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 duolongworld/AI_Renaissance --skill company_evolution_analysisgit clone --depth 1 https://github.com/duolongworld/AI_RenaissanceWrote 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/duolongworld/ai_renaissance/company_evolution_analysis)<a href="https://agentmods.dev/skills/duolongworld/ai_renaissance/company_evolution_analysis"><img src="https://agentmods.dev/badge/skills/duolongworld/ai_renaissance/company_evolution_analysis/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/duolongworld/ai_renaissance/company_evolution_analysis"><img src="https://agentmods.dev/badge/skills/duolongworld/ai_renaissance/company_evolution_analysis.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 | $0.00232 | $0.11311 |
| Opus 5 | $0.00116 | $0.05656 |
| Sonnet 5 | $0.00046 | $0.02262 |
| Haiku 4.5 | $0.00023 | $0.01131 |
Grade A, and why
company-evolution-analysis 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 10d 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 — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Company Evolution Analysis（公司发展路径分析）
核心理念
这个 skill 的精髓是**"节点叙事"**——不要写流水账式的公司简介，也不要罗列财务数据，而是把一家公司的成长史看作一张不断被新版图填充的地图，每一次重大决策（并购、转型、控制权变更、技术突破）都是地图上新画的一块版图。你的任务是找出这些节点，逐个解构它们的内在逻辑，最终把它们串成一条清晰的能力升级路径，让读者明白"这家公司是怎么从 A 走到 B、又为什么必然会走向 C 的"。
参照样本（光库科技分析）展示了这种叙事的最佳实践：从澳门商人吴玉玲的初始资本，到王兴龙带来的战略定力，到收购加华微捷（2018）开启并购之旅、收购 Lumentum 米兰工厂（2020）完成芯片级卡位、华发国资入主（2021）解决资本焦虑、收购拜安实业（2024）布局车载激光雷达第二曲线、收购武汉捷普（2025）补全器件模块能力、收购安捷讯（2025）实现 OCS 全光交换的最后一块拼图。每个节点都不是孤立的，而是上一步的必然延伸和下一步的必要铺垫。
工作流程
第一步：必须主动联网搜索（不可跳过）
用户提到任何一家公司时，严禁凭模型记忆中的信息直接撰写分析。模型记忆中的公司信息往往不完整、可能过时、或在交易金额/日期等具体细节上出错——这对于一份以"节点真实性"为核心价值的分析报告是致命的。
必须按以下顺序进行多轮搜索（一般需要 12-20 次搜索调用，强化版需要 25 次以上——其中"最新财报锁定"和"新增长曲线深度搜索"两个板块各自至少占 4-6 次搜索）：
-
基础画像搜索 ——
[公司名] 创始人 历史、[公司名] 公司简介、[公司名] 主营业务 -
关键节点搜索 ——
[公司名] 并购、[公司名] 收购、[公司名] 融资、[公司名] 上市、[公司名] 控制权变更、[公司名] 转型 -
每个重大节点单独深挖 —— 一旦发现某次重大并购或转型，立即针对它单独搜索：
[公司名] 收购 [标的名] 交易细节、[标的名] 为什么卖、[公司名] 收购 [标的名] 估值 -
行业背景搜索 ——
[公司名] 所在行业 竞争格局、[公司名] 主要竞争对手、[公司名] 技术路线 -
最新财报数据强制锁定（硬性要求，绝不可妥协） —— 这一步是数据有效性的生死线，先确定当前日期再倒推应有的最新财报：
A. 时点对照表（中国 A 股 / 港股 / 美股节奏）：
- 1-4 月：必须取得上一年度年报数据（4 月底前后是 A 股年报披露截止），同时关注上一年三季报和当年一季度业绩预告
- 4-5 月：必须取得当年一季报数据（A 股一季报披露截止 4 月 30 日）；如果搜到的最新数据还是上一年三季报，那是严重失职
- 7-8 月：必须取得当年半年报或半年度业绩预告（中报披露截止 8 月 31 日）
- 10-11 月：必须取得当年三季报数据（三季报披露截止 10 月 31 日）
- 港股节奏不同（中报 + 年报为主），美股是季报，需对应调整
B. 强制搜索查询（不可跳过任何一条）：
[公司名] [当前年] 一季报/[公司名] [当前年] 半年报/[公司名] [当前年] 三季报/[公司名] [当前年] 年报——按时点选最新的那一份[公司名] 业绩预告 [当前年/季度]——预告往往比正式财报早 1-2 个月披露[公司股票代码] 最新业绩——直接用代码搜，效果常优于公司名[公司名] 季度环比——逼自己看到环比变化- 如果第一轮搜出的数据不是最新季度的，立即换关键词重搜，直到拿到最新季度数据为止；找不到则在报告中明确写出"截至 [报告日期] 公司最新披露的财报为 [XX]，[XXX] 季度数据尚未披露"
C. 必须提取并对比的财务指标（不止营收和净利润）：
- 三表核心：营业收入、归母净利润、扣非净利润——同比 + 环比都要列（环比对科技/周期行业比同比更说明问题）
- 盈利质量：综合毛利率、销售净利率——至少看最近 4-6 个季度的趋势而不是只看一年
- 现金流：经营活动现金流量净额——和净利润对比，差异大要追问原因
- 订单印证三件套（极重要、常被忽视）：
- 合同负债（旧称"预收款项"）：这是客户已付款但公司还没确认收入的部分，是未来 1-2 个季度营收的领先指标。环比大增 = 在手订单饱满；环比骤降 = 订单可能枯竭
- 预付款项：公司向上游供应商预付的款项，反映公司对未来产能/原料的备货意愿。环比大增 = 管理层判断需求要起来、提前锁原料；环比下降 = 收缩信号
- 存货：原材料 / 在产品 / 库存商品各自的环比变化，结合下游订单解读——是积压还是为大单备货
- 资本支出 / 在建工程：环比变化反映扩产节奏，要对得上公告里的募投项目进度
- 应收账款 + 应收账款周转天数：客户回款质量，对一些下游话语权强的行业（光伏、消费电子代工）尤其关键
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.
- 10d ago First seen · 400 lines · 232 tokens per session scan A 165b29ad473f
company-evolution-analysis is a skill published in the GitHub repository duolongworld/AI_Renaissance (59 stars, last pushed 13d ago), licensed Apache-2.0. It adds 232 tokens to every session and 11,311 once invoked, about $0.0012 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.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
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.