Agent skill

Fin Brief Generator

by csmar432 in csmar432/finai-research

根据用户输入或已有研究输出(文献综述/想法报告/新颖性报告),自动生成或更新FINBRIEF.md,减少用户填写负担. An agent skill from csmar432/finai-research.

MITAuto-check passedResearch & Science

Install Fin Brief Generator

skills CLI
$ npx skills add csmar432/finai-research --skill fin-brief-generator -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install csmar432/finai-research fin-brief-generator --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/csmar432/finai-research.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/fin-brief-generator .claude/skills/fin-brief-generator && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
fin-brief-generator
GitHub stars
109
Token cost
~1.7k tokens
SKILL.md length
108 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

根据用户输入或已有研究输出(文献综述/想法报告/新颖性报告),自动生成或更新FINBRIEF.md,减少用户填写负担. An agent skill from csmar432/finai-research.

  • Works in 5 steps: 推理优先 — 有现有输出时,自动推断而非重复询问 → 最小输入 — 问卷只问必要信息,其他自动推断 → 版本备份 — 每次更新前备份旧版本 → …
  • Tasks that involve Econometrics and empirical research
  • SKILL.md covers 触发条件, 三种工作模式, FIN_BRIEF.md 结构 and 时间线, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Fin Brief Generator is an agent skill from csmar432/finai-research. 根据用户输入或已有研究输出(文献综述/想法报告/新颖性报告),自动生成或更新FINBRIEF.md,减少用户填写负担。

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science, covering Econometrics and empirical research. The repository describes itself as: Evidence-first AI workflow for economic and financial research: literature → identification → data → econometrics → verifiable LaTeX. 43 data sources, 58 method modules, 18 AI… The licence is MIT.

When your agent uses it

  • Tasks that involve Econometrics and empirical research

Example prompts

  • “/fin-brief-generator”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. 推理优先 — 有现有输出时,自动推断而非重复询问
  2. 最小输入 — 问卷只问必要信息,其他自动推断
  3. 版本备份 — 每次更新前备份旧版本
  4. 字段验证 — 期刊名必须匹配已知列表
  5. 行为控制必填 — AUTO_PROCEED 等字段不能留空

What it can do on your machine

Read from SKILL.md and the folder at commit 47eebb7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are python, markdown and yaml).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Fin Brief Generator loads about 1.7k tokens when it runs. Until then it costs about 20 tokens; SKILL.md has 108 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~20
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from csmar432/finai-research at commit 47eebb7, republished under its MIT licence (© csmar432). 108 words, ~1,720 tokens.

Download SKILL.mdSave it as .claude/skills/fin-brief-generator/SKILL.md (or your agent's skills folder).
name
fin-brief-generator
description
根据用户输入或已有研究输出(文献综述/想法报告/新颖性报告),自动生成或更新FIN_BRIEF.md,减少用户填写负担。
trigger
生成简报|FIN_BRIEF|brief|研究简报|简报
version
1.0.0
created
2026-06-13
tags
brief, research, metadata, outline, generator

fin-brief-generator

根据用户输入或已有研究输出(文献综述/想法报告/新颖性报告),自动生成或更新FIN_BRIEF.md,减少用户填写负担。

触发条件

  • 关键词: 生成简报 FIN_BRIEF brief 研究简报 简报 研究概要
  • Skill语法: Skill: fin-brief-generator
  • 前置条件: 可选 — 已有研究输出文件

三种工作模式

模式一:推理模式 (Inference Mode)

当项目中已有研究输出文件时,从现有文件中自动推断字段值。

输入文件优先级:

1. output/fin-literature/LIT_REVIEW.md       → 提取研究领域、方法、文献缺口
2. output/fin-ideas/IDEA_REPORT.md           → 提取候选想法、评分
3. output/fin-novelty/NOVELTY_REPORT.md      → 提取定位策略
4. output/fin-refinement/REFINED_DESIGN.md  → 提取研究设计细节

执行流程:

python
from scripts.brief_generator import BriefGenerator, InferenceMode

generator = BriefGenerator(project_root=".")

# 推理模式:从现有文件推断
brief = generator.generate_from_outputs(mode=InferenceMode)

# 仅向用户展示未知字段
unknown_fields = brief.get_unknown_fields()
print(f"需要您补充 {len(unknown_fields)} 个字段:")
for field in unknown_fields:
    print(f"  - {field}")

示例:

已推断字段: 12/17
- 研究主题: 碳排放权交易对企业绿色创新的影响 ✅
- 因果推断方法: 双重差分法 (DID) ✅
- 目标期刊: 经济研究 ✅

需补充字段: 5/17
- 主要作者: ?
- 协作者: ?
- 资助机构: ?
- 文献综述截止日期: ?
- 初稿截止日期: ?
模式二:问卷模式 (Questionnaire Mode)

当有部分信息时,通过结构化问卷收集缺失信息。

问卷流程:

python
from scripts.brief_generator import QuestionnaireMode

generator = BriefGenerator(project_root=".")

# 运行问卷
answers = generator.run_questionnaire(
    questions=[
        {
            "id": "topic",
            "question": "研究主题是什么?请用一句话描述",
            "type": "text",
            "required": True,
        },
        {
            "id": "journal",
            "question": "目标期刊是哪个?",
            "type": "choice",
            "options": ["JF", "JFE", "RFS", "经济研究", "金融研究", "管理世界", "其他"],
            "required": True,
        },
        {
            "id": "data_source",
            "question": "主要数据来源是什么?",
            "type": "choice",
            "options": ["Tushare/A股", "CSMAR", "Wind", "Yfinance/美股", "手动收集", "其他"],
            "required": True,
        },
        {
            "id": "method",
            "question": "有偏好的研究方法吗?",
            "type": "choice",
            "options": ["DID", "IV/2SLS", "RDD", "合成控制", "PSM", "面板GMM", "无偏好"],
            "required": False,
        },
    ],
    interactive=True,  # 对话式问卷
)

问卷示例对话:

问: 研究主题是什么?请用一句话描述
答: 碳排放权交易试点对企业绿色创新的影响

问: 目标期刊是哪个?
答: 经济研究

问: 主要数据来源是什么?
答: Tushare/A股

问: 有偏好的研究方法吗?
答: DID
模式三:快速问答模式 (Quick Q&A Mode)

从零开始,单次对话收集最基本信息,立即生成简报。

python
from scripts.brief_generator import QuickQAMode

# 快速问答 — 仅3个核心问题
generator = QuickQAMode()

brief = generator.generate(
    topic="碳排放权交易对企业绿色创新的影响",
    journal="经济研究",
    authors="张三",
)

FIN_BRIEF.md 结构

生成的文件结构如下:

markdown
# 研究简报 (FIN_BRIEF)

> 生成时间: 2026-06-13
> 版本: 1.0.0
> 状态: draft | in_progress | completed

---

## 基本信息

- **研究主题**: [topic]
- **目标期刊**: [journal]
- **研究类型**: [实证研究/综述/方法论/案例研究]
- **语言**: [中文/英文/双语]
- **预估字数**: [字数] 字

## 研究团队

- **主要作者**: [name]
- **协作者**: [names]
- **资助机构**: [funding]
- **伦理审批**: [IRB approval if applicable]

## 研究设计

- **因果推断方法**: [DID/IV/RDD/合成控制/PSM/面板GMM/其他]
- **识别策略**: [描述识别策略]
- **样本期间**: [start_year] - [end_year]
- **样本量**: [N firms/observations]
- **数据来源**:
  - [source_1]: [description]
  - [source_2]: [description]

## 变量定义

### 因变量
| 变量名 | 定义 | 数据来源 |
|--------|------|----------|
| [var_1] | [definition] | [source] |

### 自变量/核心解释变量
| 变量名 | 定义 | 数据来源 |
|--------|------|----------|
| [var_1] | [definition] | [source] |

### 控制变量
| 变量名 | 定义 | 数据来源 |
|--------|------|----------|
| [var_1] | [definition] | [source] |

## 实证方法

- **基准模型**: [模型描述]
- **固定效应**: [FE combination]
- **标准误**: [Clustering]
- **稳健性检验**: [list]
- **异质性分析**: [list]
- **机制分析**: [list]

## 行为控制

```yaml
AUTO_PROCEED: false        # 强制交互checkpoint
HUMAN_CHECKPOINT: true     # 每阶段暂停
REVIEWER_DIFFICULTY: strict # standard/strict/nightmare
LANGUAGE: zh              # zh/en/both
FALLBACK_SIMULATED_DATA: false  # 禁止静默使用模拟数据

时间线

阶段截止日期状态
文献综述[date]pending
新颖性验证[date]pending
实证设计[date]pending
数据获取[date]pending
论文写作[date]pending
初稿完成[date]pending
投稿目标[date]pending

里程碑

  • [ ] [ ] [date] 阶段1完成
  • [ ] [date] 阶段2完成
  • [date] 初稿完成

备注

[Any additional notes]


元数据

yaml
generated_by: fin-brief-generator
version: 1.0.0
created: 2026-06-13
updated: 2026-06-13
parent_outputs:
  - LIT_REVIEW.md
  - IDEA_REPORT.md
  - NOVELTY_REPORT.md
  - REFINED_DESIGN.md

## 增强工具 (2026-06)

```python
from scripts.research_framework import (
    PolicyDatabase,           # 23个中国准自然实验政策数据库
    AShareVariableFetcher,    # 8个A股特殊变量
    FinancialChartFactory,     # 20个图表模板
)

# ============ 政策数据库 ============
pd = PolicyDatabase()

# 按领域搜索政策
carbon_policies = pd.get_policies(domain="carbon")
# 返回: [Policy(id=..., name=..., year=..., description=...)]

# 按关键词搜索
matching = pd.search("绿色创新")
# 返回: [Policy(...), ...]

# 获取政策详情
detail = pd.get_policy_detail("carbon_trading_pilot")
# 返回: PolicyDetail(start_year=..., provinces=[...], intensity=...)

# ============ A股特殊变量 ============
f = AShareVariableFetcher()

# 获取研发投入强度
rd = f.get_rd_intensity(["000001.SZ", "600000.SH"], years=["2018-2022"])

# 获取ESG评分
esg = f.get_esg_rating(["000001.SZ"], source="华证")

# 获取分析师覆盖
coverage = f.get_analyst_coverage(["000001.SZ"])

# ============ 图表工厂 ============
factory = FinancialChartFactory(output_dir="figures/")

# 预设图表
fig = factory.plot("parallel_trends", df,
    time_var="year",
    treat_var="treat",
    y_var="innovation",
    save_path="figures/parallel_trends.pdf")

# 自定义图表
fig = factory.plot_custom(
    chart_type="scatter",
    data=df,
    x="size",
    y="roa",
    color="treat",
    title="企业规模与盈利能力",
    xlabel="企业规模 (对数)",
    ylabel="ROA",
)

交互流程

[模式检测] 检测到项目已有研究输出文件

检测到的文件:
✅ output/fin-literature/LIT_REVIEW.md
✅ output/fin-ideas/IDEA_REPORT.md
✅ output/fin-novelty/NOVELTY_REPORT.md

[推理模式] 正在从现有文件推断字段...

推断结果:
- 研究主题: 碳排放权交易对企业绿色创新的影响
- 目标期刊: 经济研究
- 因果推断方法: 双重差分法 (DID)
- 样本期间: 2012-2022
- 数据来源: Tushare + 手动整理碳交易数据

需要您补充:
1. 主要作者: [请输入]
2. 协作者: [请输入] (可选)
3. 资助机构: [请输入] (可选)
4. 文献综述截止日期: [请输入]
5. 初稿截止日期: [请输入]
6. 投稿目标日期: [请输入]

请回答以上问题,或输入"跳过"使用默认值。

输出文件

  • FIN_BRIEF.md — 研究简报主文件 (项目根目录)
  • FIN_BRIEF_BACKUP_v{n}.md — 每次更新的备份

依赖项

  • scripts/brief_generator.py — 简报生成器核心
  • scripts/research_framework/policy_database.py — 政策数据库
  • scripts/research_framework/asvare_variable_fetcher.py — A股变量获取
  • scripts/research_framework/fin_charts.py — 图表工厂

约束

  1. 推理优先 — 有现有输出时,自动推断而非重复询问
  2. 最小输入 — 问卷只问必要信息,其他自动推断
  3. 版本备份 — 每次更新前备份旧版本
  4. 字段验证 — 期刊名必须匹配已知列表
  5. 行为控制必填 — AUTO_PROCEED 等字段不能留空

© csmar432, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/fin-brief-generator of csmar432/finai-research.

Open the folder on GitHubat commit 47eebb7

Compare with similar skills

Fin Brief Generator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Fin Brief Generator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fin Brief Generator this skillcsmar432/finai-research109—~1.7kAutomated safety check: PassMIT
Statadylantmoore/stata-skill2911 repos~4.2kAutomated safety check: PassCustom licence
Stata C Pluginsdylantmoore/stata-skill2911 repos~5.8kAutomated safety check: PassCustom licence
Example Datasetspymc-labs/CausalPy1.2k—~587Automated safety check: PassApache-2.0
Stata AuditSepineTam/mcp-for-stata264—~1.2kAutomated safety check: PassAGPL-3.0
Stata Skill Contributordylantmoore/stata-skill2911 repos~2.4kAutomated safety check: PassCustom licence

Similar skills

  • Stata

    dylantmoore/stata-skill

    Comprehensive Stata reference for writing correct .do files, data management, econometrics, causal inference, graphics, Mata programming, and 20 community packages (reghdfe, estout, did, rdrobust…

    291 GitHub starsUsed in 1 repo~4.2k tokens
    Research & ScienceAuto-check passed
  • Stata C Plugins

    dylantmoore/stata-skill

    Develop high-performance C/C++ plugins for Stata using the stplugin.h SDK.

    291 GitHub starsUsed in 1 repo~5.8k tokens
    Research & ScienceAuto-check passed
  • Example Datasets

    pymc-labs/CausalPy

    Load built-in CausalPy example datasets for demos, tutorials, tests, and quick causal-analysis prototypes.

    1.2k GitHub stars~587 tokensUpdated yesterday
    Research & ScienceAuto-check passed
  • Stata Audit

    SepineTam/mcp-for-stata

    Inspect, validate, summarize, and render local Stata-MCP audit evidence under .statamcp.

    264 GitHub stars~1.2k tokensUpdated 4 days ago
    Research & ScienceAuto-check passed
  • Stata Skill Contributor

    dylantmoore/stata-skill

    Guide for contributing to the stata-skill project. An agent skill from dylantmoore/stata-skill.

    291 GitHub starsUsed in 1 repo~2.4k tokens
    Research & ScienceAuto-check passed
  • Diagnostic Dofile

    SepineTam/mcp-for-stata

    A skill your agent uses when the user needs to inspect, audit, or diagnose the safety of a Stata do-file.

    264 GitHub stars~1.2k tokensUpdated 4 days ago
    Research & ScienceAuto-check passed

More from csmar432/finai-research

All 15 skills in this repo
  • Fin Arch Diagram

    csmar432/finai-research

    生成研究/项目架构图、流程图、层次图(swimlane / processflow / hierarchytree)。适合 PPT 汇报、技术文档、综述插图。输出风格接近 draw.io,可选 graphviz(高质量)/ matplotlib(零依赖)双后端。

    109 GitHub stars~1.5k tokensUpdated 5 days ago
    Auto-check passed
  • Fin Data Acquisition

    csmar432/finai-research

    根据REFINEDDESIGN.md中的变量定义,自动获取所需数据并生成可执行的回归分析脚本(Python/Stata)。

    109 GitHub stars~2k tokensUpdated 5 days ago
    Auto-check passed
  • Fin Experiment Design

    csmar432/finai-research

    经济金融实证方法设计。根据研究想法和REFINEDDESIGN.md,生成完整的实证研究设计方案,覆盖识别策略选择、样本构建、变量定义、稳健性检验清单和内生性处理方案。

    109 GitHub stars~4.2k tokensUpdated 5 days ago
    Auto-check passed
  • Fin Generate Idea

    csmar432/finai-research

    针对经济金融研究方向的创意生成与评估。生成8-12个可发表的研究idea,过滤后在数据可行的情况下进行小规模实证验证,输出排序后的研究想法报告。

    109 GitHub stars~2.5k tokensUpdated 5 days ago
    Auto-check passed
  • Fin Idea Discovery

    csmar432/finai-research

    经济金融研究的完整想法发现流程。从研究方向出发,经过文献综述、想法生成、新颖性验证、实证方法设计和数据获取,输出经过数据实证验证的可执行研究方案。

    109 GitHub stars~2.7k tokensUpdated 5 days ago
    Auto-check passed
  • Fin Lit Review

    csmar432/finai-research

    经济金融领域的系统性文献综述。整合 Semantic Scholar + ArXiv + OpenAlex + NBER 构建引文网络,识别研究缺口,生成结构化文献地图。

    109 GitHub stars~1.2k tokensUpdated 5 days ago
    Auto-check passed

Questions about Fin Brief Generator

What does Fin Brief Generator do?

根据用户输入或已有研究输出(文献综述/想法报告/新颖性报告),自动生成或更新FINBRIEF.md,减少用户填写负担. An agent skill from csmar432/finai-research. Fin Brief Generator is an agent skill from csmar432/finai-research.

When should I use Fin Brief Generator?

Fin Brief Generator fits situations like: tasks that involve Econometrics and empirical research.

How do I install Fin Brief Generator in Claude Code?

Run `npx skills add csmar432/finai-research --skill fin-brief-generator -a claude-code`. Or copy the skill folder (.agents/skills/fin-brief-generator in csmar432/finai-research) into .claude/skills/fin-brief-generator in your project. Claude Code loads it when a task matches its description.

How do I install Fin Brief Generator in Codex?

Run `npx skills add csmar432/finai-research --skill fin-brief-generator -a codex`. Or copy the skill folder (.agents/skills/fin-brief-generator in csmar432/finai-research) into .agents/skills/fin-brief-generator in your project. Codex loads it when a task matches its description.

Can I use Fin Brief Generator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add csmar432/finai-research --skill fin-brief-generator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fin-brief-generator, .gemini/skills/fin-brief-generator, .github/skills/fin-brief-generator and .opencode/skills/fin-brief-generator in your project.

What does Fin Brief Generator need to run?

SKILL.md names no scripts, command-line tools or credentials: Fin Brief Generator is instructions for the agent only. Our summary lists: Python 3.

Does Fin Brief Generator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Fin Brief Generator safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Fin Brief Generator use?

Fin Brief Generator is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Fin Brief Generator use?

About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Fin Brief Generator?

Skills that share tags, products or a category with Fin Brief Generator: Stata (dylantmoore/stata-skill, 291 stars), Stata C Plugins (dylantmoore/stata-skill, 291 stars), Example Datasets (pymc-labs/CausalPy, 1.2k stars) and Stata Audit (SepineTam/mcp-for-stata, 264 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fin Brief Generator?

csmar432 (a GitHub user) maintains it in csmar432/finai-research, which has 109 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 6, 2026.

Source: csmar432/finai-research on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.