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 market_sentiment_trackergit 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/market_sentiment_tracker)<a href="https://agentmods.dev/skills/duolongworld/ai_renaissance/market_sentiment_tracker"><img src="https://agentmods.dev/badge/skills/duolongworld/ai_renaissance/market_sentiment_tracker/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/market_sentiment_tracker"><img src="https://agentmods.dev/badge/skills/duolongworld/ai_renaissance/market_sentiment_tracker.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 | $0.00094 | $0.03452 |
| Opus 5 | $0.00047 | $0.01726 |
| Sonnet 5 | $0.00019 | $0.00690 |
| Haiku 4.5 | $0.00009 | $0.00345 |
Grade A, and why
market-sentiment-tracker 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
大盘市场情绪温度计 Skill
1. 适用范围
所属小组：专家6组（舆情）
适用任务：
- 判断 A 股大盘整体情绪冷热程度，输出 0-100 综合情绪温度
- 识别大盘所处的6阶段情绪状态，给出仓位参考
- 为个股舆情分析提供大盘背景参照（"大气候"）
- 检测特殊情绪信号（顶部预警、底部信号、社区一致看多/看空等）
- 适用于沪深全市场、创业板、科创板等大盘级别情绪评估
边界说明：
- 本 Skill 产出的是大盘情绪面辅助信号，不单独构成交易建议
- 情绪极端不等于立即反转，极端情绪可能持续一段时间
- 社区数据来源存在代表性偏差（东财股吧偏散户），需在
meta.uncertainties说明 - 数据源存在延迟（融资余额 T+1、开户数月度等），需在
meta.uncertainties说明 - 本 Skill 不替代风控层的仓位管理，仅作为情绪面输入
2. 输入材料
数据来源
| 数据接口 | 执行数据源 | 提供内容 |
|---|---|---|
| AKShare 全市场接口 | data_sources/market_sentiment.py |
涨跌停数、市场宽度、北向资金、融资余额、技术指标等 |
| 东财大盘股吧 | data_sources/community_sentiment.py |
上证指数吧+创业板吧帖子、讨论热度、多空比例 |
必填输入（自动采集）
- 涨跌停板数据：今日涨停家数、跌停家数
- 市场宽度数据：上涨家数 / 下跌家数占比
- 北向资金数据：当日净流入额（亿元）
- 融资余额数据：融资余额及 20 日变化率
- 技术指标：上证指数 RSI(14)、价格相对 20 日高低点位置
社区指标（v0.4 新增）
- 讨论热度：大盘股吧帖子总量映射到0-100分
- 社区情绪倾向：看多/看空比例映射到0-100分
- 讨论量趋势：升温/降温/平稳
可选输入
- 成交额/换手率变化率
- 市盈率/市净率历史百分位
- 新增开户数/基金申赎数据
- 百度/微信搜索指数
- 个人投资者调查数据（CCTV/中证报）
缺失处理
- 如果涨跌停和市场宽度数据均缺失（非交易时间），输出
direction: "neutral"，confidence不高于 0.3，标注"非交易时间，无法获取实时市场数据" - 如果社区数据获取失败，退化为纯分数映射阶段，权重自动归一化到可用指标
- 如果可选输入缺失，可以继续分析，权重自动归一化到可用指标
3. 分析步骤
-
采集量化市场数据：通过
data_sources/market_sentiment.py自动获取可用的市场指标 -
采集社区讨论数据：通过
data_sources/community_sentiment.py获取大盘股吧讨论热度 -
逐指标标准化：将每个原始指标映射到 0-100 分
- 涨跌停比：涨停数/(涨停+跌停) × 100
- 市场宽度：上涨家数占比 × 100
- 北向资金：(50 + 净流入/3) 限制在 [0, 100]
- 融资变化率：(50 + 变化率×2.5) 限制在 [0, 100]
- RSI：直接使用（0-100）
- 讨论热度：直接使用 community_sentiment 计算结果
- 社区情绪倾向：看多比例 × 100
-
加权综合评分：按权重计算综合情绪温度
指标 权重 涨跌停比 0.12 市场宽度 0.10 融资余额变化 0.12 北向资金 0.10 RSI 0.08 换手率异动 0.12 量比/成交额变化 0.08 估值百分位 0.08 讨论热度 0.10 社区情绪倾向 0.10 - 可用指标权重自动归一化
-
判定市场阶段：根据综合温度 + 社区指标匹配6阶段（见4.1）
-
检测特殊信号：顶部预警、底部信号、恐慌踩踏、社区一致看多/看空等
-
输出标准 JSON
4. 判断规则
4.1 市场阶段判定（6阶段）
优先级从高到低（先匹配最具体的条件）：
| 优先级 | 阶段 | 条件 | direction | 说明 |
|---|---|---|---|---|
| 1 | 绝望冰点 🧊 | score≤15 AND 讨论热度≤25 AND 看空>60% AND 趋势降温 | bullish |
彻底绝望，讨论冻结，逆向看多 |
| 2 | 恐慌抛售 ⚡ | score≤40 AND 讨论热度≥50 AND 看空>75% | bullish |
恐慌主导，激烈讨论，逆向看多 |
| 3 | 人声鼎沸 🔥 | score≥65 AND 讨论热度≥70 AND 看多>75% | bearish |
全民追涨，逆向看空 |
| 4 | 暗度陈仓 🦉 | score∈[15,40] AND 讨论热度≤35 AND 聪明钱进场 | bullish |
聪明钱悄悄进场，散户沉默 |
| 5 | 无人问津 🕳️ | score≤20 AND 讨论热度≤20 | bullish |
极端冷清，市场被遗忘 |
| 6 | 人声渐起 📈 | score∈[35,60] AND 讨论热度≥30 | neutral |
中间状态，关注度上升 |
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 · 275 lines · 94 tokens per session scan A b3aae25594eb
market-sentiment-tracker is a skill published in the GitHub repository duolongworld/AI_Renaissance (59 stars, last pushed 14d ago), licensed Apache-2.0. It adds 94 tokens to every session and 3,452 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.