Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Geeksfino/finskills --skill financial-statement-analyzergit clone --depth 1 https://github.com/Geeksfino/finskillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/geeksfino/finskills/financial-statement-analyzer)<a href="https://agentmods.dev/skills/geeksfino/finskills/financial-statement-analyzer"><img src="https://agentmods.dev/badge/skills/geeksfino/finskills/financial-statement-analyzer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/geeksfino/finskills/financial-statement-analyzer"><img src="https://agentmods.dev/badge/skills/geeksfino/finskills/financial-statement-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00100 | $0.01964 |
| Opus 5 | $0.00050 | $0.00982 |
| Sonnet 5 | $0.00020 | $0.00393 |
| Haiku 4.5 | $0.00010 | $0.00196 |
Grade A, and why
financial-statement-analyzer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
财务报表深度分析
扮演法证财务分析师。对单个A股上市公司的财务报表进行全面分析，评估盈利质量、财务健康状况、财务造假风险指标和运营效率。
工作流程
第一步：确定分析对象
与用户确认：
- 公司 — 股票代码或名称
- 时间跨度 — 默认：最近5年（20个季度）
- 重点领域 — 全面分析（默认）或特定聚焦（盈利质量、造假风险、营运资本等）
- 对比公司 — 用于基准比较的主要竞争对手（可选）
- 数据来源 — 以年报、半年报、季报为主要数据源
第二步：盈利能力分解
进行5因子杜邦分析。详细公式参见 references/analysis-methodology.md。
ROE = 税负系数 × 利息负担系数 × 营业利润率 × 资产周转率 × 权益乘数
| 组成部分 | 公式 | 揭示内容 |
|---|---|---|
| 税负系数 | 净利润 / 税前利润 | 税收效率 |
| 利息负担系数 | 税前利润 / EBIT | 债务成本影响 |
| 营业利润率 | EBIT / 营业收入 | 运营效率 |
| 资产周转率 | 营业收入 / 总资产 | 资产利用效率 |
| 权益乘数 | 总资产 / 股东权益 | 财务杠杆 |
追踪各组成部分5年变化趋势，识别ROE变化的驱动因素。
第三步：盈利质量评估
评估报告盈利是否反映真实经济价值：
| 测试 | 衡量内容 | 红灯阈值 |
|---|---|---|
| 应计比率 | 非现金盈利占比 | > 总资产的10% |
| 现金转化率 | 经营现金流 / 净利润 | 持续 < 0.8 |
| 收入确认 | 收入增长 vs 应收账款增长 | 应收增速超过收入 |
| 合同负债/预收 | 合同负债趋势 | 下降（提前确认收入） |
| 非经常性项目 | 一次性收益/费用频率 | "非经常性"项目每年出现 |
| 政府补助依赖 | 政府补助占净利润比例 | > 30%（利润可持续性存疑） |
第四步：财务健康评分
计算综合财务健康指标：
| 模型 | 用途 | 组成部分 |
|---|---|---|
| Altman Z值 | 破产预测 | 营运资本、留存收益、EBIT、市值、营收——均相对于总资产 |
| Piotroski F值 | 财务实力 | 9个二元信号，涵盖盈利能力、杠杆和效率 |
| Beneish M值 | 盈利操纵检测 | 8个变量，衡量财务数据中的异常 |
详细公式和解读参见 references/analysis-methodology.md。
第五步：营运资本分析
通过现金转化周期考察运营效率：
| 指标 | 公式 | 揭示内容 |
|---|---|---|
| 应收账款周转天数（DSO） | (应收账款 / 营业收入) × 365 | 收款效率 |
| 存货周转天数（DIO） | (存货 / 营业成本) × 365 | 存货管理 |
| 应付账款周转天数（DPO） | (应付账款 / 营业成本) × 365 | 付款实践 |
| 现金转化周期 | DSO + DIO − DPO | 营运资本效率 |
追踪5年趋势并与同行比较。
第六步：资产负债表风险评估
识别表外和隐性风险：
| 风险领域 | 检查内容 |
|---|---|
| 商誉/无形资产 | 相对净资产的规模；减值风险（A股并购商誉减值是常见雷区） |
| 关联交易 | 与控股股东及关联方的交易规模和定价公允性 |
| 应收票据及应收账款 | 商业承兑汇票的信用风险 |
| 在建工程 | 长期不结转固定资产的项目（可能的费用资本化） |
| 其他应收款 | 对关联方的资金占用 |
| 股份支付 | 稀释影响 |
| 有息负债到期结构 | 短期偿债压力 vs 现金/再融资能力 |
| 股权质押 | 大股东股权质押比例 |
第七步：业务分部分析
按业务分部拆解业绩：
- 各分部营收及增长
- 各分部利润率
- 各分部资本密集度
- 识别哪些分部创造价值、哪些毁灭价值
- 分部间的交叉补贴
第八步：同行基准比较
与2–3家直接竞争对手比较关键指标：
| 指标类别 | 具体指标 |
|---|---|
| 盈利能力 | 毛利率、营业利润率、净利率、ROE、ROIC |
| 效率 | 资产周转率、存货周转率、应收周转率 |
| 杠杆 | 资产负债率、利息保障倍数、净负债/EBITDA |
| 估值 | PE、EV/EBITDA、P/FCF、PEG |
| 成长性 | 营收CAGR、EPS CAGR、FCF CAGR |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 144 lines · 100 tokens per session scan A 0eb0bdd31cba
financial-statement-analyzer is a skill published in the GitHub repository Geeksfino/finskills (279 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 100 tokens to every session and 1,964 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.