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-model-updategit 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-model-update)<a href="https://agentmods.dev/skills/jwangkun/claude-for-financial-services-cn/china-model-update"><img src="https://agentmods.dev/badge/skills/jwangkun/claude-for-financial-services-cn/china-model-update/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-model-update"><img src="https://agentmods.dev/badge/skills/jwangkun/claude-for-financial-services-cn/china-model-update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 3 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00092 | $0.01712 |
| Opus 5 | $0.00046 | $0.00856 |
| Sonnet 5 | $0.00018 | $0.00342 |
| Haiku 4.5 | $0.00009 | $0.00171 |
Grade A, and why
china-model-update 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 12d 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
china-model-update
Purpose
Update existing A股财务模型 with new data, ensuring all cells are traceable to sources and all changes are documented.
Data Sources
Primary: iFind MCP (Tier-1 付费) / AkShare MCP (Tier-2 免费备选)
get_financials(ticker, "income", "quarterly") → Q[X] actual results
get_financials(ticker, "balance", "quarterly") → BS update
get_financials(ticker, "cashflow", "quarterly") → CF update
get_financials(ticker, "income", "annual") → Full year update
get_quote(ticker) → Current market data
get_stock_info(ticker) → Any company changes
Secondary Sources
- 巨潮资讯 — official filings for exact figures
- 业绩说明会 transcript — management commentary
- 管理层指引 — guidance from earnings calls
- Wind / Choice / 同花顺 — consensus updates
Workflow
Step 1: Identify What Changed
Change triggers:
- Quarterly earnings release (季报/年报)
- Management guidance update (管理层指引调整)
- Macro assumption change (rate, tax, policy)
- Model error or refinement
- M&A or restructuring event
Change log template:
| Date | Change Type | Item | Old Value | New Value | Reason |
|---|---|---|---|---|---|
| Earnings update | Revenue FY25E | XX亿 | XX亿 | Q1 actuals beat | |
| Guidance | Tax rate | 25% | 25% | No change | |
| Macro | CapEx % | 5% | 6% | New plant announced |
Step 2: Update Historical Actuals
Quarterly actuals:
[Company] Q[X] 20XX Actuals (from AkShare / 巨潮):
- 营业收入: XXX亿 (YoY: +XX%)
- 毛利率: XX% (vs prior: XX%)
- 归母净利润: XXX亿 (YoY: +XX%)
- EPS: X.XX元
- 经营现金流: XXX亿
Update sequence:
- Drop Q[X] actuals into historical columns
- Verify sum checks (quarterly sum = annual)
- Update LTM (Last Twelve Months) calculations
- Check annual-to-quarter relationships
Step 3: Roll Forward Estimates
Revenue projections:
- Update growth rates based on Q[X] performance
- Consider:
- Order backlog changes
- New product ramp
- Market share gains/losses
- Capacity expansion
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.
- 12d ago First seen · 220 lines · 92 tokens per session scan A 24078215001e
china-model-update is a skill published in the GitHub repository jwangkun/claude-for-financial-services-cn (743 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 92 tokens to every session and 1,712 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.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.