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 agentmods add skills/feicoder/skill-factory/multi-factor-modelnpx skills add FeiCoder/Skill-Factory --skill multi-factor-modelgit clone --depth 1 https://github.com/FeiCoder/Skill-FactoryWhat 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 | $0.00065 | $0.02925 |
| Opus 5 | $0.00032 | $0.01463 |
| Sonnet 5 | $0.00013 | $0.00585 |
| Haiku 4.5 | $0.00006 | $0.00293 |
Grade A, and why
multi-factor-model 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 2d 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 — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
多因子选股模型
概述
多因子模型是应用最广泛的选股模型之一。其核心思想是：采用一系列因子作为选股标准，满足这些因子的股票则被买入，不满足的则卖出。
多因子模型相对来说比较稳定，因为在不同市场条件下，总有一些因子会发挥作用。
何时使用此技能：
- 当需要构建系统化的选股策略时
- 当需要综合多个指标进行选股时
- 当需要构建长期稳健的Alpha收益时
理论基础
有效市场假说与因子
市场上的投资者（价值投资者、投机者、短线交易者）都会根据某些因子来判断股票的涨跌。当有一群交易者同时采用某个因子时，就会造成该因子有效。
例如：当很多投资者认为低PE的价值型股票是好的投资标时，他们纷纷买入低PE股票，会使得该股票出现上涨或超越大市。这样就使得低PE因子的有效性得到体现。
两种判断方法
| 方法 | 原理 | 优点 | 缺点 |
|---|---|---|---|
| 打分法 | 根据各个因子大小对股票打分，按权重加权得到总分 | 相对稳健，不易受极端值影响 | 不能及时调整敏感性 |
| 回归法 | 用过去收益率对因子回归，预测未来收益 | 能及时调整敏感性，不同股票敏感性可不同 | 易受极端值影响 |
推荐：初学者使用打分法，熟练后可尝试回归法
模型构建五步法
第一步：候选因子选取
候选因子类型及示例：
| 类别 | 因子 | 说明 |
|---|---|---|
| 估值因子 | PE、PB、PS | 市盈率、市净率、市销率 |
| 成长因子 | 净利润增长率、营收增长率、EPS增长率 | 盈利增长速度 |
| 盈利因子 | ROE、ROA、毛利率、净利率 | 盈利能力 |
| 规模因子 | 总市值、流通市值 | 公司大小 |
| 动量因子 | 20日涨跌幅、60日涨跌幅 | 过去价格表现 |
| 波动因子 | 日收益率标准差 | 价格波动程度 |
| 预期因子 | 分析师一致预期、盈利预测 | 市场预期 |
| 宏观因子 | GDP增速、M2 | 经济环境 |
选取原则：
- 因子必须有经济意义
- 因子必须具备显著的预测能力
- 更多和更有效的因子能增强信息捕获能力
第二步：因子有效性检验
检验方法：排序法
Step 1: 在每个月初计算每只个股的各因子指标
Step 2: 按因子大小从小到大排序，平均分为n个组合（建议5个）
Step 3: 持有至月末，下月初重新构建组合
Step 4: 重复到模型形成期末
有效性判断标准（三个条件）：
-
排序关系：组合因子大小与收益应具有较大相关性
- 因子越小收益越高：x₁ < x₂ < ... < xₙ 应导致 r₁ > r₂ > ... > rₙ
- 或因子越大收益越高：反向关系
-
超额收益：极端组合应有显著超额收益
- max(Ri - Rb) > 最小超额收益阈值
- min(Ri - Rb) < 最大负超额收益阈值
-
胜率：不同市场环境下高收益组合跑赢基准概率高
关键指标：
| 指标 | 含义 | 合格标准 |
|---|---|---|
| 年化复合收益 | 组合的实际收益 | 最高组合 > 最低组合 |
| 超额收益 | 相对于基准的收益 | > 5% |
| 跑赢概率 | 跑赢基准的月份占比 | > 60% |
第三步：冗余因子剔除
问题：不同因子可能由于内在驱动因素相同，所选出的组合高度一致，需要剔除冗余因子。
剔除步骤：
Step 1: 对不同因子下的n个组合打分（收益越大分值越高）
Step 2: 按月计算个股因子得分间的相关性矩阵
Step 3: 计算整个样本期内相关性矩阵的平均值
Step 4: 设定阈值（通常0.5），超过阈值的因子只保留有效性最强的
案例：盈利收益率与PEG相关性0.89 → 只保留盈利收益率
第四步：综合评分模型
构建方法：
Step 1: 选取去除冗余后的有效因子
Step 2: 每月初计算每只股票的各因子得分
Step 3: 按权重加权求平均分
Step 4: 按总分排序，选取排名靠前的股票
可选参数：
- 选取得分最高的前20%股票
- 或选取得分最高的50~100只股票
注意：
- ST/PT股票应剔除
- 如因子无法取值，该因子不参与平均
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.
- 2d ago First seen · 296 lines · 65 tokens per session scan A f3d1e17027c8
multi-factor-model is a skill published in the GitHub repository FeiCoder/Skill-Factory (10 stars, last pushed 6mo ago), licensed MIT. It adds 65 tokens to every session and 2,925 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…