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 jwangkun/claude-for-financial-services-cn --skill china-clean-data-xlsgit clone --depth 1 https://github.com/jwangkun/claude-for-financial-services-cnWrote 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/jwangkun/claude-for-financial-services-cn/china-clean-data-xls)<a href="https://agentmods.dev/skills/jwangkun/claude-for-financial-services-cn/china-clean-data-xls"><img src="https://agentmods.dev/badge/skills/jwangkun/claude-for-financial-services-cn/china-clean-data-xls/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/jwangkun/claude-for-financial-services-cn/china-clean-data-xls"><img src="https://agentmods.dev/badge/skills/jwangkun/claude-for-financial-services-cn/china-clean-data-xls.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00074 | $0.02103 |
| Opus 5 | $0.00037 | $0.01052 |
| Sonnet 5 | $0.00015 | $0.00421 |
| Haiku 4.5 | $0.00007 | $0.00210 |
Grade A, and why
china-clean-data-xls 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 13d 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
china-clean-data-xls
Purpose
Clean and normalize A股财务数据 — prepare raw financial data from 巨潮 filings for modeling and analysis.
Data Sources
Tier 0 — 万得 Wind（最全面付费数据）
- 覆盖：A股/港美股/基金/指数/债券/宏观/研报/分析（44个工具）
- MCP 服务：
wind-mcp（需WIND_API_KEY密钥，以ak_开头） - 优势：全市场覆盖面最广、数据最全面、包含研报和量化分析
- 密钥申请：https://aifinmarket.wind.com.cn/#/home
Tier 1 — 同花顺 iFind（付费精确数据）/ AkShare MCP（Tier-2 免费备选）
get_financials(ticker, "income") → Raw income statement
get_financials(ticker, "balance") → Raw balance sheet
get_financials(ticker, "cashflow") → Raw cash flow statement
Secondary Sources
- 巨潮 — original filings (PDF/HTML)
- 审计报告 — audited figures
Workflow
Step 1: Data Extraction
Extract from source documents:
| Document | Key Data | Format |
|---|---|---|
| 资产负债表 | Assets, liabilities, equity | 千元 |
| 利润表 | Revenue, expenses, profit | 千元 |
| 现金流量表 | Operating, investing, financing CF | 千元 |
| 报表附注 | Detail breakdowns | Text/number |
| 审计报告 | Audit opinion, adjustments | Text |
Extraction checklist:
- All periods extracted (typically 3-5 years)
- Quarterly data if needed
- Prior year comparatives
- Notes and footnotes captured
Step 2: Normalize Units
Unit standardization:
| Issue | Solution |
|---|---|
| 千元 vs 万元 vs 元 | Standardize to 万元 |
| Different report dates | Align to same period-end |
| Segment data | Map to consistent segments |
| Currency | All CNY |
Unit conversion:
From 千元: divide by 10 → 万元
From 元: divide by 10,000 → 万元
From 亿元: multiply by 10,000 → 万元
Step 3: Handle CAS-Specific Items
CAS vs IFRS mapping:
| CAS Line Item | Equivalent | Notes |
|---|---|---|
| 营业收入 | Revenue | Net of VAT |
| 营业成本 | COGS | Includes VAT |
| 税金及附加 | Tax & surcharges | 城建税, 教育费附加 |
| 销售费用 | SG&A (selling) | |
| 管理费用 | G&A | |
| 研发费用 | R&D | Separated from G&A in new CAS |
| 财务费用 | Interest & finance costs | |
| 投资收益 | Investment income | Including 联营/合营 |
| 公允价值变动 | Fair value change | |
| 信用减值损失 | Credit impairment | New CAS 22 |
| 资产减值损失 | Asset impairment | |
| 资产处置收益 | Asset disposal | |
| 营业外收入 | Non-operating income | Including 政府补助 |
| 营业外支出 | Non-operating expense | |
| 所得税费用 | Income tax | |
| 净利润 | Net income | |
| 归母净利润 | Net income to parent | Key metric |
| 扣非净利润 | Non-GAAP net income |
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.
- 13d ago First seen · 238 lines · 74 tokens per session scan A 433a19c82ea6
china-clean-data-xls is a skill published in the GitHub repository jwangkun/claude-for-financial-services-cn (744 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 74 tokens to every session and 2,103 once invoked, about $0.0004 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
fs-creative-voltage
OpenDesign's seed pitch: the open, local alternative to closed AI design — why now, the wedge, and the ask. Built as a decision-grade fundraising pitch deck for pre-seed & seed VCs.
ml-strategy
Machine-learning predictive strategy based on sklearn walk-forward training, feature engineering, and signal generation. Suitable for any OHLCV data.
ai-readiness
Scan the portfolio for the highest-leverage AI opportunities and rank where to deploy operating-partner time. Ingests quarterly updates and financials across multiple portfolio companies, identifies quick wins at each, and stacks them into a single ranked action list. Use during quarterly portfolio reviews, annual…
merger-model
Build accretion/dilution analysis for M&A transactions. Models pro forma EPS impact, synergy sensitivities, and purchase price allocation. Use when evaluating a potential acquisition, preparing merger consequences analysis for a pitch, or advising on deal terms. Triggers on "merger model", "accretion dilution", "M&A…
technical-basic
Core technical indicator collection (trend EMA/ADX + mean-reversion BB/RSI + volume-price OBV/volume ratio), generates a composite signal via three-dimensional voting. Pure pandas implementation for any OHLCV data.
qveris
Paid capability marketplace for global multi-asset data; use it when free Vibe-Trading sources lack coverage, depth, or provider quality, and keep free sources as the default for routine OHLCV.