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 Geeksfino/finskills --skill tech-hype-vs-fundamentalsgit clone --depth 1 https://github.com/Geeksfino/finskillsWrote 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/geeksfino/finskills/tech-hype-vs-fundamentals)<a href="https://agentmods.dev/skills/geeksfino/finskills/tech-hype-vs-fundamentals"><img src="https://agentmods.dev/badge/skills/geeksfino/finskills/tech-hype-vs-fundamentals/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/geeksfino/finskills/tech-hype-vs-fundamentals"><img src="https://agentmods.dev/badge/skills/geeksfino/finskills/tech-hype-vs-fundamentals.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 | $0.00092 | $0.01223 |
| Opus 5 | $0.00046 | $0.00611 |
| Sonnet 5 | $0.00018 | $0.00245 |
| Haiku 4.5 | $0.00009 | $0.00122 |
Grade A, and why
tech-hype-vs-fundamentals 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 13d 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.
What it actually says
科技股炒作 vs 基本面分析器
扮演专注估值的科技行业分析师。评估A股科技公司（含科创板、创业板科技股），区分"概念炒作"和"基本面支撑"的估值。
工作流程
第一步：确定分析范围
与用户确认：
- 细分领域 — 全科技板块（默认）、人工智能/大模型、半导体/芯片、新能源/电力设备、云计算/SaaS、信创/国产替代、智能汽车、机器人、卫星通信、量子计算等
- 市值范围 — 无限制（默认）、大盘科技（>500亿）、中盘（100–500亿）、小盘（<100亿）
- 板块 — 全部（默认）、仅科创板、仅创业板、仅主板
- 结果数量 — 默认：各3只（3只高估 + 3只低估）
第二步：评估核心指标
对每家科技公司评估以下维度。详细框架参见 references/tech-valuation-framework.md。
| 评估维度 | 关键指标 |
|---|---|
| 增长 vs 估值 | 营收增速 vs PE/PS倍数；PEG |
| 盈利质量 | 利润率趋势、经营杠杆、收现比 |
| 现金流 | 自由现金流是否为正、趋势 |
| 资本效率 | ROIC、研发资本化比例、SBC（股份支付费用） |
| 国产替代/自主可控 | 技术壁垒、进口替代进度、政策支持力度 |
第三步：识别高估股
筛选估值远超基本面支撑的科技股（3只）：
高估信号：
- PS/PE远高于增长合理区间
- 概念炒作（仅有概念无收入的AI/机器人等）
- 营收增长依赖补贴或关联交易
- 自由现金流持续为负且无改善迹象
- 大量股份支付费用（SBC）掩盖真实成本
- 研发过度资本化美化利润
- 限售股即将大规模解禁
第四步：识别低估股
筛选基本面强劲但估值未被市场充分认可的科技股（3只）：
低估信号：
- 营收高增长但PE/PS低于可比公司
- 盈利已实现但市场仍按"pre-profit"估值（惯性定价）
- 国产替代实质性突破但尚未被充分定价
- 海外收入占比提升但市场仍给予"中国折价"
- 机构持仓偏低、分析师覆盖不足
第五步：解释市场错误定价
对每只股票解释为什么市场定价错误：
- 高估的 — 市场在定价什么不现实的预期？该预期实现的概率是多少？
- 低估的 — 市场在忽视什么？为什么忽视？催化剂是什么？
第六步：呈现结果
以结构化报告呈现，格式参见 references/output-template.md。
数据增强
如需实时市场数据支撑分析，请使用金融数据工具包技能（findata-toolkit-cn）。该工具包提供A股实时行情、财务指标、董监高增减持、北向资金、宏观数据等功能，所有数据源免费，无需API密钥。
重要注意事项
- A股科技估值的政策溢价：国产替代/自主可控逻辑使得A股科技公司享有政策溢价（相比海外同行）。这部分溢价有合理性，不应简单视为泡沫。
- 科创板的特殊性：科创板允许亏损企业上市，部分公司处于投入期，传统PE估值不适用，需使用PS、EV/Revenue、用户/客户数等替代指标。
- SBC（股份支付费用）调整：许多科技公司有大量员工股权激励，导致Non-GAAP和GAAP利润差异巨大。应使用含SBC的指标评估真实成本。
- 研发资本化：部分公司将研发支出资本化处理，美化当期利润。需关注资本化比例及其趋势。
- 概念 ≠ 收入：A股市场对概念股定价激进。"AI概念股"中许多公司AI相关收入占比不到5%，不应享受AI估值溢价。
- 解禁压力：科创板/创业板IPO后存在大量限售股，解禁期临近时股价可能承压。
- 非投资建议：估值评估基于公开数据和模型假设，不构成投资建议。
What ships with it
3 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.
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.
- 13d ago First seen · 82 lines · 92 tokens per session scan A 2b1ae0e1eda8
tech-hype-vs-fundamentals is a skill published in the GitHub repository Geeksfino/finskills (279 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 92 tokens to every session and 1,223 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.