Borrowing it
Nothing to install: this file belongs to spy007111/Vibe-Research. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/spy007111/Vibe-Research/main/.agents/skills/industry-chain/SKILL.mdgit clone --depth 1 https://github.com/spy007111/Vibe-ResearchWrote 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/spy007111/vibe-research/industry-chain)<a href="https://agentmods.dev/skills/spy007111/vibe-research/industry-chain"><img src="https://agentmods.dev/badge/skills/spy007111/vibe-research/industry-chain/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/spy007111/vibe-research/industry-chain"><img src="https://agentmods.dev/badge/skills/spy007111/vibe-research/industry-chain.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 | $0.00212 | $0.01931 |
| Opus 5.5 | $0.00085 | $0.00772 |
| Sonnet 5.5 | $0.00042 | $0.00386 |
| Haiku 4.5 | $0.00021 | $0.00193 |
Grade A, and why
industry-chain 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 26d 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.
This is a copy
100% identical to industry-chain — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
产业链下钻与不可替代性(industry-chain)
对应 研究宪法 投资哲学第一条——"在景气向上的行业里找不可替代的公司"——的操作手册。产业链结构是公开知识,挖出来不等于 alpha;本 skill 的价值在于把"不可替代性"从形容词变成带证据的标签,并给出它被市场定价程度的校准。
0. 三条纪律
- 每一条产业链事实(谁供谁、份额、产能、良率、认证进度、扩产周期)都要有证据 id(公告 / 研报 / 新闻 / 行业数据端点),说不出来源的写"待补",不凭印象填。
- 不可替代性标签只有四个值:
tech_moat(技术 / 工艺 / 专利 / know-how 别人短期追不上)/capacity_moat(工艺成熟度 / 产能布局 / 客户认证周期让对手赶不上,红利期内份额集中)/both/待补。每个标签后必须跟一句证据。 - 本 skill 只回答"它在链条哪一层、凭什么不可替代、市场定价到什么程度",不回答"买不买"。
1. 六步下钻(每一层问同样四个问题)
把公认的龙头当作"需求入口",不在龙头停留,沿供应链往上游走:
需求入口(整机 / 云厂 / 终端龙头)→ ① 关键部件 → ② 核心器件 / 芯片 → ③ 关键材料 → ④ 衬底 / 耗材 → ⑤ 设备 / 检测 → ⑥ 设备的核心零件
每一层四问:
- 不可替代吗?(技术 / 工艺 / 专利;或认证周期 / 产能爬坡期)
- 供给刚性吗?(扩产周期多长、良率爬坡多久、有没有替代路线、新进入者要多久)
- 集中度如何?(寡头 / 双寡头 / 分散;份额证据)
- 被看见了吗?(市值、研报覆盖数、一致预期机构数——"大家都知道"的卡口通常已经定价)
停在"不可替代 + 供给刚性 + 集中 + 关注度低"同时成立的那一层;A 股按"龙头 + 可研究到的最深一层"两条线并记(有无可交易标的只是事实记录,不是结论)。
2. 物理硬筛子(比商业叙事可靠的约束)
| 约束类型 | 看什么 | 证据来源(注册表端点示例) |
|---|---|---|
| 扩产周期 | 新产线从投资到满产要多久;设备交期 | 公告(fetch_announcements / cninfo_announcements)、研报(em_reports / em_industry_reports) |
| 良率 / 工艺成熟度 | 良率爬坡曲线、单位成本、批量稳定性 | 研报、公司互动问答(cninfo_irm)、新闻(em_stock_news / rss_news) |
| 认证周期 | 进入大客户 BOM 需要的验证时长、换供应商成本 | 公告、研报、行业新闻 |
| 替代路线 | 有没有技术路线切换会绕开这一层(路线断层风险) | 行业研报、海外同行(yahoo_news / sec_filings 等) |
| 物料 / 资源垄断 | 全球供给是否集中于少数地区 / 企业(中国独有物理卡口:部分稀土永磁、特种化工材料) | 行业数据、宏观端点 |
| 行业归属与景气 | 行业分类、同行对比、景气方向 | sw_industry、em_industry_comparison、em_concept_blocks |
物理不撒谎:优先用"扩产周期 / 良率 / 认证周期"这类可核的约束,而不是"品牌 / 生态 / 赛道好"这类叙事。
3. 校准:卡口越硬越贵
- 卡口的不可替代性一旦被广泛认知,估值会把它计价完("卡口越硬越贵");本 skill 的标签要与 valuation 的 PEG / 分位一起看:硬卡口 + 高 PEG 是常态,不是机会信号。
- 预期差四问(判断"方向新"维度有没有预期差):① 方向新吗(认知未形成)② 会供不应求吗(需求新增 × 供给刚性)③ 本市场有标的吗 ④ 已经炒过了吗(最关键——多数热门方向卡在这一问)。识别信号:需求侧"路线切换 / everyone betting on";供给侧"售罄 / 交期拉长 / 涨价函"。
- 默认假设与证伪:对任何"新方向",先假设它已被市场定价,再用 ④ 问去证伪——证据是该方向相关标的的涨幅 / 换手 / 研报覆盖数 / 一致预期修正(注册表端点可取),拿不到证据就写"定价程度待补",不凭印象下"已炒过 / 没炒过"的结论。在此前提下可用的分析视角是:① 方向真 + 有订单兑现路径时,分析"兑现确定性";② 有实业、尚未被概念化的标的,分析"基本面与定价的差距";③ 赛道已全部计价时,只比较"业绩兑现度 + 增速能否消化估值"(回到 valuation 口径)。这三条是分析框架,用于组织证据与裁决点,不是筛选或买卖指令。
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.
- 26d ago Changed c6fae25d3f6a
- 1mo ago First seen · 68 lines · 212 tokens per session scan A 70c65a93a620
industry-chain is a skill published in the GitHub repository spy007111/Vibe-Research (8 stars, last pushed 8d ago), licensed MIT. It adds 212 tokens to every session and 1,931 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to industry-chain, differing in 0 lines, and is treated as a copy.
industry-chain compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| industry-chainspy007111/Vibe-Research | Skill | 8 | 8d ago | MIT | A | 212 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |