深度研究工具deep-research：AI驱动的高质量研究报告生成与自动化写作

deep-research by daymade/claude-code-skills

238 周安装量

778 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/daymade/claude-code-skills --skill deep-research

AI/机器学习内容创作研究方法

🇨🇳中文介绍

深度研究

通过严格的格式控制、证据映射和多轮综合，创建高质量的研究报告。

快速开始

明确报告规范和格式约定
制定研究计划和查询集
使用 deepresearch 工具收集证据（如需要可进行多轮）
筛选来源并构建证据表
通过多轮完整起草（并行子代理）撰写完整报告草案
进行 UNION 合并、强制执行格式合规性、验证引用
提交草案供人工审阅并进行迭代

核心工作流程

复制此清单并跟踪进度：

Deep Research Progress:
- [ ] 步骤 1：需求接收与格式约定
- [ ] 步骤 2：研究计划与查询集
- [ ] 步骤 3：证据收集（deepresearch 工具）
- [ ] 步骤 4：来源筛选与证据表
- [ ] 步骤 5：大纲与章节映射
- [ ] 步骤 6：多轮完整起草（并行子代理）
- [ ] 步骤 7：UNION 合并与格式合规
- [ ] 步骤 8：证据与引用验证
- [ ] 步骤 9：提交草案供人工审阅与迭代

步骤 1：需求接收与格式约定

在进行任何研究之前，确立报告要求：

确认受众、目的、范围、时间范围和地理区域
锁定输出格式：Markdown、DOCX、幻灯片或用户提供的模板
捕获必需的章节和确切的格式规则
确认引用风格（脚注、内联、编号、APA 等）
确认各章节的长度目标
询问是否有现有的风格指南或示例报告

创建一个简洁的报告规范文件：

Report Spec:
- Audience:
- Purpose:
- Scope:
- Time Range:
- Geography:
- Required Sections:
- Section Formatting Rules:
- Citation Style:
- Output Format:
- Length Targets:
- Tone:
- Must-Include Sources:
- Must-Exclude Topics:

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

步骤 2：研究计划与查询集

在调用工具之前定义研究策略：

将主要问题分解为 3-7 个子问题
定义关键实体、关键词和同义词
区分一手来源与二手来源
定义排除标准（过时、质量低、仅为观点）
为每个章节组装查询集

步骤 3：证据收集（Deepresearch 工具）

使用 deepresearch 工具收集证据和引用。

如果覆盖范围不确定，运行多轮完整收集
改变查询措辞以减少盲点
将原始工具输出保存在文件中以便追溯

文件结构（推荐）：

<output_dir>/research/<topic-name>/
  deepresearch_pass1.md
  deepresearch_pass2.md
  deepresearch_pass3.md

如果 deepresearch 不可用，则仅依赖用户提供的来源，并明确说明限制。

步骤 4：来源筛选与证据表

在起草前对来源进行标准化和评分：

跨轮次去重来源
使用 references/source_quality_rubric.md 对来源进行评分
构建将论点映射到来源的证据表

证据表至少包含以下列：

Source ID
Title
Publisher
Date
URL or reference
Quality tier (A/B/C)
Notes

步骤 5：大纲与章节映射

创建一个强制执行格式约定的提纲：

使用 references/research_report_template.md 中的模板
生成包含每个章节所需元素的章节映射
确认排序和标题与报告规范匹配

步骤 6：多轮完整起草（并行子代理）

避免单轮起草；生成多个完整报告，然后合并。

首选策略：并行子代理（每个起草完整报告）

使用 Task 工具生成具有独立上下文的并行子代理。每个子代理必须：

加载报告规范、大纲和证据表
起草完整的报告（所有章节）
强制执行格式规则和引用风格

Task(subagent_type="general-purpose", prompt="Draft complete report ...", run_in_background=false) -> version1.md
Task(subagent_type="general-purpose", prompt="Draft complete report ...", run_in_background=false) -> version2.md
Task(subagent_type="general-purpose", prompt="Draft complete report ...", run_in_background=false) -> version3.md

将草案写入文件，而非对话上下文：

<output_dir>/intermediate/<topic-name>/version1.md
<output_dir>/intermediate/<topic-name>/version2.md
<output_dir>/intermediate/<topic-name>/version3.md

步骤 7：UNION 合并与格式合规

使用 UNION 进行合并，切勿在没有基于证据的理由的情况下删除内容：

保留所有版本中的所有独特发现
合并重复项，同时保留最详细的措辞
确保合并草案中的每个论点都有引用的来源
强制执行确切的章节顺序、标题和格式
重新运行 references/formatting_rules.md 中的格式规则

步骤 8：证据与引用验证

验证可追溯性：

每个数字论点至少有一个来源
每条建议都引用了支持证据
没有无引用的孤立论点
日期和时间范围一致
冲突被明确指出并附上双方来源

步骤 9：提交草案供人工审阅与迭代

将草案作为可审阅的版本提交：

强调格式合规性和事实准确性需要人工审查
接受对格式、结构和范围的编辑
如果用户提供了另一个 AI 输出，请进行交叉比较和 UNION 合并

匹配要求的语言和语气
保留英文技术术语
遵守报告规范和格式规则
包含参考文献部分或参考书目

文件	何时加载
research_report_template.md	构建大纲和起草结构
formatting_rules.md	强制执行章节格式和引用规则
source_quality_rubric.md	对来源进行评分和筛选
research_plan_checklist.md	制定研究计划和查询集
completeness_review_checklist.md	审查覆盖范围、引用和合规性

没有并行完整轮次的单轮起草
按章节拆分轮次而非完整报告草案
忽略格式约定或用户模板
论点没有引用或证据表映射
混合冲突日期而未明确指出差异
未经核实即复制外部 AI 输出
删除中间草案或原始研究输出

🇺🇸English

Deep Research

Create high-fidelity research reports with strict format control, evidence mapping, and multi-pass synthesis.

Quick Start

Clarify the report spec and format contract
Build a research plan and query set
Collect evidence with the deepresearch tool (multi-pass if needed)
Triage sources and build an evidence table
Draft the full report in multiple complete passes (parallel subagents)
UNION merge, enforce format compliance, verify citations
Present draft for human review and iterate

Core Workflow

Copy this checklist and track progress:

Deep Research Progress:
- [ ] Step 1: Intake and format contract
- [ ] Step 2: Research plan and query set
- [ ] Step 3: Evidence collection (deepresearch tool)
- [ ] Step 4: Source triage and evidence table
- [ ] Step 5: Outline and section map
- [ ] Step 6: Multi-pass full drafting (parallel subagents)
- [ ] Step 7: UNION merge and format compliance
- [ ] Step 8: Evidence and citation verification
- [ ] Step 9: Present draft for human review and iterate

Step 1: Intake and Format Contract

Establish the report requirements before any research:

Confirm audience, purpose, scope, time range, and geography
Lock output format: Markdown, DOCX, slides, or user-provided template
Capture required sections and exact formatting rules
Confirm citation style (footnotes, inline, numbered, APA, etc.)
Confirm length targets per section
Ask for any existing style guide or sample report

Create a concise report spec file:

Report Spec:
- Audience:
- Purpose:
- Scope:
- Time Range:
- Geography:
- Required Sections:
- Section Formatting Rules:
- Citation Style:
- Output Format:
- Length Targets:
- Tone:
- Must-Include Sources:
- Must-Exclude Topics:

If a user provides a template or an example report, treat it as a hard constraint and mirror the structure.

Step 2: Research Plan and Query Set

Define the research strategy before calling tools:

Break the main question into 3-7 subquestions
Define key entities, keywords, and synonyms
Identify primary sources vs secondary sources
Define disqualifiers (outdated, low quality, opinion-only)
Assemble a query set per section

Use references/research_plan_checklist.md for guidance.

Step 3: Evidence Collection (Deepresearch Tool)

Use the deepresearch tool to collect evidence and citations.

Run multiple complete passes if coverage is uncertain
Vary query phrasing to reduce blind spots
Preserve raw tool output in files for traceability

File structure (recommended):

<output_dir>/research/<topic-name>/
  deepresearch_pass1.md
  deepresearch_pass2.md
  deepresearch_pass3.md

If deepresearch is unavailable, rely on user-provided sources only and state limitations explicitly.

Step 4: Source Triage and Evidence Table

Normalize and score sources before drafting:

De-duplicate sources across passes
Score sources using references/source_quality_rubric.md
Build an evidence table mapping claims to sources

Evidence table minimum columns:

Source ID
Title
Publisher
Date
URL or reference
Quality tier (A/B/C)
Notes

Step 5: Outline and Section Map

Create an outline that enforces the format contract:

Use the template in references/research_report_template.md
Produce a section map with required elements per section
Confirm ordering and headings match the report spec

Step 6: Multi-Pass Full Drafting (Parallel Subagents)

Avoid single-pass drafting; generate multiple complete reports, then merge.

Preferred Strategy: Parallel Subagents (Complete Draft Each)

Use the Task tool to spawn parallel subagents with isolated context. Each subagent must:

Load the report spec, outline, and evidence table
Draft the FULL report (all sections)
Enforce formatting rules and citation style

Implementation pattern:

Task(subagent_type="general-purpose", prompt="Draft complete report ...", run_in_background=false) -> version1.md
Task(subagent_type="general-purpose", prompt="Draft complete report ...", run_in_background=false) -> version2.md
Task(subagent_type="general-purpose", prompt="Draft complete report ...", run_in_background=false) -> version3.md

Write drafts to files, not conversation context:

<output_dir>/intermediate/<topic-name>/version1.md
<output_dir>/intermediate/<topic-name>/version2.md
<output_dir>/intermediate/<topic-name>/version3.md

Step 7: UNION Merge and Format Compliance

Merge using UNION, never remove content without evidence-based justification:

Keep all unique findings from all versions
Consolidate duplicates while preserving the most detailed phrasing
Ensure every claim in the merged draft has a cited source
Enforce the exact section order, headings, and formatting
Re-run formatting rules from references/formatting_rules.md

Step 8: Evidence and Citation Verification

Verify traceability:

Every numeric claim has at least one source
Every recommendation references supporting evidence
No orphan claims without citations
Dates and time ranges are consistent
Conflicts are explicitly called out with both sources

Use references/completeness_review_checklist.md.

Step 9: Present Draft for Human Review and Iterate

Present the draft as a reviewable version:

Emphasize that format compliance and factual accuracy need human review
Accept edits to format, structure, and scope
If the user provides another AI output, cross-compare and UNION merge

Output Requirements

Match the requested language and tone
Preserve technical terms in English
Respect the report spec and formatting rules
Include a references section or bibliography

Reference Files

File	When to Load
research_report_template.md	Build outline and draft structure
formatting_rules.md	Enforce section formatting and citation rules
source_quality_rubric.md	Score and triage sources
research_plan_checklist.md	Build research plan and query set
completeness_review_checklist.md	Review for coverage, citations, and compliance

Anti-Patterns

Single-pass drafting without parallel complete passes
Splitting passes by section instead of full report drafts
Ignoring the format contract or user template
Claims without citations or evidence table mapping
Mixing conflicting dates without calling out discrepancies
Copying external AI output without verification
Deleting intermediate drafts or raw research outputs

Weekly Installs

175

Repository

daymade/claude-…e-skills

GitHub Stars

708

First Seen

Jan 25, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykWarn

Installed on

claude-code158

opencode150

gemini-cli148

codex141

cursor134

antigravity112

AI 代码实施计划编写技能 | 自动化开发任务分解与 TDD 流程规划工具

49,000 周安装