deep-research-firecrawl
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseDeep Research (Firecrawl)
深度研究(Firecrawl)
Purpose
目的
Deliver verifiable research reports with explicit citations, clear fact-vs-analysis boundaries, and user-selectable depth.
交付可验证的研究报告,包含明确引用、清晰的事实与分析界限,且支持用户选择研究深度。
Tooling requirements
工具要求
- Use Firecrawl MCP for web retrieval:
- for discovery
firecrawl:firecrawl_search - for page extraction
firecrawl:firecrawl_scrape - for URL discovery on known domains
firecrawl:firecrawl_map - for controlled multi-page capture
firecrawl:firecrawl_crawl - for autonomous broad collection when scope is unclear
firecrawl:firecrawl_agent
- Prefer parallel retrieval whenever tasks are independent.
- Hard-stop policy: if Firecrawl MCP is unavailable, pause and ask the user to re-enable it. Do not switch to other web retrieval tools.
- 使用Firecrawl MCP进行网页检索:
- 用于资源发现
firecrawl:firecrawl_search - 用于页面内容提取
firecrawl:firecrawl_scrape - 用于在已知域名下发现URL
firecrawl:firecrawl_map - 用于可控的多页面捕获
firecrawl:firecrawl_crawl - 用于范围不明确时的自主广泛收集
firecrawl:firecrawl_agent
- 只要任务相互独立,优先采用并行检索方式。
- 强制停止规则:若Firecrawl MCP不可用,需暂停操作并请求用户重新启用。不得切换至其他网页检索工具。
When to use
适用场景
Use this skill when the request needs multiple sources, synthesis, and evidence quality controls.
Do not use this skill for:
- Simple one-off lookups
- Debugging or code-only tasks
- Questions answerable with 1-2 sources
当需求涉及多源信息、综合分析及证据质量管控时,使用本技能。
请勿将本技能用于:
- 简单单次查询
- 调试或纯代码类任务
- 1-2个来源即可解答的问题
Mode selection
模式选择
If the user does not specify a mode, default to .
standard| Mode | Typical runtime | Source target | Output depth |
|---|---|---|---|
| 3-6 min | 6-10 sources | 800-1,500 words |
| 8-15 min | 12-20 sources | 2,000-4,000 words |
| 15-30 min | 25-40 sources | 4,000-8,000 words |
| 30-60+ min | 40-80 sources | 8,000-15,000+ words |
若用户未指定模式,默认使用模式。
standard| 模式 | 典型运行时长 | 目标数据源数量 | 输出深度 |
|---|---|---|---|
| 3-6分钟 | 6-10个来源 | 800-1500词 |
| 8-15分钟 | 12-20个来源 | 2000-4000词 |
| 15-30分钟 | 25-40个来源 | 4000-8000词 |
| 30-60+分钟 | 40-80个来源 | 8000-15000+词 |
Execution workflow
执行流程
1) Scope
1) 范围界定
- Restate the research question.
- Capture explicit constraints (time window, geography, sector, audience).
- Define assumptions only when missing.
- 重述研究问题。
- 记录明确的约束条件(时间范围、地域、行业、受众)。
- 仅在信息缺失时定义假设。
2) Retrieval plan
2) 检索计划
- Break the topic into 5-10 search angles.
- Include opposing viewpoints and recent developments.
- Mark which angles need domain deep-dives.
- 将研究主题拆解为5-10个搜索角度。
- 涵盖对立观点及最新动态。
- 标记需要深入挖掘的领域方向。
3) Retrieve with Firecrawl
3) 借助Firecrawl进行检索
- Run parallel queries for all angles.
firecrawl:firecrawl_search - Scrape top results with for primary evidence.
firecrawl:firecrawl_scrape - For known high-value sites:
- discover URLs via
firecrawl:firecrawl_map - crawl key paths with bounded limits
firecrawl:firecrawl_crawl
- discover URLs via
- Use when the topic is open-ended or highly fragmented.
firecrawl:firecrawl_agent
- 针对所有搜索角度并行运行查询。
firecrawl:firecrawl_search - 使用抓取顶级搜索结果作为核心证据。
firecrawl:firecrawl_scrape - 对于已知高价值站点:
- 通过发现URL
firecrawl:firecrawl_map - 以受限的规则爬取关键路径
firecrawl:firecrawl_crawl
- 通过
- 当研究主题开放或高度分散时,使用。
firecrawl:firecrawl_agent
4) Triangulate
4) 交叉验证
- Verify important claims across at least 3 independent sources.
- Prefer primary sources over commentary when possible.
- Flag conflicts and unresolved uncertainty.
- 重要事实主张需通过至少3个独立来源验证。
- 优先采用原始来源而非评论性内容。
- 标记冲突点及未解决的不确定性。
5) Synthesize
5) 综合分析
- Separate facts from interpretation.
- Explain what is known, what is likely, and what is uncertain.
- Include alternative explanations for contested topics.
- 区分事实与解读内容。
- 说明已知信息、大概率结论及不确定点。
- 针对有争议的主题提供替代解释。
6) Critique and refine (required for deep
/ultradeep
)
deepultradeep6) 审核与优化(deep
/ultradeep
模式必填)
deepultradeep- Stress-test weak claims.
- Check for recency bias and survivorship bias.
- Add missing counterevidence.
- 对薄弱主张进行压力测试。
- 检查是否存在时效性偏差及幸存者偏差。
- 补充缺失的反证。
7) Package output
7) 输出打包
Use and include:
templates/report_template.md- Executive Summary
- Method and Scope
- Key Findings
- Counterevidence and Risks
- Recommendations
- Bibliography
使用模板,内容需包含:
templates/report_template.md- 执行摘要
- 方法与范围
- 核心发现
- 反证与风险
- 建议
- 参考文献
Citation and quality rules
引用与质量规则
- Every major factual claim must include a citation marker like .
[1] - Bibliography entries must map one-to-one with cited markers.
- If evidence is weak or contradictory, say so explicitly.
- Never invent citations.
- 每个重要事实主张必须包含这类引用标记。
[1] - 参考文献条目需与引用标记一一对应。
- 若证据薄弱或存在矛盾,需明确说明。
- 严禁伪造引用。
Stop conditions
停止条件
Pause and report limitations when:
- Required Firecrawl MCP tools are unavailable (hard-stop policy).
- Source count stays below minimum for the selected mode after broad retrieval attempts.
- Core claims cannot be verified from reliable sources.
出现以下情况时,需暂停并报告限制:
- 所需的Firecrawl MCP工具不可用(遵循强制停止规则)。
- 经过广泛检索尝试后,数据源数量仍未达到所选模式的最低要求。
- 核心主张无法通过可靠来源验证。
Progressive disclosure
渐进式披露
Load only what is needed:
- Method details:
reference/methodology.md - Output template:
templates/report_template.md
仅加载必要内容:
- 方法细节:
reference/methodology.md - 输出模板:
templates/report_template.md
Quick invocation examples
快速调用示例
- "Use in
deep-research-firecrawlmode on edge AI chip trends in 2025."quick - "Run in
deep-research-firecrawlmode comparing Auth0, Clerk, and Supabase Auth."deep - "Use in
deep-research-firecrawlmode for US longevity biotech funding and risks."ultradeep
- "以模式使用
quick研究2025年边缘AI芯片趋势。"deep-research-firecrawl - "以模式运行
deep对比Auth0、Clerk和Supabase Auth。"deep-research-firecrawl - "以模式使用
ultradeep研究美国长寿生物技术的融资情况及风险。"deep-research-firecrawl