AI-Trader Market Intel
HKUDS/AI-Trader
Reads AI-Trader's read-only market snapshots, grouped financial news and events board through its market-intel endpoints, for context before trading or posting.
Agent skill
Serenity Supply Chain Bottleneck Research
A research framework for finding supply chain bottlenecks in equities, with a nine-step workflow, red-flag scans, risk-first reports and a falsification section.
SKILL.md written in Chinese; this summary is our English description.
Install Serenity Supply Chain Bottleneck Research
$ npx skills add yux1azhengye/BestSerenitySkillFromAT --skill serenity-unified-skill -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install yux1azhengye/BestSerenitySkillFromAT serenity-unified-skill --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "serenity-unified-skill" agent skill from https://github.com/yux1azhengye/BestSerenitySkillFromAT/tree/main into .claude/skills/serenity-unified-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "serenity-unified-skill", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add yux1azhengye/BestSerenitySkillFromAT --skill serenity-unified-skill -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install yux1azhengye/BestSerenitySkillFromAT serenity-unified-skill --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "serenity-unified-skill" agent skill from https://github.com/yux1azhengye/BestSerenitySkillFromAT/tree/main into .agents/skills/serenity-unified-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "serenity-unified-skill", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add yux1azhengye/BestSerenitySkillFromAT --skill serenity-unified-skill -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install yux1azhengye/BestSerenitySkillFromAT serenity-unified-skill --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "serenity-unified-skill" agent skill from https://github.com/yux1azhengye/BestSerenitySkillFromAT/tree/main into .cursor/skills/serenity-unified-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "serenity-unified-skill", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add yux1azhengye/BestSerenitySkillFromAT --skill serenity-unified-skill -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install yux1azhengye/BestSerenitySkillFromAT serenity-unified-skill --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "serenity-unified-skill" agent skill from https://github.com/yux1azhengye/BestSerenitySkillFromAT/tree/main into .gemini/skills/serenity-unified-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "serenity-unified-skill", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install yux1azhengye/BestSerenitySkillFromAT serenity-unified-skillInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add yux1azhengye/BestSerenitySkillFromAT --skill serenity-unified-skill -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "serenity-unified-skill" agent skill from https://github.com/yux1azhengye/BestSerenitySkillFromAT/tree/main into .github/skills/serenity-unified-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "serenity-unified-skill", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add yux1azhengye/BestSerenitySkillFromAT --skill serenity-unified-skill -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install yux1azhengye/BestSerenitySkillFromAT serenity-unified-skill --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "serenity-unified-skill" agent skill from https://github.com/yux1azhengye/BestSerenitySkillFromAT/tree/main into .opencode/skills/serenity-unified-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "serenity-unified-skill", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
serenity-unified-skill- GitHub stars
- 511
- Token cost
- ~2.4k tokens
- SKILL.md length
- 880 words
- Files
- 11
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
A research framework for finding supply chain bottlenecks in equities, with a nine-step workflow, red-flag scans, risk-first reports and a falsification section.
- Works in 9 steps: 范围门 (Scope Gate) → 锁周期 + 画栈 → 卡点定位 + 判据 (满足越多信念越高) → …
- Analyzing the supply chain behind a theme such as AI hardware
- SKILL.md covers 免责声明, 核心立场 (决定一切), 红线 (始终生效，但不在报告里单列板块) and 输出契约 (给用户的最终回复，必须遵守), plus 6 more sections
- Calls node and python3
What it does
This skill, written in Chinese, packages a supply-chain bottleneck research method for equities, combining ideas from ten GitHub repositories into one framework. It states plainly that it is not investment advice, that it is an unofficial third-party distillation, and that the track record it refers to is self-reported and unaudited.
The core stance is to treat markets as a physical system and ask which layer to examine rather than whether a stock can be bought, tracing the supply chain upstream from capital spending to find bottlenecks the market has not priced, with a lean toward small caps. A nine-step workflow runs from a scope gate and cycle mapping through bottleneck criteria, red-flag scans, valuation, catalysts and evidence, and it adapts to A-share, US and global markets, with anti-hallucination rules against inventing facts.
Output rules require a professional research report in natural Chinese that keeps the method implicit, writes risks before upside, adds a section on what would disprove the thesis, and ends with an independent review. Separate templates cover single stocks and whole sectors.
When your agent uses it
- Analyzing the supply chain behind a theme such as AI hardware
- Looking for bottleneck layers that the market may have mispriced
- Producing a risk-first research report on one company
- Stress-testing a thesis with a falsification section
Example prompts
- “Use Serenity's approach to look at the supply chain behind AI data center networking.”
- “Run a single-stock report on this small-cap optical component maker, risks first.”
- “What would falsify the bottleneck thesis for this company?”
Requirements
- Access to current market and filing data
Workflow steps
9 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 1eeb91f. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
nodepython3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Serenity Supply Chain Bottleneck Research loads about 2.4k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 880 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from yux1azhengye/BestSerenitySkillFromAT at commit 1eeb91f, republished under its MIT licence (© yux1azhengye). 880 words, ~2,383 tokens.
Download SKILL.mdSave it as
.claude/skills/serenity-unified-skill/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.- name
- serenity-unified-skill
- description
- Serenity 供应链卡点投资统一框架 v3.0。整合 10 个 GitHub 仓库精华， 含九步工作流、好卡点判据、防幻觉机制、A 股/美股/全球市场适配。 触发词: "/serenity"、"用 Serenity 的方式看"、"供应链/卡点/瓶颈分析"
- license
- MIT
- metadata.author
- Unified from 10 public repositories
- metadata.version
- 3.0.0
- metadata.last_updated
- 2026-06-07
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
skills/serenity-unified/templates/single-stock-report.md)；一条赛道/板块 -> 赛道报告结构 (见skills/serenity-unified/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。
3. 排版克制: 加粗只标真结论/关键数字/转折。密度控制: 每 500 字不超过 3 处加粗。少用嵌套括号和破折号链。
行业术语 (投资/半导体/光通信/AI，如 TAM、P/E、InP、AI-RAN、design-win) 一律保留，不强行翻译。要清掉的只有系统自己的特异黑话。
九步工作流 (分阶段对话，别一次性全倒)
Step 0 范围门 -> Step 1 锁周期+画栈 -> Step 2 卡点定位+判据
-> Step 3 红旗扫描 -> Step 4 估值+预期空间 -> Step 5 催化剂+证据
-> Step 6 综合判定 -> Step 7 独立复核 -> Step 8 仓位逻辑 (追问才给)Step 0: 范围门 (Scope Gate)
用户含糊时最多问 3 个短问题: (1) 市场/地域? (2) 主题/赛道? (3) 时间窗口? 默认值: 超级趋势 = AI 基础设施建设；周期 = 6-18 月；地域 = 全球。如果 scope 不在 AI 基础设施 (如新能源、生物医药)，显式说明 "本框架针对供应链物理卡点设计，对该领域判断力可能较弱"。
Step 1: 锁周期 + 画栈
锁周期: 它在哪个 supercycle? 早段还是中段? 只追结构性周期，不追单日新闻瓶颈。落到一台具体机器 (GB300 NVL72 / TPU pod / 1.6T 光链 / AI factory 供电)。
画栈: 画 6-9 层栈 (终端 -> 网络 -> 模组 -> 器件/激光 -> 测试 -> 代工/封装 -> 外延/设备 -> 材料/衬底)；顺已知供货关系逐跳推上游；用 OSINT 线索 (官网供应商增删/CFO 失言/生态 PPT/RFQ/投资 deck/收购继承) 推断未公开关系。问: 这层明天停产，下游要等几周/几季/几年? 再往底层钻: module -> device/laser -> epiwafer -> substrate -> feedstock -> 原料现货；是不是 single point of failure? 有无叠加地缘单卡?
供应链地图参考:
skills/serenity-unified/knowledge/supply-chain-map.md
Step 2: 卡点定位 + 判据 (满足越多信念越高)
9 条好卡点判据 (从原 14 条精简合并):
| # | 判据 | 核心维度 |
|---|---|---|
| 1 | 垄断性/不可替代性 | 结构性垄断/SPOF、单一供应商或寡头、技术壁垒 (专利/know-how)、无备选方案、产能建设周期长 (2-5 年) |
| 2 | 极小市值 vs 巨大下游 TAM | Sub-$2B 才有 10x；市值 vs 下游 BOM/TAM 的比值 |
| 3 | designed-in + 多客户 | 在多条链反复出现 = toll booth；定型锁死后替换成本高 |
| 4 | 认证周期未反映营收 | 量产在 2027 -> 现在财报必然难看 = 错杀 |
| 5 | 资产负债表能活到放量 | 现金跑道 vs 烧钱速度；toxic 负债 = 红旗 |
| 6 | 供需严重失衡 | demand >> supply、大客户全包产能、backlog 去风险 |
| 7 | 政策/地缘护城河 | 国安护城河、Made in America、国内自给率低 (A 股特色)、出口管制/制裁壁垒 |
| 8 | 机构低配 + 下行保护 | 机构持股 <40% (上行空间，>$5-10B 大盘失效)；净现金 ≈ 市值 (下行保护) |
| 9 | 估值安全边际 | 当前价格相对内在价值有折价；好卡点已被过度炒作到 100x forward P/E 就不是好卡点 |
新增 #9 "估值安全边际" 和 #1 中合并了原 1/7/10/11 的重叠项。
Step 3: 红旗扫描 (命中即降级/否决)
- 无限 ATM 增发稀释 = 硬否决 (区分: 战略投资/可转债/已 priced in 的稀释是绿旗)
- 单一客户集中
- toxic 负债撑不过爬坡
- 零收入纯炒作
- 中国敞口 (原则性排除) [美股特色] — 细分: 收入依赖中国 vs 供应链依赖中国 vs 仅在中国销售，颗粒度越细判断越准
- 技术太远 (2028+)
- 纯软件无硬卡点
- 大市值已无不对称
- brand 假合作
- A 股特色红旗: 蹭热点 (有业务但不是主营)、国内竞争格局分散无护城河、产能扩张太容易 (壁垒低)、无机构关注 (日均成交额 <5000 万 = 流动性陷阱)
- 管理层诚信红旗 (新增): 管理层频繁更换 CFO、审计师辞职、SEC/CSRC 调查、历史财务造假
- 技术路线变更风险 (新增): 卡点依赖特定技术路线 (如 InP 衬底)，若下游转向替代方案 (如硅光替代 InP) 则 thesis 崩塌
Step 4: 估值 + 预期空间 (decision-neutral，必出)
先判类型再套尺子:
| 类型 | 方法 | 硬阈值 |
|---|---|---|
| 超成长 | forward revenue/ARR / 市值 + 高毛利；自己算 forward P/E | 单位数 fwd P/E = 极便宜；$WMT 40PE = 贵的反向锚 |
| 紧缺卡点 | capacity ≈ revenue + 同层同行倍数差 + 历史卡点价格曲线 | 别用传统 P/S P/E |
| 深价值 | P/E、EV/FCF、净现金占比、book | - |
估值法 (连续退化，不硬分 case):
- 可比 peer 质量高 (同子行业 + 同商业模式 + 相近毛利/增速) -> 主用 A 相对估值
- 可比 peer 质量低/无 peer -> 退化加重 B 份额跨层法
- 多数标的两套都跑、按可比度加权
A. 相对估值: 客观对标 gap (P/E、forward P/E、EV/S、PEG，同源且时间差不超过 7 天) -> 显式加权层 (±% 必须锚到市场可观察溢价，找不到依据就不给数字) -> 合成 bear/base/bull (绑死假设: 对标谁/几倍/哪年)；bull 允许标 "滚动到 FY+2 营收" 作上沿；加权后 bull <= 客观 gap 的 1.5 倍。
B. 份额 + 跨层法: 定位环节 -> 估蛋糕 (份额 = 营收 / TAM，分子绑一手源，TAM 分母双源三角) -> 跨层/类比对标 (须给 "凭什么可比" 桥接 + 正反成对锚) -> 合成 bear/base/bull + 一行敏感性 ("TAM 估错一半，区间塌到哪")。TAM 层级必须与分子层级一致；跨层 TAM 不计入双源、只作上界旁注。单源或仅跨层 -> 标 [推测] 且禁入 bull。
通用纪律:
- 输入分级标注
已证实 / 管理层声称 / 我的推断 / 纯推测 - 精度降级: 关键假设 (影响最终估值区间上下沿超过 20% 的假设) 里 >=1 个标
[推断]/[推测]-> 输出从具体百分比强制降级为 "数量级/方向" - 诚实门: 无可信对标/太早期 -> 直接说 "区间太宽，不给假精确"
- 别抄分析师目标价当标尺 (共识 PT 仅作 positioning 旁证)
Show full SKILL.md (331 more words)Show less
Step 5: 催化剂 + 证据
催化剂 (走先行/衍生信号，不等财报): 上游原料现货价 / 相关公司财报电话会 cross-read / 大厂资本动作 / 行业会议 (GTC/OFC) / 政策法案 / 指数纳入。区分 "会不会发生" vs "何时发生"。
证据规则 (必须照做):
三桶: ① 公司 (财报/IR/客户供应商提及) ② 行业 (产能交期/部署) ③ 跨链 (多家从不同位置描述同一压力点 = 质量最高)。 强弱: 财报/transcript/IR > 供应商名单变更/design-win/扩产 > 产业报道/券商 > 社交帖。
取数纪律 (必做):
- 一手源强制清单: 营收结构/分部占比、客户集中度、backlog/订单、市值、净利/毛利、指引 -> 必须取最新 10-K/10-Q/8-K/IR 原值 + 标 as-of + 确认目标财年。聚合站/博客只作线索。
- 虚构守门 (双向): ① 先在一手源尽力找，找到标
已证实(把 10-K 已点名的真关系误标 "未点名" 和虚构同样是取数失真)；② 真搜过仍找不到才标[推断]/[推测]+ 注 "未找到一手源"。 - 时效守门: 为 backlog/订单/指引/并购/客户名单这类快变字段，专门搜一次 as-of 前 ~60 天的新 8-K/IR/新闻；>10% 客户名单必取最新财年 10-K。
- 跨标的倍数对比同源且时间差不超过 7 天 (原 "同源同日" 放宽)。
- 知识截止声明: 如果无法联网获取实时数据，显式声明知识截止日期，将基于训练数据的数字标为
[知识库 · 截止 YYYY-MM]。 - 铁律: 永远把
已证实 / 管理层声称 / 我的推断 / 纯推测分开标注；已证实必须有可引用一手源，否则一律降级。
A 股取数纪律 (巨潮资讯/业绩预告/问询函等) 详见
skills/serenity-unified/knowledge/market-adaptation.md
Step 6: 综合判定 "值不值得投" (核心交付)
跑完给结构化结论，不要含糊的 "各有优劣":
值不值得 = 卡点强度 (判据命中几条) x 错杀程度 (市值是否反映链上地位) x 证据成色 (强/中/弱) x 催化剂时点 (3 个月内 = 近、6 个月内 = 中、12 个月+ = 远) x 红旗 (有无硬否决) x 所处周期 (概念/认证/早期放量/真实放量)
多候选按 "集中度 x 不可替代 x 爬坡难度 x 需求证据 x 是否已被机构发现 (未发现 > 已 re-rate)" 排序。
适用边界 (必标): 市值远超 Sub-$2B 且已被充分发现的大盘: 显式声明 "本框架判断力弱"，给卡点真伪定性，不给买点。
Step 7: 独立复核 (必做，不可跳过)
给用户最终回复之前，对报告进行挑刺复核。复核立场是挑刺反驳，不是背书:
有 sub-agent 环境 (支持 Task/Agent 工具时): 派一个独立 reviewer sub-agent (使用当前可用的最强推理模型，全新上下文) 复核。
无 sub-agent 环境 (Desktop/手机/大多数对话环境): 对报告中的每个关键数字逐一进行自问自答式复核:
- "这个数字的来源是什么？是否是一手源？是否是最新数据？"
- "卡点判据的命中是否有依据支撑，还是主观判断？"
- "估值对标的选择是否有挑肥拣瘦？"
- "bear/风险段是否写在 bull 段之前？"
- "是否有内部黑话/生造词外泄？加粗是否泛滥？"
在报告末尾标注 [自查复核，非独立实例] 或 [独立复核: 通过]。有 load-bearing 错误先改再发。复核没过别硬发——宁可标 [未核实] 或降低定档。
复核清单 (5 项):
- 查编造/取数: 每个可度量数字有一手源？专盯: 二手/过时数据当
已证实、虚构关系、快变字段是否过时、重大遗漏 - 查逻辑 + 反偏误: 判据/红旗/估值尺子用对没？结论与事实自洽？有无确认偏误？份额法 TAM 双源？含
[推断]假设是否已精度降级？每个候选是否都点了 >=1 条判据或红旗？ - 查迎合: 结论是否迎合用户倾向？用户有方向性暗示时反向加压
- 查可读性: 有无英文黑话整段没解释、英式句法、生造词/内部代号外泄、加粗泛滥
- 裁决: pass / revise (列具体问题 + 纠正值)
Step 8: 仓位逻辑 (用户问才给)
权重跟执行确定性走不跟叙事 (龙头/已验证执行者重仓，早期未商业化小起步仓，认证/放量改善才加仓)；仓位匹配波动承受力；离场 = thesis 论点破裂才卖，不因价格。
语气 (可选薄层，默认关)
默认用朴素、怀疑、聚焦卡点的分析师口吻。仅当用户明确要 "用他的味儿" 时，才叠加招牌短语——语气是表层，方法论才是主体。
参考知识库 (按需引用，非执行指令)
以下文件包含详细的参考资料，在分析过程中按需查阅:
| 文件 | 内容 | 何时查阅 |
|---|---|---|
skills/serenity-unified/knowledge/market-adaptation.md | A 股/美股/全球市场适配、取数纪律、工具箱 | 分析非美股市场时 |
skills/serenity-unified/knowledge/mental-models.md | 心智模型、决策启发式、表达 DNA、诚实边界 | 需要认知框架参考时 |
skills/serenity-unified/knowledge/supply-chain-map.md | AI 基础设施/光子学/半导体供应链地图 | 画栈和定位卡点时 |
skills/serenity-unified/templates/single-stock-report.md | 单股报告结构和定档量化标准 | 输出单股分析时 |
skills/serenity-unified/templates/sector-report.md | 赛道报告结构 | 输出赛道/板块分析时 |
数据增强 (可选模块)
注意力雷达 (lanfuli/aleabito-serenity-skills)
基于 6,120 条帖子的实证分析。提供注意力动量 (升温标的、新进、重仓核心、主题轮动)。候选发生器 + 检查清单，不是预言机。
node skills/follow-aleabito/scripts/analyze-mentions.js --incremental
node skills/serenity-radar/scripts/radar.js --window 14 --top 12风险: 幸存者偏差、单账号脆弱性。
本地数据库 (haskaomni/serenity)
完全本地化运行 + Web Dashboard 可视化。
python3 scripts/ingest.py all --max-pages 10 --days 500 --min-mentions 3
python3 scripts/server.py --port 8787版本历史
v3.0.0 (2026-06-07)
- 模块化拆分: 核心指令 ~200 行 + knowledge/ + templates/ 子目录
- 工作流从 12 步精简为真正的 9 步 (合并估值+预期空间、催化剂+证据)
- 好卡点判据从 14 条精简为 9 条 (消除重叠，新增 "估值安全边际")
- 五档买卖定档增加量化触发条件参考
- 独立复核机制简化: 无 sub-agent 环境提供可操作的自问自答式复核
- 补充 A 股取数纪律平行版本 (巨潮资讯/业绩预告/问询函)
- 红旗扫描新增 "管理层诚信" 和 "技术路线变更风险"
- 中文表达规范改为密度控制 (每 500 字不超过 3 处加粗)
- "同源同日" 放宽为 "同源且时间差不超过 7 天"
- 新增知识截止日期声明规则
- metadata.sources 统一为 10 个仓库
v2.0.0 (2026-06-06)
- 初始统一版本，整合 8 个公开仓库精华
许可证
MIT — 随便用，随便改，随便造。方法论提炼内容供个人学习/研究使用。
© yux1azhengye, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 10 other files in the repository root of yux1azhengye/BestSerenitySkillFromAT.
- SKILL.md
- .gitignore
- BestSkillFromAT.png
- FINAL_UNIFIED_SKILL.md
- LICENSE
- README.en.md
- README.md
- SKILL.en.md
- docs/ANALYSIS_SUMMARY.md
- docs/DEEP_OPTIMIZATION_REPORT.md
- skills
Open the folder on GitHubat commit 1eeb91f
Compare with similar skills
Serenity Supply Chain Bottleneck Research next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Serenity Supply Chain Bottleneck Research this skillyux1azhengye/BestSerenitySkillFromAT | 511 | — | ~2.4k | Automated safety check: Pass | MIT | |
| AI-Trader Market IntelHKUDS/AI-Trader | 23k | — | ~1.1k | Automated safety check: Pass | None | |
| Eastmoney Market DataHKUDS/Vibe-Trading | 35k | — | ~1k | Automated safety check: Pass | MIT | |
| Stock Deep Analysis Workflowwbh604/UZI-Skill | 7.1k | — | ~9.1k | Automated safety check: Notes | MIT | |
| Zhengxi Fund Manager Views Librarylyra81604/zhengxi-views | 1.8k | — | ~1.6k | Automated safety check: Pass | MIT | |
| SEC EDGAR Filings FetcherHKUDS/Vibe-Trading | 35k | — | ~1.4k | Automated safety check: Pass | MIT |
Similar skills
Eastmoney Market Data
HKUDS/Vibe-Trading
Index of Eastmoney's free, no-token market data interfaces for China A-shares and Hong Kong stocks: fund flows, dragon-tiger lists, margin trading, reports and news.
Stock Deep Analysis Workflow
wbh604/UZI-Skill
Runs a staged deep analysis of a single stock on China A-share, Hong Kong and US markets, ending in an HTML report with valuation models and investor-panel scores.
Zhengxi Fund Manager Views Library
lyra81604/zhengxi-views
Answers questions with sourced quotes from one Chinese fund manager's public writings, applies his stated investment method and compares his words with real fund holdings.
SEC EDGAR Filings Fetcher
HKUDS/Vibe-Trading
Fetches U.S. SEC EDGAR data: resolves tickers to CIK numbers, lists recent 10-K, 10-Q and 8-K filings with document URLs, and pulls XBRL financial series.
Supply Chain Bottleneck Hunter
xbtlin/ai-berkshire
Scans a long-running industry trend for supply chain chokepoints, aiming to find second- and third-layer suppliers that the market has not yet priced in.
Related
Categories
Questions about Serenity Supply Chain Bottleneck Research
What does Serenity Supply Chain Bottleneck Research do?
A research framework for finding supply chain bottlenecks in equities, with a nine-step workflow, red-flag scans, risk-first reports and a falsification section. This skill, written in Chinese, packages a supply-chain bottleneck research method for equities, combining ideas from ten GitHub repositories into one framework. It states plainly that it is not investment advice, that it is an unofficial third-party distillation, and that the track record it refers to is self-reported and unaudited.
When should I use Serenity Supply Chain Bottleneck Research?
Serenity Supply Chain Bottleneck Research fits situations like: analyzing the supply chain behind a theme such as AI hardware; looking for bottleneck layers that the market may have mispriced; producing a risk-first research report on one company; stress-testing a thesis with a falsification section.
How do I install Serenity Supply Chain Bottleneck Research in Claude Code?
Run `npx skills add yux1azhengye/BestSerenitySkillFromAT --skill serenity-unified-skill -a claude-code`. Or copy the skill folder (the yux1azhengye/BestSerenitySkillFromAT repository) into .claude/skills/serenity-unified-skill in your project. Claude Code loads it when a task matches its description.
How do I install Serenity Supply Chain Bottleneck Research in Codex?
Run `npx skills add yux1azhengye/BestSerenitySkillFromAT --skill serenity-unified-skill -a codex`. Or copy the skill folder (the yux1azhengye/BestSerenitySkillFromAT repository) into .agents/skills/serenity-unified-skill in your project. Codex loads it when a task matches its description.
Can I use Serenity Supply Chain Bottleneck Research in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add yux1azhengye/BestSerenitySkillFromAT --skill serenity-unified-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/serenity-unified-skill, .gemini/skills/serenity-unified-skill, .github/skills/serenity-unified-skill and .opencode/skills/serenity-unified-skill in your project.
What does Serenity Supply Chain Bottleneck Research need to run?
Going by SKILL.md and its folder, Serenity Supply Chain Bottleneck Research needs the command-line tools its instructions call (node and python3). Our summary lists: Access to current market and filing data.
Does Serenity Supply Chain Bottleneck Research access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Serenity Supply Chain Bottleneck Research safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Serenity Supply Chain Bottleneck Research use?
Serenity Supply Chain Bottleneck Research is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Serenity Supply Chain Bottleneck Research use?
About 2.4k tokens (SKILL.md is roughly 9.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Serenity Supply Chain Bottleneck Research?
Skills that share tags, products or a category with Serenity Supply Chain Bottleneck Research: AI-Trader Market Intel (HKUDS/AI-Trader, 23k stars), Eastmoney Market Data (HKUDS/Vibe-Trading, 35k stars), Stock Deep Analysis Workflow (wbh604/UZI-Skill, 7.1k stars) and Zhengxi Fund Manager Views Library (lyra81604/zhengxi-views, 1.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Serenity Supply Chain Bottleneck Research?
yux1azhengye (a GitHub user) maintains it in yux1azhengye/BestSerenitySkillFromAT, which has 511 GitHub stars. The repository was last updated on June 24, 2026.
Source: yux1azhengye/BestSerenitySkillFromAT on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.