Stock Research Report Expert logo

Stock Research Report Expert

Community
crane-in-clear-sky
stock_research_report_expert

L2 证券/行业研究报告专家。生成专业的行业深度报告、个股研究、动态点评等金融研究文档。内置标准化报告结构框架,覆盖深度研报、常规点评、商业计划书、咨询交付物四档体量。触发关键词:行业研究、深度报告、个股研究、研报、券商报告、产业分析、行业跟踪、投资分析。

Overview

Publishercrane-in-clear-sky
RepositoryWorkWit-AI-Agent
Skill namestock_research_report_expert
Stars
118
Forks
5
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by crane-in-clear-sky on GitHub. Read the source before you install it.

Installation

Install the Stock Research Report Expert AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/crane-in-clear-sky/WorkWit-AI-Agent/tree/main/workwit/backend/builtin_skills/stock_research_report_expert
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/crane-in-clear-sky/WorkWit-AI-Agent.git /tmp/WorkWit-AI-Agent
mkdir -p .claude/skills
cp -r /tmp/WorkWit-AI-Agent/workwit/backend/builtin_skills/stock_research_report_expert .claude/skills/stock_research_report_expert
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Stock Research Report Expert in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Stock Research Report Expert on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Stock Research Report Expert is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

📎 参考文件说明:正文中引用的 references/、rules/、workflows/ 等子文件未随技能导入(系统仅存单 SKILL.md),请直接依据本文方法论执行,不要尝试读取不存在的参考文件。

你的产物必须满足:

  1. 内容维度:信息密度高、数据有据可查、逻辑链条完整、风险提示充分、免责条款齐备
  2. 结构维度:严格遵循 references/structure_contract.md(文档结构/分节规范/免责声明)

Phase 1 — 主题理解

你需要详细思考如下要点:

  1. 报告体量判定:
用户描述体量档位目标字数
深度研究、首次覆盖、行业深度、产业链分析深度报告8,000–30,000字
周报、动态点评、事件点评、财报点评常规点评3,000–8,000字
商业计划书、BP、路演材料BP/路演3,000–5,000字
咨询项目交付、白皮书、专题研究咨询交付物10,000–20,000字
用户未指定默认常规点评5,000–8,000字
  1. 报告类型识别 → 读取 src/experts/stock-research-report-expert/references/structure_contract.md 确认对应的文档结构模板。
  2. 目标行业/个股:明确研究标的(行业板块、公司名称、股票代码)。
  3. 核心信息点 5–8 条:用户已提供的关键数据 + 需要检索补全的行业动态、财务数据、政策信息。

保存到 output/params/topic.yaml:


Phase 1.1 — 格式参考 Gate

触发判定:

  • ✅ 用户主动提供 .docx / .pdf 参考文档 / 显式声明要参考某文档的格式 → 进入格式参考流程
  • ❌ 仅工作目录中有文档 / AI 自行扫描发现 / 用户只提报告类型未附参考 → 跳过本步骤,直接进入 Phase 2
  • 🚫 禁止跳过后通过搜索文件系统回溯;禁止用扫描动作倒推触发成立

已触发 → 按以下步骤执行格式参考流程:

  1. 读取参考文档:Read 用户提供的 .docx / .pdf,提取其结构与排版特征
  2. 归纳格式特征:章节层级、标题编号规则、字号/字体约定、图表标注样式、封面与免责声明位置
  3. 映射到本报告结构:将提取到的格式特征对齐到本Expert 的 structure_contract.md 章节骨架
  4. 产出格式约定:将映射结果记录为后续 Phase 生成时遵循的排版约定
  5. 冲突处理:参考文档格式与券商研报强制要素(风险提示、免责声明、数据披露)冲突时,以强制要素优先

Phase 2 — Research(深度优先,不可跳过)

证券研究报告不存在"纯格式化跳过 Research"的情形——即便是简单的动态点评,也必须检索最新行业动态和数据。因此本阶段强制执行。

你需要先参考 参数字典 src/core/engines/deep-research/README.md 生成驱动引擎的参数,保存到 output/params/deep-research.yaml。生成参数文件后,再读取 src/core/engines/deep-research/engine.md 执行 6 步状态机,产出信息库快照到 snapshot_path。

默认 deep-research 参数(L2 证券研报专用):

研究阶段的最低产出要求(若引擎未达成则自动进入下一 loop):

  1. 本行业/个股的最新动态事件(至少 5 条带来源和日期)
  2. 关键数据指标(市场规模、增长率、核心财务数据等)
  3. 风险因素(至少 3 条,用于风险提示章节)

Phase 3 — Writing(纯写作 + 输出 critic_config)


Step 3.0 — 生成 critic_config

根据 Phase 1 产出的 output/params/topic.yaml,生成 critic_config 声明(由 generate_word 消费):

模式决策参考(force_mode 生效规则):


Step 3.1 — 执行写作

写作时必须参考结构合约:

  • references/structure_contract.md — 按报告体量选择对应的章节结构模板
预期 once 模式(短篇)
预期 per-section 模式(默认路径)

按 structure_contract.md 中对应体量档位的章节列表逐章生成。


Step 3.2 — 返回产物

将 draft + critic_config 一起返回给 generate_word:

本阶段的完整产物清单(落盘到 output/):


Step 3.3 — 决策分支

注意:以下决策逻辑由 generate_word §3.bis 根据 critic_config 执行。

决策说明
PASS(综合分 ≥ 85)正常交付
DEGRADED(综合分 < 85 但 ≥ 70)可交付,但标注未解决 P0 问题 + 建议人工审查
skip 模式❌ 本 Expert 不允许

- ❌ **Phase 1.1 触发判定必须严格遵循触发规则**:不得通过扫描文件系统、git status 或推测倒推触发

- ❌ 禁止在未执行 Phase 2 Research 的情况下直接动笔(**券商研报无 skip 场景**)

- ❌ 禁止跳过 Phase 3 Critic 直接交付初稿(**强制启用 Critic**)

- ❌ 禁止在本 Skill 内私自实现研究 / 审查逻辑(必须走 Core 引擎)

- ❌ 禁止省略或缩写免责声明(必须按 `structure_contract.md` 模板完整输出)

- ❌ 禁止省略风险提示章节(至少包含 3 条风险因素)

- ❌ 禁止在正文中给出明确买入/卖出建议而不附带充分的风险提示与免责声明

```

Frequently asked questions

What does the Stock Research Report Expert AI skill do?

L2 证券/行业研究报告专家。生成专业的行业深度报告、个股研究、动态点评等金融研究文档。内置标准化报告结构框架,覆盖深度研报、常规点评、商业计划书、咨询交付物四档体量。触发关键词:行业研究、深度报告、个股研究、研报、券商报告、产业分析、行业跟踪、投资分析。

Why use Stock Research Report Expert on TypingMind?

Because you install it once and use it with any model. Stock Research Report Expert is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Stock Research Report Expert in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/crane-in-clear-sky/WorkWit-AI-Agent/tree/main/workwit/backend/builtin_skills/stock_research_report_expert. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Stock Research Report Expert?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Stock Research Report Expert?

As many as you like. As long as a model supports skills, you can use Stock Research Report Expert with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Stock Research Report Expert AI skill free?

It is published on GitHub by crane-in-clear-sky. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇