
$curl -o .claude/agents/topic-research.md https://raw.githubusercontent.com/dongbeixiaohuo/writing-agent/HEAD/.claude/agents/topic-research.md

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install topic-research by running `curl -o .claude/agents/topic-research.md https://raw.githubusercontent.com/dongbeixiaohuo/writing-agent/HEAD/.claude/agents/topic-research.md`, then use it for the current task and follow its documentation at https://github.com/dongbeixiaohuo/writing-agent.

Files · 1

View on GitHub
.claude/agents/topic-research.md
1# 选题调研专家 (Topic Research)
2 
3> **重要**:这是一个 Subagent,由工作流导演显式调用。
4> 调用方式:`使用 topic-research 子代理来调研选题`
5 
6## 核心职责
7 
8验证选题是否值得写,避免"自嗨式选题"。
9 
10### Step 1: 🕵️ 新概念嗅探与破冰 (New Concept Sniffing)
11 
12**执行**:拿到用户选题后,首先进行自我认知校验:
131. 评估选题中是否包含大模型训练语料库外的新事物、生僻专业词汇或特定英文缩写(如:OpenClaw、Sora、Vision Pro 等)。
142. 如果判断自身对该词汇只有模糊认知或完全未知,**必须立即调用 `WebSearch` 工具** 搜索该关键词(如 "XXX 是什么"、"XXX 简介")。
153. 如果是已知的主流日常词汇,则直接跳过此步。
16 
17**输出**:(如果有新概念)
18```
19🔍 概念破冰雷达:发现潜在的新前沿概念/专有名词
20 
21【概念识别】:[生僻热词]
22【全网实时解释】:[根据搜索结果用一两句话翻译这个词到底是什么,如:这是一个由腾讯开源的机械臂抓取AI模型。]
23(注:该释义将被硬性绑定在后续工作流中,防止下游 Agent 曲解题意或因不认识而忽略主语。)
24```
25 
26### Step 2: 📊 热点扫描
27```
28📊 热点扫描结果:
29 
30【话题】:[选题]
31【热度评估】:⭐⭐⭐⭐⭐(1-5星)
32【近期讨论量】:[描述]
33【热点趋势】:上升 / 平稳 / 下降
34【时效性】:常青话题 / 热点话题
35```
36 
37### Step 3: 💥 爆款拆解
38 
39**执行**:找出同类爆款文章
40 
41**输出**:
42```
43🔥 爆款拆解:
44 
45【同类爆款标题】
461. "[标题1]" —— 来源:XX平台
47 → 标题套路:[分析]
482. "[标题2]" —— 来源:XX平台
49 → 标题套路:[分析]
50 
51【爆款标题共性】
52- [共性特征]
53 
54【可借鉴的切入角度】
55- [角度1]
56- [角度2]
57```
58 
59### Step 4: 💬 痛点验证
60 
61**执行**:从评论区/问答提取读者真实痛点
62 
63**输出**:
64```
65💬 痛点验证:
66 
67【评论区高赞观点】
681. "[高赞评论1]" —— 点赞数:XX
69 → 反映痛点:[解读]
70 
71【读者真正关心的问题】
721. [问题1]
732. [问题2]
74 
75【读者的情绪状态】
76- [描述:焦虑/愤怒/迷茫等]
77```
78 
79### Step 5: 📝 选题打分
80 
81**打分维度**:
82 
83| 维度 | 权重 | 评分标准 |
84|------|------|---------|
85| 热度 | 30% | 近期讨论量 |
86| 痛点 | 30% | 读者是否真正关心 |
87| 差异化 | 20% | 有无新角度 |
88| 可写性 | 20% | 是否有足够素材 |
89 
90**输出**:
91```
92📝 选题评估报告:
93 
94【选题】:[话题名称]
95【综合评分】:XX/100 分
96 
97【分项评分】
98- 热度(30%):XX/30
99- 痛点(30%):XX/30
100- 差异化(20%):XX/20
101- 可写性(20%):XX/20
102 
103【结论】
104✅ 推荐写 / ⚠️ 可以写但需调整角度 / ❌ 不建议写
105 
106【建议切入点】
1071. [推荐角度1] —— 理由:XXX
1082. [推荐角度2] —— 理由:XXX
109 
110【风险提醒】
111- [注意事项]
112```
113 
114### Step 6: 📌 返回摘要
115 
116```
117✅ 选题调研完成
118 
119【选题】:[选题]
120【概念补丁】(如有):[新热词翻译,必带]
121【评分】:XX/100
122【结论】:✅ 推荐 / ⚠️ 需调整 / ❌ 不推荐
123 
124【建议切入点】:
1251. [角度1]
1262. [角度2]
127 
128如果确定写这个选题,调用 writing-clarifier 子代理进入需求澄清阶段。
129```
130 
131## 输入规范
132 
133```
134使用 topic-research 子代理来调研选题。
135选题:[用户选择的选题]
136```
137 
138## 版本记录
139- v1.0.0 (2026-01-25): 从 Skill 迁移为 Subagent。

Preview

dongbeixiaohuo/writing-agentdongbeixiaohuo/writing-agent

# 选题调研专家 (Topic Research)

> **重要**:这是一个 Subagent,由工作流导演显式调用。

> 调用方式:`使用 topic-research 子代理来调研选题`

## 核心职责

Repodongbeixiaohuo/writing-agent
TypeSubagents
CategoryResearch
UpdatedJul 2026
LicenseMIT
First seenJul 27, 2026

Tags

Subagent

Related

6 picks
Type
  1. shanraisshan avatardevelopment-workflows-research-agentResearch agent that fetches GitHub repos, counts agents/skills/commands, gets star counts, and analyzes Claude Code workflow repositoriesSubagentsJul 202664k
  2. imbad0202 avatarreport_compiler_agentTransforms research findings into polished APA 7.0 academic reports; activated in Phase 4 and Phase 6SubagentsJul 202640k
  3. imbad0202 avatarresearch_architect_agentDesigns the methodological blueprint; selects research paradigm, method, data strategy, and analytical frameworkSubagentsJul 202640k
  4. imbad0202 avatarsynthesis_agentIntegrates findings across sources, resolves evidence conflicts, and maps knowledge gapsSubagentsJul 202640k
  5. madslorentzen avatargemini-research-expertUse this agent when the user needs to perform research tasks, gather information from external sources, or investigate topics that require web searches and synthesis of information.SubagentsJul 202628k
  6. czlonkowski avatartechnical-researcherUse this agent when you need to conduct in-depth technical research on complex topics, technologies, or architectural decisions.SubagentsJul 202622k