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 duolongworld/AI_Renaissance --skill volume_price_reversalgit clone --depth 1 https://github.com/duolongworld/AI_RenaissanceWrote 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/duolongworld/ai_renaissance/volume_price_reversal)<a href="https://agentmods.dev/skills/duolongworld/ai_renaissance/volume_price_reversal"><img src="https://agentmods.dev/badge/skills/duolongworld/ai_renaissance/volume_price_reversal/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/duolongworld/ai_renaissance/volume_price_reversal"><img src="https://agentmods.dev/badge/skills/duolongworld/ai_renaissance/volume_price_reversal.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 | $0.17451 |
| Opus 5 | $0.00037 | $0.08725 |
| Sonnet 5 | $0.00015 | $0.03490 |
| Haiku 4.5 | $0.00007 | $0.01745 |
Grade A, and why
volume-price-reversal 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 — 733 lines — stays where its author put it; the contents beside it link to each section on GitHub.
量价背离与反转信号识别
理论来源:Goldman Sachs QIS STR 因子家族,结合 Campbell-Grossman-Wang (1993)、Lee-Swaminathan (2000)、Gervais-Kaniel-Mingelgrin (2001) 等学术经典整理。
1. 适用范围
所属小组:专家2组(指标)
适用任务:
- 个股、板块、指数的短期量价背离识别(顶背离 / 底背离 / 量价齐升后乏力 / 量价齐跌后衰竭)
- 事件驱动后的反转概率判断(财报公告、研报调评、指数调仓)
- 持仓股短期超涨减仓时机 / 目标股低位建仓时机判断
- 适合时间周期:5
21 个交易日(短期),A 股建议优先取 510 日
边界说明
-
强趋势牛市(过去 3 个月指数涨幅 > 20% 且仍加速)中,动量主导,反转策略失效,输出
neutral -
极端流动性枯竭阶段(市场出现系统性危机、全面踩踏)中,价格冲击不回归,输出
neutral -
A 股以下场景不适用,输出
neutral并标记needs_human_review: true:- 政策强刺激期(如单日指数涨超 3%、全面利好政策出台)
- 游资题材股 / 妖股(连续涨停且无基本面支撑)
- ST 股 / 退市风险股(±5% 涨跌停 + 基本面恶化)
- 北交所股票(流动性差,须严格执行 §4.4 过滤器三 Amihud 和过滤器四绝对成交额双重检查;不达标即输出
neutral) - 重大节假日前后 2 个交易日(春节 / 国庆资金季节性扰动)
-
成交量数据缺失或历史数据不足 60 日时,需降低
confidence并标记人工复核
2. 输入材料
必填输入
- 标的:股票代码 / 板块名称 / 指数代码
- 时间范围:分析窗口(至少包含过去 60 个交易日行情数据)
- 核心行情数据:
- 日线收盘价序列(用于计算 STR 和形态判断)
- 日线最高价 / 最低价(用于识别上影线 / 下影线形态)
- 日线成交量序列(用于计算 VolSurp 和均量比较)
- 换手率序列(用于换手率分层,至少 20 日)
- 数据来源:行情数据(market_data),来自东方财富 / 同花顺 / Wind 等
可选输入
- RSI 指标数值(RSI6 / RSI12 / RSI24),用于复合判断规则
- 主力资金净流入数据(超大单净额),来自资金流数据(fund_flow)
- A 股涨停板信息(是否涨停、封板时间、打开次数)
- A 股集合竞价价格(9:25 竞价价格 vs 昨收比较)
- 融资余额变化(连续 N 日净增 / 净减)
- 板块 / 行业成交量均值(用于板块超涨超跌判断)
缺失处理
- 缺少成交量数据 → 无法执行任何量价判断,输出
direction: "neutral",confidence降至 0.2,meta.needs_human_review: true,meta.uncertainties写明「缺少成交量数据,无法完成量价分析」 - 缺少换手率数据 → 跳过换手率分层,
confidence降低 0.1,在meta.uncertainties说明「换手率分层未执行,信号权重未调整」 - 历史数据不足 60 日 →
confidence降至 0.3,meta.needs_human_review: true - 缺少 RSI 数据 → 仅执行量价形态判断,跳过 RSI 复合判断规则;
meta.uncertainties写明「RSI 缺失,复合信号不完整」 - 可选输入缺失 → 继续分析,但在
meta.uncertainties中说明对信号覆盖度的影响
3. 分析步骤
- 确认分析对象与市场环境:检查标的所属市场(A 股主板 / 科创板 / 创业板 / 北交所 / 港股 / 美股),判断是否处于强趋势牛市或极端流动性枯竭,若是则直接输出
neutral。 - 检查数据完整性:核对必填输入是否齐全;缺失时按缺失处理规则降低
confidence或输出neutral。 - 计算量价核心指标:
- 计算 STR(横截面短期反转得分)
- 计算 VolSurp(异常成交量 Z 分数)
- 计算换手率分位,确定分层系数
- 计算 Amihud ILLIQ,判断流动性是否可执行
- 计算绝对成交额(当日 + 过去 20 日均值),对照 §4.4 过滤器四阈值表,确定是降权 ×0.5 还是强制 neutral
- A 股涨跌停前置过滤(若标的为 A 股):检查当日是否涨停一字板/跌停一字板/未开板封死,若是则跳过形态一/二的顶/底背离判断,转入 §4.7 涨停板规则。
- 识别量价形态:依据第 4 节判断规则,匹配以下四种形态中的一种或多种:顶背离 / 底背离 / 量价齐升后乏力 / 量价齐跌后衰竭;形态三/四须按 §4.2 长上下影线精确定义(三条件全成立)判定,并区分是否为十字星犹豫形态。
- 执行 RSI + 空间位置三维度复合验证:按 §4.3 复合判断三维度(量价 + 动量 + 空间)规则,校验信号是否撞到关键压力位/支撑位;空间未确认的反转信号显著降权并写入
meta.uncertainties。 - 执行 A 股特有规则(若标的为 A 股):按第 4.7 节处理涨停板特有形态、T+1 执行约束、参数阈值调整。
- 确定 direction / confidence / risk_level:汇总所有信号,按第 4 节规则映射,对照 §4.4 指标解读速查表逐项累加 confidence 调整量。
- 整理 evidence、key_findings 和命中逻辑说明:
- 记录触发规则的指标值、数据来源、对比基准;
- 对每个被命中"强制约束等级"的指标(如 STR 中度/强烈、VolSurp 爆量/巨量/缩量/地量、换手率高/极端/低、影线标准/极端、流动性差、绝对成交额不足/长期不足等),必须从 §4.4 速查表的「命中逻辑说明」列原文引用对应一句话,写入:
- 标准 JSON 的
reasoning字段(多指标命中时按"指标名 → 命中逻辑"句式拼接为一段) - 标准 JSON 的
meta.evidence[].note字段(每条 evidence 对应一个指标,note 写该指标命中等级 + 命中逻辑说明) - §5.2 Markdown 摘要中该指标行的「→ 意味着:……」子项
- 标准 JSON 的
- 命中"平淡/正常/中等/容量充足/非长影线"等中性等级时不需要写命中逻辑说明,避免输出冗余。
- 输出结果:
- Agent 系统调用:按第 5 节格式输出标准 JSON,供
Signal.from_dict()解析; - 人工 / Cursor 直接调用:按第 5.2 节格式输出 Markdown 摘要,省略 JSON,提升可读性。
- 不确定调用场景时,优先输出 JSON。
What ships with it
1 file 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.
- 13d ago First seen · 733 lines · 74 tokens per session scan A 1c380c36c172
volume-price-reversal is a skill published in the GitHub repository duolongworld/AI_Renaissance (59 stars, last pushed 15d ago), licensed Apache-2.0. It adds 74 tokens to every session and 17,451 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
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.