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 Haochenhust/ch-skills --skill industry-chain-researchgit clone --depth 1 https://github.com/Haochenhust/ch-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/haochenhust/ch-skills/industry-chain-research)<a href="https://agentmods.dev/skills/haochenhust/ch-skills/industry-chain-research"><img src="https://agentmods.dev/badge/skills/haochenhust/ch-skills/industry-chain-research/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/haochenhust/ch-skills/industry-chain-research"><img src="https://agentmods.dev/badge/skills/haochenhust/ch-skills/industry-chain-research.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 | $0.00126 | $0.01428 |
| Opus 5.5 | $0.00050 | $0.00571 |
| Sonnet 5.5 | $0.00025 | $0.00286 |
| Haiku 4.5 | $0.00013 | $0.00143 |
Grade A, and why
industry-chain-research 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 2mo 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
产业链研究（Industry Chain Research）
从一个宏观趋势出发，沿产业链逐层下钻，定位瓶颈环节和具体标的，最终输出可执行的投资研究报告。
方法论来源
前 RISC-V Foundation 成员、AI 研究科学家的公开方法 + 王鹏景气度投资四阶段模型。
工作流
四个阶段，每阶段结束后与用户确认方向再继续。
Phase 1 — 产业链地图（Chain Mapping）
用户给出宏观趋势/主题。AI 执行：
- 用
web-accessskill 搜索最新产业动态 - 拆解完整产业链（上游原材料 → 中游制造 → 下游应用）
- 标注每个环节供需状态：
充裕/紧平衡/瓶颈 - 输出 Mermaid 产业链地图
交互点：展示地图，问用户对哪个瓶颈环节最感兴趣。
Phase 2 — 瓶颈下钻（Bottleneck Drill-down）
对用户选定的环节深入拆解：
- 子产业链结构（核心零部件、工艺、材料）
- 哪一段最难扩产？为什么？
- 全球和 A 股供应商清单：公司名、代码、市值、市占率、核心客户
- 是否已进入头部客户供应链？
输出：候选公司清单（聚焦 A 股上市公司）。
Phase 3 — 交叉验证（Cross Validation）
对每个候选标的做五维验证（详见 REFERENCE.md）：
- 瓶颈持续性 — 技术替代风险？替代方案进展？
- 竞争壁垒 — 壁垒来源？追赶者距离？
- 收入兑现 — 订单→收入周期？新业务占比？
- 风险因素 — 减持/增发？地缘？管理层？
- 估值合理性 — 当前 price in 几年？下行空间？
输出：风险验证摘要，标注每个标的为 强烈关注 / 值得跟踪 / 暂时回避。
Phase 4 — 市场阶段判断（Phase Assessment）
判断市场对该产业的认知阶段，给出对应的选股建议：
| 阶段 | 市场特征 | 策略 |
|---|---|---|
| 1 分歧期 | 趋势初现，多空争论 | 买龙头，确定性优先 |
| 2 共识期 | 逻辑被验证，资金涌入 | 找供需错配最大的细分环节 |
| 3 压制期 | 预期透支，估值高位 | 只看二线弹性或新催化 |
| 4 泡沫期 | 全民讨论，故事代替逻辑 | 回避或只做交易 |
输出 — 研究报告
汇总 Phase 1-4 内容，生成结构化报告，用 lark-doc skill 发布到飞书云文档。
报告结构见 REFERENCE.md。
数据源
wechat-article-feeds（微信公众号文章）
本地存储路径：apps/天演资本/wechat-article-feeds/{公众号名称}/{YYYY-MM-DD}-{标题}.md
订阅了 ~22 个财经类公众号（猫哥读研报、调研纪要更新、聪明投资者、搬砖小组 等），每篇文章含 YAML frontmatter（title, author, date, URL, summary）+ Markdown 正文。
在产业链研究中的用法：
- Phase 1（产业链地图）：搜索公众号文章中关于目标产业的分析，获取国内视角的产业链拆解和景气度判断
- Phase 2（瓶颈下钻）：搜索特定环节的深度研报、调研纪要，获取一手的供需数据和公司调研信息
- Phase 3（交叉验证）：用不同公众号的分析交叉印证，避免单一信源偏见
搜索方式：直接用 Grep 工具在 apps/天演资本/wechat-article-feeds/ 目录下搜索关键词。
东方财富研报中心（券商研报）
通过 web-access skill 访问东方财富研报中心，获取券商研报原文和摘要。
搜索入口：https://reportapi.eastmoney.com/report/list?industryCode=&pageSize=50&industry=关键词&beginTime=起始日期&endTime=结束日期
在产业链研究中的用法：
- Phase 1（产业链地图）：搜索行业研报，获取券商对产业链的专业拆解和景气度评级
- Phase 2（瓶颈下钻）：搜索细分环节的深度研报，获取供需数据、产能统计、公司覆盖
- Phase 3（交叉验证）：查看目标公司的最新研报，获取盈利预测、目标价、风险提示
What ships with it
1 file 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.
- 2mo ago First seen · 106 lines · 126 tokens per session scan A 2388382bd6f8
industry-chain-research is a skill published in the GitHub repository Haochenhust/ch-skills (9 stars, last pushed 3mo ago), licensed MIT. It adds 126 tokens to every session and 1,428 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-31.
industry-chain-research compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| industry-chain-researchHaochenhust/ch-skills | Skill | 9 | 3mo ago | MIT | A | 126 | Claude Code, Codex |
| rugpull-detectorDjordjeMojsilovic/Djordjes-Claude-Setup | Skill | 4 | 3mo ago | none | A | 205 | Claude Code, Codex |
| ma-playbookalirezarezvani/claude-skills | Skill | 29k | yesterday | MIT | A | 29 | Claude Code |
| fiscalisteromainsimon/paperasse | Skill | 2.6k | yesterday | MIT | A | 320 | Claude Code, Codex |
| comptableromainsimon/paperasse | Skill | 2.6k | yesterday | MIT | A | 153 | Claude Code, Codex |
| syndicromainsimon/paperasse | Skill | 2.6k | yesterday | MIT | A | 204 | Claude Code, Codex |
| prompt-masternidhinjs/prompt-master | Skill | 16k | 15d ago | MIT | B | 78 | Claude Code, Codex |