Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

A Share Market Impact · aifinlab | DecimalAI

financeby aifinlab

A Share Market Impact

aifinlab/a-share-market-impact

Source aifinlab/finclaw ↗License Apache-2.0

A股市场冲击/价格影响分析。当用户说"市场冲击"、"market impact"、"价格影响"、"冲击成本"、"大单冲击"、"价格冲击模型"时触发。基于 cn-stock-data 获取数据，估算交易的市场冲击成本。支持 formal/brief 两种输出风格。

SkillScore83Maintained

Automatic

Finance & Accounting pack

Last verified 8/27/2026

What it changes

Passed 16 of 19 test cases with the skill, and 13 of 19 without it.

Without skill70%

With skill83%

Checks it passed that the model alone missed

The primary section headings are ordered as 冲击估算, 冲击因素, 执行方案对比, and 优化建议.
The response specifies the empirical coefficient lambda range of 0.1 to 0.3 for A-shares.
The response identifies tick-by-tick transaction data, order book depth data, and historical daily volume or volatility as required data types.

and 1 more in the full report

4 fixed15 passed either way3 still failing1 broke

Pass-rate lift: +13 pp
Tokens: +26%
Agent turns: 0%
Response time: +3%

Model gemini-3.6-flashMeasured 8/27/2026v119 of 23 cases passed with skill · 19 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-market-impact/SKILL.md https://app.decimal.ai/s/aifinlab-a-share-market-impact/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add aifinlab-a-share-market-impact, 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-market-impact/ and pins it in .decimal/skills.lock

decimalai skills add aifinlab-a-share-market-impact

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

撰写比亚迪（002594）大额交易冲击分析研报时，研报的主体二级标题应该包含哪四个标准部分？请按先后顺序排列。

What was checked, without and with the skill
Checked	Without skill	With skill
The primary section headings are ordered as 冲击估算, 冲击因素, 执行方案对比, and 优化建议.	Missed	Passed

case-13 · gemini-3.6-flash · 8/27/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md84 lines2 files

市场冲击/价格影响分析助手

数据获取

通过 cn-stock-data skill 获取数据：

逐笔成交: 大单成交与价格变动
盘口数据: 市场深度
历史数据: 日均成交量/波动率

分析工作流

Step 1: 冲击模型

线性模型：Impact = λ × OrderSize / ADV
平方根模型：Impact = σ × √(OrderSize/ADV) (Almgren)
临时冲击 vs 永久冲击分解
A股经验参数：λ ≈ 0.1-0.3

Step 2: 冲击因素分析

订单大小/ADV比：越大冲击越大
波动率：高波动时冲击更大
流动性：盘口深度越深冲击越小
执行速度：越急迫冲击越大

Step 3: 冲击估算

给定订单量，估算预期冲击成本
置信区间：冲击的不确定性范围
不同执行策略的冲击对比
分批执行vs一次性执行的冲击差异

Step 4: 冲击优化

最优执行速度：平衡冲击与风险
最优拆单大小：单笔订单的最优规模
时段选择：流动性高峰期执行降低冲击
暗池/大宗交易：绕过公开市场降低冲击

Step 5: 输出报告

输出格式

formal 风格（研报级）

Track record

Benchmark

16 / 19

test cases passed, vs 13 / 19 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-market-impact/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.