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 yuping322/financial-services-plugins-new --skill idea-generationgit clone --depth 1 https://github.com/yuping322/financial-services-plugins-newWrote 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/yuping322/financial-services-plugins-new/idea-generation)<a href="https://agentmods.dev/skills/yuping322/financial-services-plugins-new/idea-generation"><img src="https://agentmods.dev/badge/skills/yuping322/financial-services-plugins-new/idea-generation/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/yuping322/financial-services-plugins-new/idea-generation"><img src="https://agentmods.dev/badge/skills/yuping322/financial-services-plugins-new/idea-generation.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 | $0.00000 | $0.01117 |
| Opus 5 | $0.00000 | $0.00558 |
| Sonnet 5 | $0.00000 | $0.00223 |
| Haiku 4.5 | $0.00000 | $0.00112 |
Grade A, and why
idea-generation 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.
What it actually says
创意生成
描述：系统性股票筛选和投资创意寻源。结合定量筛选、主题研究和模式识别，以发现新的多头和空头创意。寻找新创意、运行筛选或进行主题扫描时使用。触发条件："创意生成"、"股票筛选"、"寻找创意"、"什么看起来有趣"、"筛选"、"新创意"或"给我推荐什么"。
工作流程
第 1 步：定义搜索标准
向用户要求参数：
- 方向：多头创意、空头创意或两者
- 市值：大盘股、中盘股、小盘股、微盘股
- 部门：特定部门或跨部门
- 风格：价值、增长、质量、特殊情况、事件驱动
- 地理位置：美国、国际、全球
- 主题：任何特定的主题角度（人工智能、回岸、老龄化人口等）
第 2 步：定量筛选
根据风格运行筛选：
价值筛选
- P/E 低于部门中值
- EV/EBITDA 低于历史平均水平
- 自由现金流收益率 >5%
- 价格/账面价值低于 1.5x
- 过去 90 天内的内部人员买入
- 股息收益率高于市场平均水平
增长筛选
- 收入同比增长 >15%
- 盈利同比增长 >20%
- 收入加速（增长率上升）
- 扩大的利润率
- 高投资资本回报率（>15%）
- 强劲的净保留率（SaaS >110%）
质量筛选
- 一致的收入增长（5+ 年）
- 稳定或扩大的利润率
- 净资产收益率 >15%
- 低债务/股本比率
- 高自由现金流转化率
- 内部人员所有权 >5%
空头筛选
- 收入下降或增长减速
- 利润率压缩
- 应收账款/库存相对销售额上升
- 内部人员卖出
- 估值溢价相对于同行而没有合理解释
- 空头兴趣高但基本面恶化
- 会计红旗（审计师更换、重述）
特殊情况筛选
- 最近的 IPO/SPAC，锁定期即将到期
- 过去 12 个月内的分拆
- 从重组中复苏的公司
- 激进股东参与
- 表现不佳公司的管理层变化
第 3 步：主题扫描
对于主题创意，研究主题并识别受益者：
- 定义论文（例如，"2026 年及以后人工智能基础设施支出加速"）
- 绘制价值链 — 谁直接获益，谁间接获益？
- 识别纯玩和多元化敞口
- 评估哪些名称已"价格化"vs低估
- 寻找市场尚未连接到主题的二阶受益者
第 4 步：创意呈现
对于通过筛选的每个创意，展示：
[公司名称] — [多头/空头] — [一句论文]
| 指标 | 价值 | vs 同行 |
|---|---|---|
| 市值 | ||
| EV/EBITDA (NTM) | ||
| P/E (NTM) | ||
| 收入增长 | ||
| EBITDA 利润率 | ||
| 自由现金流收益率 |
论文（3-5 条要点）：
- 为什么被错误定价
- 市场遗漏的是什么
- 实现价值的催化剂
关键风险：
- 什么会使这个创意错误
建议的后续步骤：
- 构建完整模型？深入尽职调查？专家电话？
第 5 步：输出
- 5-10 个创意的简称列表，附带单页摘要
- 已记录的筛选标准和方法
- 所有创意的比较表
- 优先列表：优先研究哪些创意
重要说明
- 筛选会产生候选，不是结论 — 每个筛选输出都需要基本面工作
- 最好的创意通常来自交叉点（例如，质量公司以价值价格出现，因为短期逆风）
- 避免拥挤的交易 — 检查所有权数据、空头兴趣和有多少分析师覆盖该名称
- 对立创意需要更高的确信度 — 时机更难，风险不对称
- 跟踪创意成功率随时间的变化 — 哪些筛选和方法会产生最好的创意？
- 空头创意需要更高的确信度 — 时机较难，风险不对称
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 · 112 lines · 0 tokens per session scan A 2f871ea32b64
idea-generation is a skill published in the GitHub repository yuping322/financial-services-plugins-new (17 stars, last pushed 6mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,117 tokens. 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.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.