financeby aifinlab

A Share Index Arb

aifinlab/a-share-index-arb

Source aifinlab/finclaw ↗License Apache-2.0

A股期现套利/基差交易策略。当用户说"期现套利"、"基差交易"、"index arb"、"期货基差"、"正向套利"、"反向套利"、"基差收敛"时触发。基于 cn-stock-data 获取数据，分析股指期货基差与套利机会。支持 formal/brief 两种输出风格。

SkillScore68Maintained

Automatic

Finance & Accounting pack

Last verified 8/28/2026

What it changes

Passed 14 of 20 test cases with the skill, and 10 of 20 without it.

Without skill50%

With skill68%

Checks it passed that the model alone missed

The strategy is identified as basis convergence trading.
The theoretical basis formula is defined as S * (r - d) * T.
The calculation computes simple basis as futures price minus spot index.

and 1 more in the full report

4 fixed11 passed either way7 still failing0 broke

Pass-rate lift: +18 pp
Tokens: +35%
Agent turns: 0%
Response time: +13%

Model gemini-3.6-flashMeasured 8/28/2026v115 of 22 cases passed with skill · 20 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/aifinlab-a-share-index-arb/SKILL.md https://app.decimal.ai/s/aifinlab-a-share-index-arb/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add aifinlab-a-share-index-arb, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/aifinlab-a-share-index-arb/ and pins it in .decimal/skills.lock

decimalai skills add aifinlab-a-share-index-arb

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/aifinlab-a-share-index-arb/SKILL.md https://app.decimal.ai/s/aifinlab-a-share-index-arb/SKILL.md

Raw file: /s/aifinlab-a-share-index-arb/SKILL.md ↗ · machine-readable summary at /s/aifinlab-a-share-index-arb.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

What's inside

The instructions your model reads when the skill loads.

SKILL.md84 lines2 files

期现套利/基差交易助手

数据获取

通过 cn-stock-data skill 获取数据：

期货数据: 股指期货价格(IF/IC/IM/IH)
指数数据: 对应现货指数
利率数据: 无风险利率/融资成本

分析工作流

Step 1: 基差分析

基差 = 期货价格 - 现货指数
年化基差率 = 基差/现货 × 365/剩余天数
理论基差 = 现货 × (r-d) × T (持有成本模型)
基差偏离 = 实际基差 - 理论基差

Step 2: 套利策略

正向套利：期货溢价→买现货+卖期货
反向套利：期货贴水→卖现货(融券)+买期货
跨期套利：买近月+卖远月(或反向)
基差收敛交易：到期日基差必然收敛至零

Step 3: 现货组合构建

完全复制：买入全部成分股(成本高)
抽样复制：选取代表性成分股(跟踪误差)
ETF替代：用ETF替代现货组合(最简单)
跟踪误差控制：<0.5%为优秀

Step 4: 风险与成本

保证金风险：期货追加保证金
跟踪误差风险：现货组合偏离指数
交易成本：期货手续费+现货冲击成本
A股特征：IC/IM长期贴水，反向套利受融券限制

Step 5: 输出报告

输出格式

formal 风格（研报级）

Track record

Benchmark

14 / 20

test cases passed, vs 10 / 20 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

aifinlab / finclaw

skills/a-share-index-arb/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1Bundled 1 file

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

+13 pp pass-rate lift

aifinlab/a-share-futures-analysis股指期货/期现价差分析。当用户说"股指期货"、"IF"、"IC"、"IM"、"IH"、"期指"、"基差"、"期现价差"、"升水"、"贴水"、"futures"、"期货贴水多少"、"对冲"、"期现套利"时触发。分析股指期货（IF沪深300/IC中证500/IH上证50/IM中证1000）的基差变化、期限结构、持仓变动，辅助判断市场情绪和套利机会。支持研报风格（formal）和快速查看风格（brief）。Close match-13 pp pass-rate lift

A股个股深度研究/首次覆盖报告/个股全面研究分析。当用户说"深度研究"、"深度分析"、"全面分析XX"、"首次覆盖"、"initiation"、"initiating coverage"、"帮我研究一下XX"、"XX值不值得买"、"给我出一份XX的研究报告"、"个股深度"、"深度报告"、"投资价值分析"时触发。MUST USE when user asks for deep research, initiating coverage, comprehensive stock analysis, or a full research report on a specific stock. 整合公司概况、行业地位、财务分析、估值（DCF+可比）、投资论点，生成全面的个股研究报告。通过 cn-stock-data 获取全量数据，结合 web 搜索获取公司信息、行业背景、分析师观点。支持券商深度报告风格（formal，15-30页）和个人研究笔记风格（brief，3-5页）。

aifinlab/a-share-insiderA股股东/高管增减持分析/内部人交易追踪。当用户说"增减持"、"减持"、"增持"、"大股东"、"高管买卖"、"insider"、"insider trading"、"XX的股东在减持吗"、"谁在增持"、"重要股东"、"举牌"、"解禁"、"股东增减持"、"高管增减持"、"大股东减持"、"内部人交易"时触发。MUST USE when user asks about insider trading, shareholder/executive buy/sell activities, share increase/decrease by major holders, or lock-up expiry impact. 基于 akshare 增减持数据和 cn-stock-data 行情数据，分析重要股东和高管的增减持行为、规模、动机和市场影响。支持研报风格（formal）和快速解读风格（brief）。不适用于基金持仓（用 a-share-fund-holding）或龙虎榜（用 a-share-dragon-tiger）。

aifinlab/a-share-intraday-momentumA股日内动量/分时趋势策略。当用户说"日内动量"、"分时趋势"、"intraday momentum"、"盘中趋势"、"日内追涨"、"分时动量"时触发。基于 cn-stock-data 获取数据，分析日内动量效应、分时趋势信号、最优交易时段。支持 formal/brief 两种输出风格。+36 pp pass-rate lift

aifinlab/a-share-intraday-patternA股日内模式/分时走势量化分析。当用户说"日内模式"、"intraday"、"分时"、"盘中走势"、"几点涨"、"尾盘规律"时触发。量化分析A股日内交易模式。支持formal和brief风格。+9 pp pass-rate lift

aifinlab/a-share-intraday-reversalA股日内反转/均值回归策略。当用户说"日内反转"、"日内均值回归"、"intraday reversal"、"盘中回调"、"日内超跌反弹"、"分时反转"时触发。基于 cn-stock-data 获取数据，分析日内反转信号、超买超卖状态、均值回归速度。支持 formal/brief 两种输出风格。+18 pp pass-rate lift