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 crowding_state2x2git 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/crowding_state2x2)<a href="https://agentmods.dev/skills/duolongworld/ai_renaissance/crowding_state2x2"><img src="https://agentmods.dev/badge/skills/duolongworld/ai_renaissance/crowding_state2x2/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/crowding_state2x2"><img src="https://agentmods.dev/badge/skills/duolongworld/ai_renaissance/crowding_state2x2.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 | $0.00126 | $0.05244 |
| Opus 5 | $0.00063 | $0.02622 |
| Sonnet 5 | $0.00025 | $0.01049 |
| Haiku 4.5 | $0.00013 | $0.00524 |
Grade A, and why
crowding-state2x2 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 — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
资金拥挤度四象限状态诊断 Skill
1. 适用范围
所属小组：专家3组（资金）
适用任务：
- 对单只A股进行资金拥挤度四象限状态诊断，判断当前处于哪个象限
- 基于「资金流强度」和「拥挤度水平」两个维度交叉分类，给出结构化警示信号
- 为仲裁层提供资金面的方向信号（看多/看空/中性），辅助综合判断
象限定义（基于 Kyle-Obizhaeva 2018 与高盛 Tactical Flow of Funds 实践）：
| 象限 | 拥挤度 | 资金流 | 含义 | 操作建议 | direction |
|---|---|---|---|---|---|
| State 1: EarlyTrend | 低（≤30%） | 高流入（z≥+1） | 早期趋势，资金刚涌入，拥挤尚低 | 跟随 | bullish |
| State 2: LateTrend | 高（≥70%） | 高流入（z≥+1） | 晚期趋势，资金涌入但已拥挤 | 警惕反转，减仓 | bearish |
| State 3: Distribution | 低（≤30%） | 高流出（z≤-1） | 出货阶段，资金撤离但拥挤低 | 中性等待 | neutral |
| State 4: Reversal | 高（≥70%） | 高流出（z≤-1） | 反转信号，拥挤+流出双杀 | 均值回归，逆向做多 | bullish |
| State 0: Neutral | 中间区域 | 中间区域 | 未触达极端阈值 | 无明确信号 | neutral |
边界说明：
- 本 Skill 产出的是资金面状态信号，不单独构成交易建议
- 四象限分类基于统计阈值，在趋势延续期可能持续停留在某象限，象限切换才是关键信号
- 当前仅使用 CumFlowOverFloat 单一拥挤度子指标（融资余额和龙虎榜数据暂缺），拥挤度维度覆盖不完整
- 需要至少 60 个交易日的历史数据才能计算 z-score 和历史分位，数据不足时置信度降低
2. 输入材料
必填输入
stock_code：6位A股股票代码（如"600519"）- 资金流向数据（money_flow_df）：
NetAmountMain：主力净流入（万元）NetAmountX：超大单净流入（万元）NetAmountL：大单净流入（万元）NetAmountM：中单净流入（万元）NetAmountS：小单净流入（万元）
- 日线行情数据（daily_df）：
Close：收盘价Volume：成交量Amount：成交额（万元）
- 股票属性数据（prop_df）：
CirculatingMarketCap：流通市值（万元）IsPaused：是否停牌IsST：是否ST
可选输入
- 融资余额数据（MarginBalance）：用于补充拥挤度子指标2，暂缺时自动降权
- 龙虎榜数据（DragonTigerFreq）：用于补充拥挤度子指标3，暂缺时自动降权
- 人工补充观点：对当前象限的定性判断
缺失处理
- 如果 CirculatingMarketCap 缺失：使用 ADV_20 × 240 作为流通市值代理，在
meta.uncertainties说明 - 如果主力净流入数据全部缺失：输出
direction: "neutral"，confidence不高于 0.2，meta.needs_human_review: true - 如果历史数据不足 60 个交易日：仍可计算但
confidence降低，在meta.uncertainties写明"历史数据不足60日，统计指标可靠性下降" - 如果融资余额和龙虎榜数据缺失（当前常态）：拥挤度仅使用 CumFlowOverFloat 单指标，在
meta.uncertainties说明"拥挤度仅基于资金流/市值比单一维度"
3. 分析步骤
-
明确分析对象：确认股票代码，加载该股票的资金流、行情和属性数据
-
检查数据充足性：确认至少有 60 个交易日的主力净流入数据；若不足，降低置信度并标注
-
计算资金流强度（Y轴）：
- 计算
Flow_zscore = (NetAmountMain - rolling_mean_60d) / rolling_std_60d，按个股分组滚动计算 - z-score ≥ +1.0 为高流入，≤ -1.0 为高流出
- 计算
What ships with it
2 files 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 · 384 lines · 126 tokens per session scan A f8af66c19e31
crowding-state2x2 is a skill published in the GitHub repository duolongworld/AI_Renaissance (59 stars, last pushed 15d ago), licensed Apache-2.0. It adds 126 tokens to every session and 5,244 once invoked, about $0.0006 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.