Agent skill

Financial Report Analyst

by digoal in digoal/blog

深度解读企业财报,将财报 PDF 或 URL 转化为面向普通投资者的专业分析报告,以 Markdown 格式保存到当前项目的 markdown/ 目录。

GPL-2.0Auto-check passedDocuments & Office

Install Financial Report Analyst

skills CLI
$ npx skills add digoal/blog --skill financial-report-analyst -a claude-code

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

GitHub CLI
$ gh skill install digoal/blog financial-report-analyst --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/digoal/blog.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skills_for_claude_web/financial-report-analyst .claude/skills/financial-report-analyst && 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
financial-report-analyst
GitHub stars
8.6k
Token cost
~920 tokens
SKILL.md length
217 words
Files
2 (incl. references)
Skills in repo
98
Repo updated
First seen
Licence
GPL-2.0

At a glance

深度解读企业财报,将财报 PDF 或 URL 转化为面向普通投资者的专业分析报告,以 Markdown 格式保存到当前项目的 markdown/ 目录。

  • Works in 8 steps: 获取财报 → 结构化信息提取 → 八大"坑位"排查 → …
  • Tasks that involve Financial analysis
  • SKILL.md covers Step 0 — 获取财报, Step 1 — 结构化信息提取, Step 2 — 八大"坑位"排查 and Step 3 — 行业竞争格局 & 护城河评估, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Financial Report Analyst is an agent skill from digoal/blog. 深度解读企业财报,将财报 PDF 或 URL 转化为面向普通投资者的专业分析报告,以 Markdown 格式保存到当前项目的 markdown/ 目录。 触发条件:用户上传或提供财报 PDF、提到"分析财报"/"读财报"/"解读财报"/"看看这家公司"/"帮我分析一下 XX 公司",或任何需要深入理解一份财务报告的场景。 输出一份犀利、有逻辑支撑的投资参考报告,涵盖:核心收入分析、财务健康诊断、隐蔽风险雷区排查、行业竞争格局、前瞻性估值,以及明确的投资参考建议。 即使用户只说"帮我看这份年报"但内容是财报,也应使用本 skill。

Its SKILL.md is about 920 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/advanced-frameworks.md`).

It sits in Documents & Office, covering Financial analysis, PDF and Markdown. The repository describes itself as: AI,Opensource,Database,Business,Finance,Minds. git clone --depth 1 https://github.com/digoal/blog. The licence is GPL-2.0.

When your agent uses it

  • Tasks that involve Financial analysis
  • Tasks that involve PDF
  • Tasks that involve Markdown

Example prompts

  • “看看这家公司”
  • “帮我分析一下 XX 公司”
  • “帮我看这份年报”
  • “/financial-report-analyst”

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. 获取财报
  2. 结构化信息提取
  3. 八大"坑位"排查
  4. 行业竞争格局 & 护城河评估
  5. 前瞻性关键问题拆解
  6. 估值分析
  7. 投资参考建议
  8. 输出文件

What it can do on your machine

Read from SKILL.md and the folder at commit ad6fcb7. 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 bash and markdown).

    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

Financial Report Analyst loads about 920 tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 73 tokens; SKILL.md has 217 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~73
When it runs · the whole SKILL.md, loaded when a task matches
~920
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.4k

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 digoal/blog at commit ad6fcb7, republished under its GPL-2.0 licence (© digoal). 217 words, ~920 tokens.

Download SKILL.mdSave it as .claude/skills/financial-report-analyst/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
financial-report-analyst
description
深度解读企业财报,将财报 PDF 或 URL 转化为面向普通投资者的专业分析报告,以 Markdown 格式保存到当前项目的 markdown/ 目录。 触发条件:用户上传或提供财报 PDF、提到"分析财报"/"读财报"/"解读财报"/"看看这家公司"/"帮我分析一下 XX 公司",或任何需要深入理解一份财务报告的场景。 输出一份犀利、有逻辑支撑的投资参考报告,涵盖:核心收入分析、财务健康诊断、隐蔽风险雷区排查、行业竞争格局、前瞻性估值,以及明确的投资参考建议。 即使用户只说"帮我看这份年报"但内容是财报,也应使用本 skill。

Financial Report Analyst — 财报深度解读技能

你将扮演资深财务分析师 + 基金经理 + 投行研究员三位一体的角色,以专业视角、犀利观点,为普通投资者解读财报。

核心原则:观点要有前提假设,结论要有权威数据支撑,不以个例以偏概全。前提假设崩塌时,主动引出替代观点。


Step 0 — 获取财报

  • 若用户提供 URL:用 web_fetch 抓取,或从 SEC EDGAR / 港交所披露易 / 巨潮资讯 等数据源获取原始 PDF。
  • 若用户提供 PDF 文件:读取 /mnt/user-data/uploads/ 下的文件,参考 pdf-reading skill。
  • 若只提供公司名:搜索其最新年报/季报的官方 PDF 链接,再 fetch。

Step 1 — 结构化信息提取

阅读财报时,按以下优先级提取数据,先看附注,再看正文:

1.1 基础财务数据
科目本期上期YoY%
营业收入
毛利润 / 毛利率
营业利润 / 营业利润率
归母净利润
经营活动现金流净额(OCF)
自由现金流(FCF = OCF - Capex)
资产负债率
货币资金
1.2 收入结构拆分
  • 各业务线 / 产品线的营收占比及增速
  • 地理区域拆分(国内 vs 海外)
  • 一次性收入 vs 经常性收入(订阅/服务)
1.3 现金流质量检验
  • OCF / 净利润 ratio(>1 为优质,<0.5 需警惕)
  • Capex 强度(Capex / 营收)
  • FCF margin

Step 2 — 八大"坑位"排查

依次排查以下风险,每项给出明确结论(✅ 未见异常 / ⚠️ 需关注 / 🚨 重大风险):

坑 1:纸面富贵(应收账款陷阱)
  • 应收账款增速 vs 营收增速
  • OCF 是否持续为负
  • 账龄分析:1 年以上欠款占比趋势
坑 2:垃圾资产(存货 & 应收爆棚)
  • 存货周转率趋势
  • 存货减值计提是否充分
  • 应收账款坏账拨备率
坑 3:财务黑盒(其他应收款 & 预付款)
  • 其他应收款 / 总资产 是否 >5%
  • 关联方交易披露是否充分
坑 4:商誉雷区
  • 商誉 / 净资产 是否 >30%
  • 被收购标的业绩承诺完成情况
坑 5:大存大贷
  • 货币资金 vs 短期借款同时高企的逻辑自洽性
  • 是否有资产质押/冻结披露
坑 6(隐蔽):研发资本化
  • 研发支出资本化比例 vs 同行
  • 开发支出余额趋势
坑 7(隐蔽):折旧政策微调
  • 固定资产折旧年限是否变更(藏在"会计政策变更"附注)
  • 变更影响净利润的量化估算
坑 8(隐蔽):联营企业 & 洗大澡
  • 长期股权投资规模 + 投资收益率
  • 当年大额减值是否有"洗大澡"迹象(管理层换届背景下)

Step 3 — 行业竞争格局 & 护城河评估

  • 定价权:毛利率趋势是否反映竞争加剧/减弱?
  • 市场份额:营收增速 vs 行业增速(超越 = 抢份额,落后 = 失份额)
  • 护城河类型:品牌、成本、网络效应、转换成本、规模壁垒,各给出1-10分评分并说明理由
  • 主要竞争对手对比:至少列出3家,关键指标横向对比

Step 4 — 前瞻性关键问题拆解

根据公司业务特点,从以下维度提出并分析关键问题(每个公司必选3-5个,结合财报数据给出答案或推断):

收入转型维度

  • 高毛利业务(软件/服务/订阅)的渗透率拐点在哪里?
  • 新业务线从"烧钱"到"毛利转正"的时间节点?

盈利质量维度

  • 下一代产品/平台的单位成本目标能否兑现?
  • 新产品线对整体毛利率的拖累何时消除?

研发 & 技术维度

  • 重大资本开支(Capex)的投入产出比(ROI)如何评估?
  • 核心技术突破距商业化落地还有多远?

风险维度

  • 地缘政治/监管/汇率对供应链和市场准入的影响量化估算
  • 核心监管批准的法律时间表是否明确?

Step 5 — 估值分析

5.1 当前估值水位
  • P/E、P/S、EV/EBITDA、P/FCF 当前值 vs 历史均值 vs 行业均值
  • 结论:低估 / 合理 / 高估,以及溢价/折价的合理解释
5.2 情景分析(Bull / Base / Bear)

对核心假设变量(增速、毛利率、渗透率等)设定三种情景,给出对应目标市值和股价区间。

5.3 新业务估值重构(如适用)

若公司存在变革性新业务(如从卖硬件转向订阅、租赁、AI服务),需单独建立分部估值(Sum-of-the-Parts):

  • 传统业务:用 DCF 或同业 P/E
  • 新业务:用增长调整后的 P/S 或 EV/Revenue

Step 6 — 投资参考建议

以下为必须输出的结构,语气要犀利、明确,不做墙头草:

## 🎯 投资参考建议

**综合评级**:[强烈买入 / 买入 / 中性持有 / 卖出 / 强烈卖出]

**核心投资逻辑**(2-3条,每条须有数据支撑):
1. ...
2. ...

**主要风险**(2-3条,量化影响):
1. ...
2. ...

**触发上行的催化剂**:
- ...

**触发下行的警报信号**:
- ...

**建议持仓周期**:[短期(<1年) / 中期(1-3年) / 长期(>3年)]

**前提假设**:本建议基于 [核心假设]。若 [假设崩塌条件],则上述逻辑不成立,
届时应重新评估。替代观点:[反向论点]。

Step 7 — 输出文件

创建目录并保存:

bash
mkdir -p markdown/

文件命名:markdown/{公司名}_{报告期}_财报深度解读.md

输出 Markdown 结构模板
markdown
# {公司名} {报告期} 财报深度解读

> 解读日期:{今天日期} | 数据来源:{财报原始文件}

## 执行摘要(TL;DR)
[3-5句话,直接给出最重要结论]

## 一、核心财务数据速览
[Step 1 的表格]

## 二、收入结构解剖
[Step 1.2 详细拆解]

## 三、财务健康诊断
### 现金流质量
### 资产负债健康度

## 四、八大风险坑位扫描
[Step 2 的排查结果,每项给出结论 ✅/⚠️/🚨]

## 五、行业竞争格局
[Step 3]

## 六、前瞻性关键问题
[Step 4,Q&A 形式,每问有推断结论]

## 七、估值分析
[Step 5]

## 八、投资参考建议
[Step 6 的完整结构]

## 附:数据来源与免责声明
本报告基于公开财报数据,不构成投资建议。投资者需自行承担决策风险。

风格规范

  • 语气:专业但不晦涩,犀利但不哗众取宠
  • 数据:每个观点必须附数字/比例,不允许只说"大幅增长"之类的模糊表述
  • 对比:尽量引用同行数据或历史均值做锚定
  • 假设透明:预测类结论必须标注前提假设,并给出假设崩塌后的替代视角
  • 立场明确:必须给出明确的投资倾向,不做"一方面…另一方面…"的骑墙表述
  • 篇幅:完整报告不低于 3000 字,核心数据齐全时可达 5000-8000 字

© digoal, GPL-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/skills_for_claude_web/financial-report-analyst of digoal/blog.

  • SKILL.md
  • references/advanced-frameworks.md

Open the folder on GitHubat commit ad6fcb7

Compare with similar skills

Financial Report Analyst 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.

Financial Report Analyst compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Financial Report Analyst this skilldigoal/blog8.6k—~920Automated safety check: PassGPL-2.0
Minesweeperterancejiang/financial-report-minesweeper431—~3.6kAutomated safety check: PassNone
MarkitdownImCa0/just-laws78114 repos~3.2kAutomated safety check: NotesMIT
Doc Cleanernotoriouslab/doc-cleaner309—~712Automated safety check: PassMIT
Ky Markdown RebuilderKyrieCheungYep/ky-markdown-rebuilder117—~5.7kAutomated safety check: PassNone
MineruNebutra/MinerU-Skill123—~504Automated safety check: PassMIT

Similar skills

  • Minesweeper

    terancejiang/financial-report-minesweeper

    财报排雷工具 (Financial Report Minesweeper). An agent skill from terancejiang/financial-report-minesweeper.

    431 GitHub stars~3.6k tokensUpdated 5 mo ago
    Documents & OfficeAuto-check passed
  • Markitdown

    ImCa0/just-laws

    Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.

    781 GitHub starsUsed in 14 repos~3.2k tokens
    Documents & OfficeAuto-check: notes
  • Doc Cleaner

    notoriouslab/doc-cleaner

    Convert PDF, DOCX, XLSX, and text files to clean, structured Markdown.

    309 GitHub stars~712 tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed
  • Ky Markdown Rebuilder

    KyrieCheungYep/ky-markdown-rebuilder

    Rebuild visual documents into reliable Markdown by combining text extraction with page or screenshot alignment.

    117 GitHub stars~5.7k tokensUpdated 3 mo ago
    Documents & OfficeAuto-check passed
  • Mineru

    Nebutra/MinerU-Skill

    An AI-Native skill for parsing PDF / Office / image files into Markdown with MinerU — a fast, zero-config document parser for AI agents.

    123 GitHub stars~504 tokensUpdated 16 days ago
    Documents & OfficeAuto-check passed
  • Skill Doc Delivery

    nyldn/claude-octopus

    Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables

    4.2k GitHub starsUsed in 1 repo~2.4k tokens
    Documents & OfficeAuto-check passed

More from digoal/blog

All 98 skills in this repo
  • 三层审查模型,逐段逐句验证文章真伪、证据链与逻辑结构。Use when the user asks to fact-check, verify, audit, or evaluate the credibility of an article, essay, report, opinion piece, social-media post, or any written claim —…

    8.6k GitHub stars~939 tokensUpdated yesterday
    Auto-check passed
  • Find latent bugs in a local PostgreSQL source tree (RELxxSTABLE branch or HEAD) the way a core hacker does: build a heavily-poisoned debug instance (cassert + cache-discard + -O0/-ggdb3 + core…

    8.6k GitHub stars~4k tokensUpdated yesterday
    Auto-check passed
  • Digoal

    digoal/blog

    Portable digital employee distilled from digoal's personal blog for PostgreSQL, PolarDB, DuckDB, AI+database, vector/RAG, database operations, source-code reading, technical content creation…

    8.6k GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed
  • 从论文 PDF 文件或论文 PDF URL 生成通俗易懂、图文并茂、带批判性评估的中文 Markdown 解读,并保存到当前项目的 markdown 目录。Use when the user asks to interpret,精读,解读,summarize,explain,analyze, or write an article from an academic paper PDF…

    8.6k GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed
  • Analyze a product from documentation, websites, PDFs, articles, release notes, pricing pages, app listings, reviews, filings, or related links; save separate intermediate analyses from seven roles…

    8.6k GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed
  • Turn a blog post, article, notes, or any source material into a set of vertical poster images — one cover plus several coherent content slides that explain the core points.

    8.6k GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

Questions about Financial Report Analyst

What does Financial Report Analyst do?

深度解读企业财报,将财报 PDF 或 URL 转化为面向普通投资者的专业分析报告,以 Markdown 格式保存到当前项目的 markdown/ 目录。. Financial Report Analyst is an agent skill from digoal/blog.

When should I use Financial Report Analyst?

Financial Report Analyst fits situations like: tasks that involve Financial analysis; tasks that involve PDF; tasks that involve Markdown.

How do I install Financial Report Analyst in Claude Code?

Run `npx skills add digoal/blog --skill financial-report-analyst -a claude-code`. Or copy the skill folder (skills/skills_for_claude_web/financial-report-analyst in digoal/blog) into .claude/skills/financial-report-analyst in your project. Claude Code loads it when a task matches its description.

How do I install Financial Report Analyst in Codex?

Run `npx skills add digoal/blog --skill financial-report-analyst -a codex`. Or copy the skill folder (skills/skills_for_claude_web/financial-report-analyst in digoal/blog) into .agents/skills/financial-report-analyst in your project. Codex loads it when a task matches its description.

Can I use Financial Report Analyst 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 digoal/blog --skill financial-report-analyst -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/financial-report-analyst, .gemini/skills/financial-report-analyst, .github/skills/financial-report-analyst and .opencode/skills/financial-report-analyst in your project.

What does Financial Report Analyst need to run?

SKILL.md names no scripts, command-line tools or credentials: Financial Report Analyst is instructions for the agent only.

Does Financial Report Analyst 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 Financial Report Analyst 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 Financial Report Analyst use?

Financial Report Analyst is published under the GPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Financial Report Analyst use?

About 920 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.5k tokens, read only when the agent opens those files.

What are the alternatives to Financial Report Analyst?

Skills that share tags, products or a category with Financial Report Analyst: Minesweeper (terancejiang/financial-report-minesweeper, 431 stars), Markitdown (ImCa0/just-laws, 781 stars), Doc Cleaner (notoriouslab/doc-cleaner, 309 stars) and Ky Markdown Rebuilder (KyrieCheungYep/ky-markdown-rebuilder, 117 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Financial Report Analyst?

digoal (a GitHub user) maintains it in digoal/blog, which has 8,588 GitHub stars. The repository holds 98 skills in this directory. The repository was last updated on October 9, 2026.

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