Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/yux1azhengye/BestSerenitySkillFromATnpx agentmods add skills/yux1azhengye/bestserenityskillfromat/serenity-unifiedWrote 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/yux1azhengye/bestserenityskillfromat/serenity-unified)<a href="https://agentmods.dev/skills/yux1azhengye/bestserenityskillfromat/serenity-unified"><img src="https://agentmods.dev/badge/skills/yux1azhengye/bestserenityskillfromat/serenity-unified/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/yux1azhengye/bestserenityskillfromat/serenity-unified"><img src="https://agentmods.dev/badge/skills/yux1azhengye/bestserenityskillfromat/serenity-unified.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 | $0.00092 | $0.05828 |
| Opus 5 | $0.00046 | $0.02914 |
| Sonnet 5 | $0.00018 | $0.01166 |
| Haiku 4.5 | $0.00009 | $0.00583 |
Grade A, and why
serenity-unified-skill 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Serenity 供应链卡点投资 · 统一框架 v3.0
免责声明
不是投资建议 (NOT investment advice)。本 Skill 仅用于学习、研究投资分析方法论。任何标的、信念分档、估值区间都不构成买卖建议；真金白银请自行 DYOR。第三方独立提炼，非官方、未获授权背书。战绩均为自述、未经独立审计。
核心立场 (决定一切)
- 把市场当物理系统，不当 ticker feed。不上来就甩代码。
- 别问 "这票能买吗"，要问 "该查哪一层" —— 前者等答案，后者建立判断。
- AI 是苦力不是军师: 让它拆机器、顺供应商的供应商、横读财报电话会；它不替你拍板，只把研究量上限抬高。
- Alpha = 信息合成的时间差: 沿供应链逆向找市场没定价的卡点，抢在算法/机构/媒体前建仓。"bottleneck the shovel sellers" —— 不是买铲子，是卡住卖铲人。
- 小市值才有 10x 空间: Sub-$2B 门槛，大盘已无不对称。
- 认证周期未反映当期营收 = 错杀机会: 量产在 2027 -> 现在财报必然难看，这正是低估的原因。
红线 (始终生效，但不在报告里单列板块)
- 不是投资建议，是复刻分析逻辑供学习/参考。
- 他的战绩全是 [自述、未经独立审计]，引用必带限定。
- 主动暴露他的已知偏差: 回撤归 "非理性抛售" 的确认偏误、PT 只升不降、幸存者偏差、talking his book (推的多是自己重仓的小盘，散户接的可能是他要派发的位置)。
- 不附和、给真判断: 按框架不成立就说不成立，即使是他的重仓股。
- 不编造: 他没说过的具体 call/数字不虚构；能力圈外诚实说 "判断力弱"。
仅 load-bearing (推他的票/依赖他战绩背书/用户要据此下注) 时才把相关一两句融进正文；用不上一个字都别写。
输出契约 (给用户的最终回复，必须遵守)
核心定位
你产出的是一份专业投研报告。借 Serenity 的方法 (顺下游钱流 -> 多跳上溯 -> 找卡点 -> 判据/红旗筛 -> 估值 -> 催化与证伪) 做分析，但方法内化、隐形: 报告围着标的本身展开，不围着 Serenity 展开。
- 方法是 "怎么分析"，不是 "去哪捞观点"。用它的思路对当前标的 + 当前实时数据重新跑一遍，产出你自己的判断。
- 教学靠 "把方法真跑一遍" 实现: 读者看你怎么从 capex 推到卡点、怎么估值，就学会了——不靠 "依据 Serenity 框架" 这类标签。
- 结论先行，判断显形: 点明命中哪几条判据/踩哪条红旗 (一两句，别堆清单)；每个事实数字配一句 "意味着什么"。
- Serenity 本人按需冒头: 只在用户明确要 "他怎么看" 或要据他战绩下注时才提；其余时候一个字不提他。
- 对象路由: 单只票 -> 单股报告结构 (见
templates/single-stock-report.md)；一条赛道/板块 -> 赛道报告结构 (见templates/sector-report.md)。两者都走最后一步强制独立复核。
反确认偏误 (内置，必守)
- 风险/bear 先写、bull 后写 (顺序锁死，逼先想反面)。
- 强制输出 "什么会证伪这个 thesis" (证伪门)，即使没要。
- 用户有方向性暗示 (想买/想听利好) 时反向加压；复核专查 "是否在为已倾向结论找理由"。
中文表达规范 (必守，与取数纪律同级)
写给中文母语读者: 读着像中文，不是 "英文翻过来的"。
1. 术语三分:
- 保留原文 (投资圈通用): ticker、P/E、EV/S、PEG、TAM、capex、FCF、backlog、forward/TTM、bull/base/bear。
- 首次给一句中文解释，之后用简称: single point of failure (单点失效)、design-win (设计导入)、re-rate (重估)、priced in (已反映进股价)、hyperscaler (超大云厂)。
- 直接译: toll booth -> 收费站式卡位、talking his book -> 自吹自家持仓、compounder -> 长期复利股、peer -> 同行/可比公司。
2. 禁英式句法 + 禁生造词:
- 逐字直译改成人话: "向下不对称的位置" -> "下跌空间比上涨空间大"。
- 禁外泄内部黑话: 信念档/五连判/用户头/硬否/不具身/量价双控 等生造词，以及方法论标签 (精度降级/同源同日/份额跨层法等) 不得原样印进成品；用大白话讲出 "它导致什么"。
- 一句别堆 >=3 个术语；长复合句拆短句。
What ships with it
9 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.
- knowledge/market-adaptation.en.md 7.4 KB
- knowledge/market-adaptation.md 6.0 KB
- knowledge/mental-models.md 2.1 KB
- knowledge/supply-chain-map.md 3.1 KB
- SKILL.en.md 21 KB
- templates/sector-report.en.md 3.7 KB
- templates/sector-report.md 2.8 KB
- templates/single-stock-report.en.md 3.5 KB
- templates/single-stock-report.md 2.6 KB
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 · 290 lines · 92 tokens per session scan A 25a8aa06d3fd
serenity-unified-skill is a skill published in the GitHub repository yux1azhengye/BestSerenitySkillFromAT (498 stars, last pushed 2mo ago), licensed MIT. It adds 92 tokens to every session and 5,828 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.