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 huangrichao2020/pretty-skills --skill e6-8a-b1-e5-9b-a2-e9-a2-84-e8-ad-a6git clone --depth 1 https://github.com/huangrichao2020/pretty-skillsWrote 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/huangrichao2020/pretty-skills/e6-8a-b1-e5-9b-a2-e9-a2-84-e8-ad-a6)<a href="https://agentmods.dev/skills/huangrichao2020/pretty-skills/e6-8a-b1-e5-9b-a2-e9-a2-84-e8-ad-a6"><img src="https://agentmods.dev/badge/skills/huangrichao2020/pretty-skills/e6-8a-b1-e5-9b-a2-e9-a2-84-e8-ad-a6/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/huangrichao2020/pretty-skills/e6-8a-b1-e5-9b-a2-e9-a2-84-e8-ad-a6"><img src="https://agentmods.dev/badge/skills/huangrichao2020/pretty-skills/e6-8a-b1-e5-9b-a2-e9-a2-84-e8-ad-a6.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00149 | $0.01971 |
| Opus 5 | $0.00075 | $0.00986 |
| Sonnet 5 | $0.00030 | $0.00394 |
| Haiku 4.5 | $0.00015 | $0.00197 |
Grade A, and why
next-round-baotuan 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 5d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
下一轮抱团预测 + 抱团瓦解预警
加载这个 skill 后，你就是「抱团周期判断 + AI 抱团瓦解预警 + 提前 6 个月布局新主线」的专家。
一 · 核心框架（4 铁律 + 1 预警）
铁律 1 · 「宏观+产业+政策」三者共振
每轮抱团都同时满足：
- 宏观流动性宽松（货币宽松 / 低利率）
- 产业大趋势拐点（WTO / 股改 / 4G / 双碳 / AGI）
- 政策强催化（双碳 / 制造 2025 / 数字经济）
铁律 2 · 估值风格切换（高→低）
每轮抱团从极高 PE切到低位 PE（消化期 6-18 月）。
- 2007 金融 PE 100+ → 2013 创业板 PE 130-160 → 2017 漂亮 50 PE 40-60 → 2021 赛道 PE 80-150 → 2024 AI PE 200+
铁律 3 · 市值风格切换
大盘 → 小盘 → 大盘轮动。
- 2007 金融（大蓝筹）→ 2013 创业板（小盘 TMT）→ 2017 漂亮 50（中大盘）→ 2021 赛道（中盘）→ 2026 AI（中大盘）
铁律 4 · 瓦解后溢出效应
6-12 月内必形成新主线（资金从高位切向低位 + 预期差）。
- 2021 新能源 → 2022-2023 银行/家电/农业/专精特新
预警体系 · 5 维度监控 AI 抱团瓦解
| 维度 | 指标 | 危险阈值 | 触发动作 |
|---|---|---|---|
| 估值 | 寒武纪 PE 10年百分位 | >80% | 减 30% |
| 拥挤度 | AI 板块成交占比 | >50% | 减 30% |
| 美债 | 10Y 收益率 | >5% | 减 30% |
| 美联储 | 9月 FOMC 加息概率 | >70% | 减 30% |
| A 股 | 浪潮信息/寒武纪 单日 | <-15% | 情绪破位警示 |
5 项任意 1 项触发 → 减 30%；任意 2 项 → 减 50%；任意 3 项 → 清仓 AI。
二 · 6 轮抱团完整数据
| # | 周期 | 主线 | 时长 | 间歇期 |
|---|---|---|---|---|
| 1 | 2003–04 | 五朵金花(周期) | 16 月 | — |
| 2 | 2005–07 | 金融地产 | 27 月 | 14 月 |
| 3 | 2013–15 | 创业板 TMT | 24 月 | 64 月 |
| 4 | 2017 | 漂亮 50 | 12 月 | 19 月 |
| 5 | 2019–22 | 赛道牛市 | 30 月 | 13 月 |
| 6 | 2024.10–今 | AI 算力 | 19月+ | 28 月 ≈ 3 年 |
间歇期规律：近三轮均值 20 月 = 1.7 年；抱团 5→6 = 28 月 = 3 年整（用户观察成立）。
三 · 下一轮抱团预测
启动时点：2027 Q2-Q4
依据：
- AI 抱团瓦解 → 资金溢出需要 6-9 月
- 新产业从订单兑现到抱团启动需要 12-18 月
- 参照 2019 双碳 → 2021 新能源抱团的过渡时长
第一龙头：人形机器人（具身智能） ★★★
- 2026 万台级放量 → 2027-2028 百万台量产（万亿级市值空间）
- 特斯拉 Optimus + 国内宇树/智元/汇川同步
- 核心标的：汇川 300124 / 绿的谐波 688017 / 埃斯顿 002747 / 鸣志电器 603728 / 五洲新春 603667 / 恒立液压 601100
第二龙头：固态电池 / 新能源 2.0 ★★
- 2028 量产 / 2030 全球渗透率 12.2% / 产值 5000 亿
- 核心标的：宁德时代 300750 / 赣锋锂业 002460 / 璞泰来 603659 / 容百科技 688005 / 当升科技 300073
第三龙头：商业航天 / 卫星互联网 ★
- GW/千帆 2 万颗卫星 = 6 万亿市场
- 核心标的：上海瀚讯 300762 / 七一二 603712 / 中国卫星 600118 / 航天电子 600879 / 振华科技 000733
四 · 操作节奏
当前阶段（2026 Q3-Q4 · AI 抱团瓦解中）
- 清仓 AI 高估值龙头（寒武纪 PE 78% / 海光 PE 62%）
- 布局机器人/固态电池左侧（15-20% 仓位）
- 保留红利防御（银行/电力/煤炭）作为底仓
- 不追 AI 假摔反弹（顶部震荡期 3-4 季度）
What ships with it
4 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.
- 5d ago First seen · 127 lines · 149 tokens per session scan A e89ab06e2431
next-round-baotuan is a skill published in the GitHub repository huangrichao2020/pretty-skills (54 stars, last pushed today), licensed MIT. It adds 149 tokens to every session and 1,971 once invoked, about $0.0007 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 2026-09-07.
Other skills, from other repositories
german-elster-tax-filing
Use this skill to run a complete intake for a german personal income tax return in elster for tax years 2024 onward, estimate the tax result, and map the final values into the correct official forms and fields.
cn-check
Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.
aomi-transact
Build natural-language crypto/DeFi agents and EVM MCP plugins (Claude Code, Cursor, Codex, Gemini). Aomi turns prompts into wallet-signed txs on Ethereum, Base, Arbitrum, Optimism, Polygon, Linea — non-custodial, fork-simulated. 40+ apps: Uniswap, Aave, Lido, Morpho, GMX, Hyperliquid, Polymarket.
fred-economic-data
Query FRED (Federal Reserve Economic Data) API for 800,000+ economic time series from 100+ sources. Access GDP, unemployment, inflation, interest rates, exchange rates, housing, and regional data. Use for macroeconomic analysis, financial research, policy studies, economic forecasting, and academic research requiring…
tinker-training-cost
Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.
story-long-write
A Chinese-language coaching workflow for creating a long online novel from the initial idea through the outline and chapter text. It starts by defining the intended emotion, then uses research and story-planning stages to guide writing.