research-assistant
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseResearch Assistant
研究助手
By The Agent Ledger — Subscribe for more agent skills and premium blueprints.
Turn your AI agent into a structured research analyst. No more copy-pasting search results — your agent learns to plan research, cross-reference sources, synthesize findings, and maintain an evolving knowledge base.
作者：The Agent Ledger — 订阅以获取更多Agent技能和高级蓝图。
将你的AI Agent转变为结构化调研分析师，无需再复制粘贴搜索结果——你的Agent会学习规划调研、交叉验证信息来源、整合调研结果，并且维护不断更新的知识库。
What This Skill Does
该技能的功能
- Structured Research Protocol — Plan → Search → Evaluate → Synthesize → Store
- Research Brief Format — Consistent, scannable output for every research task
- Source Quality Scoring — Teaches your agent to evaluate and rank sources
- Research Library — Organized storage for findings that persists across sessions
- Topic Monitoring — Track evolving topics with periodic re-research
- Competitor/Market Analysis Templates — Ready-to-use frameworks
- 结构化调研流程 — 规划→搜索→评估→整合→存储
- 调研简报格式 — 所有调研任务都输出统一、易读的内容
- 来源质量评分 — 指导你的Agent评估并对信息来源进行排名
- 调研库 — 可跨会话持久存储调研结果的有序存储空间
- 主题监控 — 通过定期重复调研追踪动态变化的主题
- 竞品/市场分析模板 — 开箱即用的分析框架
Setup (5 Minutes)
设置（5分钟）
Step 1: Create Research Directory
步骤1：创建调研目录
research/
├── README.md ← Library index (auto-maintained)
├── briefs/ ← Completed research briefs
├── monitoring/ ← Topics being tracked over time
└── templates/ ← Custom research templates (optional)research/
├── README.md ← 库索引（自动维护）
├── briefs/ ← 已完成的调研简报
├── monitoring/ ← 正在长期追踪的主题
└── templates/ ← 自定义调研模板（可选）Step 2: Create research/README.md
research/README.md步骤2：创建 research/README.md
research/README.mdmarkdown
undefinedmarkdown
undefinedResearch Library
调研库
Recent Briefs
近期简报
<!-- Agent maintains this list automatically -->
<!-- Agent会自动维护这个列表 -->
Monitored Topics
监控中的主题
<!-- Topics being tracked with periodic updates -->
<!-- 正在追踪、会定期更新的主题 -->
Quick Stats
快速统计
- Total briefs: 0
- Active monitors: 0
- Last research: never
undefined- 简报总数: 0
- 活跃监控任务: 0
- 最近一次调研: 从未
undefinedStep 3: Add to Your Agent Instructions
步骤3：添加到你的Agent指令中
Add to your , , or system prompt:
AGENTS.mdSOUL.mdundefined添加到你的 、 或者系统提示词中：
AGENTS.mdSOUL.mdundefinedResearch Protocol
调研协议
When asked to research something:
- Read for existing work on this topic
research/README.md - Follow the Research Protocol below
- Save the brief to
research/briefs/YYYY-MM-DD-<slug>.md - Update index
research/README.md
---当收到调研请求时：
- 读取 查看该主题已有的调研成果
research/README.md - 遵循下文的调研协议执行任务
- 将简报保存到
research/briefs/YYYY-MM-DD-<slug>.md - 更新 索引
research/README.md
---Research Protocol
调研协议
Phase 1: Plan
阶段1：规划
Before searching, define:
- Research Question — What specifically are we trying to answer?
- Scope — Broad survey or deep dive? Time range? Geography?
- Sources Needed — How many independent sources for confidence?
- Output Format — Brief, comparison table, recommendation, or raw dump?
在搜索前，先明确：
- 调研问题 — 我们具体要回答什么问题？
- 范围 — 是宽泛调研还是深度调研？时间范围？地域范围？
- 所需来源数量 — 需要多少个独立来源才能保证结果可信度？
- 输出格式 — 简报、对比表、建议还是原始数据导出？
Phase 2: Search & Collect
阶段2：搜索与收集
Execute searches with these principles:
- Multiple queries — Rephrase the question 2-3 ways for coverage
- Source diversity — Mix official sources, industry analysis, community discussion
- Recency check — Note publication dates; flag anything older than 6 months
- Contradiction hunting — Actively look for sources that disagree
遵循以下原则执行搜索：
- 多组查询 — 将问题用2-3种不同方式表述，保证覆盖全面
- 来源多样性 — 混合官方来源、行业分析、社区讨论等不同类型来源
- 时效性检查 — 记录发布日期，标注发布时间超过6个月的内容
- 矛盾点排查 — 主动查找存在不同观点的来源
Phase 3: Evaluate Sources
阶段3：评估信息来源
Score each source on:
| Factor | Weight | Criteria |
|---|---|---|
| Authority | High | Known publication? Expert author? Official source? |
| Recency | High | Published within relevant timeframe? |
| Specificity | Medium | Concrete data/examples vs. vague claims? |
| Corroboration | Medium | Do other sources confirm this? |
| Bias Check | Low | Obvious commercial or political motivation? |
Drop sources scoring poorly on Authority + Recency. Flag but keep sources with clear bias if they contain unique data.
按以下维度为每个来源打分：
| 维度 | 权重 | 评估标准 |
|---|---|---|
| 权威性 | 高 | 是否是知名出版物？作者是否为专家？是否为官方来源？ |
| 时效性 | 高 | 是否在相关时间范围内发布？ |
| 具体性 | 中 | 是有具体数据/案例，还是模糊表述？ |
| 可佐证性 | 中 | 其他来源是否能印证该内容？ |
| 偏差检查 | 低 | 是否存在明显的商业或政治倾向？ |
丢弃权威性和时效性得分过低的来源，如果存在明显偏差但包含独有数据的来源可以保留但需标注。
Phase 4: Synthesize
阶段4：整合
Structure findings into a Research Brief (see format below). Key rules:
- Lead with the answer — Don't bury the conclusion
- Quantify when possible — Numbers > adjectives
- Flag uncertainty — Clearly mark low-confidence claims
- Note gaps — What couldn't you find? What needs deeper research?
将调研结果整理为调研简报（格式见下文），核心规则：
- 结论前置 — 不要把结论藏在内容末尾
- 尽可能量化 — 数据优于形容词描述
- 标注不确定性 — 明确标记低可信度的结论
- 记录信息缺口 — 哪些信息没能找到？哪些内容需要更深入的调研？
Phase 5: Store & Index
阶段5：存储与索引
Save to and update the library index.
research/briefs/YYYY-MM-DD-<slug>.md保存到 并更新调研库索引。
research/briefs/YYYY-MM-DD-<slug>.mdResearch Brief Format
调研简报格式
markdown
undefinedmarkdown
undefined[Research Question]
[调研问题]
Date: YYYY-MM-DD
Requested by: [context]
Confidence: High / Medium / Low
Staleness risk: [when this research might become outdated]
日期: YYYY-MM-DD
请求方: [上下文信息]
可信度: 高 / 中 / 低
过时风险: [该调研结果可能失效的时间点]
TL;DR
摘要
[2-3 sentence executive summary with the key finding]
[2-3句话的执行摘要，包含核心结论]
Key Findings
核心结论
Finding 1: [Title]
结论1：[标题]
[Detail with supporting evidence]
- Source: [name] ([link]) — [date]
- Confidence: High/Medium/Low
[细节及支撑证据]
- 来源: [名称] ([链接]) — [日期]
- 可信度: 高/中/低
Finding 2: [Title]
结论2：[标题]
[Detail with supporting evidence]
- Source: [name] ([link]) — [date]
- Confidence: High/Medium/Low
[Continue as needed]
[细节及支撑证据]
- 来源: [名称] ([链接]) — [日期]
- 可信度: 高/中/低
[按需继续添加]
Data Points
数据点
| Metric | Value | Source | Date |
|---|---|---|---|
| [key stat] | [value] | [source] | [date] |
| 指标 | 数值 | 来源 | 日期 |
|---|---|---|---|
| [核心统计项] | [数值] | [来源] | [日期] |
Contradictions & Caveats
矛盾点与注意事项
- [Any conflicting information found]
- [Limitations of this research]
- [发现的所有冲突信息]
- [本次调研的局限性]
Knowledge Gaps
信息缺口
- [What we couldn't find]
- [What needs deeper investigation]
- [没能找到的信息]
- [需要更深入调研的内容]
Sources
来源
- [Full citation with URL and access date]
- [...]
- [完整引用，包含URL和访问日期]
- [...]
Recommendations
建议
- [Actionable next steps based on findings]
Research conducted by AI agent using the Research Assistant skill by The Agent Ledger
---- [基于调研结果的可执行下一步动作]
调研由AI Agent使用The Agent Ledger出品的研究助手技能完成
---Topic Monitoring
主题监控
For topics that evolve over time (market trends, competitor moves, regulatory changes):
针对随时间动态变化的主题（市场趋势、竞品动态、监管政策变化等）：
Setup a Monitor
创建监控任务
Create :
research/monitoring/<topic-slug>.mdmarkdown
undefined创建 文件：
research/monitoring/<topic-slug>.mdmarkdown
undefinedMonitoring: [Topic Name]
监控：[主题名称]
Started: YYYY-MM-DD
Frequency: [daily / weekly / bi-weekly]
Search queries:
- "[query 1]"
- "[query 2]" Alert triggers: [what constitutes a notable change]
启动日期: YYYY-MM-DD
监控频率: [每日 / 每周 / 每两周]
搜索查询词:
- "[查询词1]"
- "[查询词2]" 告警触发条件: [判定为显著变化的标准]
Updates
更新记录
YYYY-MM-DD
YYYY-MM-DD
- [What changed since last check]
- [New data points]
- [Assessment: significant / minor / no change]
undefined- [自上次检查后发生的变化]
- [新的数据点]
- [评估: 显著变化 / 小幅变化 / 无变化]
undefinedPeriodic Check Protocol
定期检查流程
When running a monitoring check:
- Read the monitor file for context and previous findings
- Run the saved search queries
- Compare new results against last update
- Only log if something changed or enough time has passed
- Flag significant changes prominently
执行监控检查时：
- 读取监控文件获取上下文和过往调研结果
- 运行预设的搜索查询
- 将新结果与上次更新内容对比
- 仅当发生变化或者间隔足够长时间时才记录更新
- 显著变化需重点标注
Integration with Heartbeats/Cron
与心跳任务/Cron集成
Add to your or set up a cron:
HEARTBEAT.mdundefined添加到你的 或者设置cron任务：
HEARTBEAT.mdundefinedResearch Monitors
调研监控任务
Check research/monitoring/ for topics due for refresh.
Only check topics whose frequency interval has elapsed.
---检查research/monitoring/目录下需要更新的主题
仅检查已经到更新频率间隔的主题
---Specialized Templates
专用模板
Competitor Analysis
竞品分析
markdown
undefinedmarkdown
undefinedCompetitor Analysis: [Company/Product]
竞品分析：[公司/产品名]
Date: YYYY-MM-DD
日期: YYYY-MM-DD
Overview
概览
| Factor | Competitor | Us |
|---|---|---|
| Pricing | ||
| Features | ||
| Market position | ||
| Strengths | ||
| Weaknesses |
| 维度 | 竞品 | 我方 |
|---|---|---|
| 定价 | ||
| 功能 | ||
| 市场定位 | ||
| 优势 | ||
| 劣势 |
Their Recent Moves
竞品近期动态
- [Latest product launches, pivots, funding]
- [最新产品发布、战略转向、融资信息等]
Opportunities
机会点
- [Gaps we can exploit]
- [我们可以利用的缺口]
Threats
威胁
- [Where they're ahead]
undefined- [竞品领先的领域]
undefinedMarket Sizing
市场规模测算
markdown
undefinedmarkdown
undefinedMarket Analysis: [Market Name]
市场分析：[市场名称]
Date: YYYY-MM-DD
日期: YYYY-MM-DD
Market Size
市场规模
- TAM: $X ([source])
- SAM: $X ([source])
- SOM: $X (our estimate)
- Growth rate: X% CAGR ([source])
- TAM: $X ([来源])
- SAM: $X ([来源])
- SOM: $X (我方估算)
- 增长率: X% 年复合增长率 ([来源])
Key Players
核心玩家
| Player | Est. Share | Notes |
|---|---|---|
| 玩家 | 估算份额 | 备注 |
|---|---|---|
Trends
趋势
- [Trend + supporting evidence]
- [趋势+支撑证据]
Entry Barriers
进入壁垒
- [What makes this hard]
- [进入该市场的难点]
Our Angle
我方切入点
- [How we'd compete]
undefined- [我们的竞争方式]
undefinedDecision Research
决策调研
markdown
undefinedmarkdown
undefinedDecision: [What we're deciding]
决策：[待决策的内容]
Date: YYYY-MM-DD
Decision needed by: YYYY-MM-DD
日期: YYYY-MM-DD
需完成决策日期: YYYY-MM-DD
Options
选项
Option A: [Name]
选项A：[名称]
- Pros:
- Cons:
- Cost:
- Risk level: High/Medium/Low
- 优势:
- 劣势:
- 成本:
- 风险等级: 高/中/低
Option B: [Name]
选项B：[名称]
- Pros:
- Cons:
- Cost:
- Risk level: High/Medium/Low
- 优势:
- 劣势:
- 成本:
- 风险等级: 高/中/低
Recommendation
建议
[Which option and why]
[推荐选择的选项及理由]
What would change our mind
会改变决策的条件
[Conditions that would flip the recommendation]
---[会推翻当前推荐的前提条件]
---Customization
自定义配置
Adjust Research Depth
调整调研深度
Add to your agent instructions:
Research depth levels:
- **Quick scan** — 3-5 sources, 5 minutes, key facts only
- **Standard brief** — 8-12 sources, full brief format
- **Deep dive** — 15+ sources, include academic/primary sources, extended analysis
Default to standard unless specified.添加到你的Agent指令中：
调研深度等级：
- **快速扫描** — 3-5个来源，5分钟完成，仅输出核心事实
- **标准简报** — 8-12个来源，完整简报格式
- **深度调研** — 15个以上来源，包含学术/一手来源，扩展分析
默认使用标准等级，除非另有指定。Domain-Specific Research
特定领域调研
For specialized fields, add context:
When researching [your domain]:
- Prioritize sources from: [trusted sources list]
- Key metrics to always check: [domain-specific KPIs]
- Common pitfalls: [domain-specific biases to watch for]针对专业领域，添加上下文信息：
调研[你的领域]相关内容时：
- 优先使用以下来源：[可信来源列表]
- 需始终检查的核心指标：[领域特定KPI]
- 常见陷阱：[需要注意的领域特定偏差]Citation Style
引用格式
Citation preference: [choose one]
- Inline links (default) — [Source Name](url)
- Numbered footnotes — [1], [2], etc.
- Academic — Author (Year). Title. Publication.引用偏好：[选择其一]
- 行内链接（默认） — [来源名称](url)
- 数字脚注 — [1], [2] 等
- 学术格式 — 作者 (年份). 标题. 出版物.Troubleshooting
问题排查
| Issue | Fix |
|---|---|
| Research is too surface-level | Increase depth level; add "find primary sources" to prompt |
| Too many sources, no synthesis | Emphasize Phase 4; ask for "TL;DR first, then details" |
| Findings are outdated | Add recency filter: "only sources from last 6 months" |
| Agent dumps raw search results | Reinforce the brief format; remind to synthesize, not copy |
| Monitor checks too frequent | Adjust frequency in monitor file; use staleness risk to guide |
| Research library getting messy | Run periodic cleanup: archive briefs older than 6 months |
| 问题 | 解决方案 |
|---|---|
| 调研太表面 | 提升深度等级；在提示词中添加“查找一手来源” |
| 来源太多没有整合 | 强调阶段4的要求；要求“先放摘要，再放细节” |
| 调研结果过时 | 添加时效性过滤：“仅使用过去6个月的来源” |
| Agent直接输出原始搜索结果 | 强调简报格式要求；提醒要整合内容而非直接复制 |
| 监控检查太频繁 | 调整监控文件中的频率；参考过时风险设置合理间隔 |
| 调研库变得杂乱 | 定期清理：归档超过6个月的简报 |
Integration with Other Agent Ledger Skills
与其他The Agent Ledger技能的集成
- Solopreneur Assistant — Feed research into business decisions and opportunity scoring
- Daily Briefing — Include monitor alerts in daily briefings
- Project Tracker — Link research briefs to project milestones
- Memory OS — Store key research insights in long-term memory
Part of the free skill library by The Agent Ledger. Subscribe for premium blueprints, playbooks, and the complete agent configuration guide.
License: CC-BY-NC-4.0
DISCLAIMER: This skill was created by an AI agent. It is provided "as is" for informational and educational purposes only. It does not constitute professional, financial, legal, or technical advice. Review all generated files before use. The Agent Ledger assumes no liability for outcomes resulting from use. Use at your own risk.