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 maydengximin-sketch/amos-sem-workflow-skill --skill amos-sem-workflowgit clone --depth 1 https://github.com/maydengximin-sketch/amos-sem-workflow-skillWrote 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/maydengximin-sketch/amos-sem-workflow-skill/amos-sem-workflow)<a href="https://agentmods.dev/skills/maydengximin-sketch/amos-sem-workflow-skill/amos-sem-workflow"><img src="https://agentmods.dev/badge/skills/maydengximin-sketch/amos-sem-workflow-skill/amos-sem-workflow/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/maydengximin-sketch/amos-sem-workflow-skill/amos-sem-workflow"><img src="https://agentmods.dev/badge/skills/maydengximin-sketch/amos-sem-workflow-skill/amos-sem-workflow.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 | $0.00385 | $0.03417 |
| Opus 5 | $0.00192 | $0.01708 |
| Sonnet 5 | $0.00077 | $0.00683 |
| Haiku 4.5 | $0.00038 | $0.00342 |
Grade A, and why
amos-sem-workflow 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 11d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AMOS SEM 一条龙工作流
核心姿态
大多数人做 AMOS 的顺序是错的：先画图跑模型，跑不出来再回头查数据。
正确的顺序是——在进 AMOS 之前，先做一遍"达标预检验"。
数据不达标就进 AMOS，你会遇到：模型不收敛、载荷是负的、拟合指标怎么修都不过、Heywood case（负误差方差）。然后你就会开始"修正指数疯狂加路径"——这是审稿人一眼就能看出来的数据操纵。
这个 skill 的第一原则：把关口前移。
不要承诺"跑一遍就能发表"。不要用修正指数把模型硬拗到拟合。拟合好但没有理论支撑的模型，一文不值。
五个阶段
① 数据清洗
↓
② 达标预检验 ← 关键关口。不达标不许进 AMOS
↓
③ AMOS 自动绘图（Plugin）+ 自动分析（AmosEngine）
↓
④ 模型评估与修正 · 中介/调节/多群组
↓
⑤ APA 格式结果撰写
① 数据清洗
| 步骤 | 做什么 | 判定 |
|---|---|---|
| 反向计分 | 先做，别忘了 | 反向题必须转换后再算 α |
| 缺失值 | 检查缺失比例与模式 | < 5% 可处理；做 Little's MCAR 检验 |
| 单变量异常 | 标准化后 |z| > 3.29 | 逐个核查，不要无脑删 |
| 多变量异常 | Mahalanobis D²，p < .001 | 删除需说明理由与数量 |
| 无效样本 | 规律作答、极短作答时间、全选同一选项 | 事先定规则 |
详见
references/01-data-cleaning.md
② 达标预检验（进 AMOS 前必过的关）
这是整个工作流最有价值的一步。 逐项检查，任何一项不达标 → 回去修数据/修量表，不要进 AMOS。
| # | 检验 | 常用标准 | 不达标怎么办 |
|---|---|---|---|
| 1 | 样本量 | N ≥ 200；N : 待估参数 ≥ 5:1（理想 10:1） | 继续收数据 / 简化模型 |
| 2 | 正态性 | |偏度| < 2 |
严重偏离 → Bootstrap ML 或稳健估计 |
| 3 | 共同方法偏差 | Harman 单因子：第一因子 < 40% | 加 CLF 潜在共同方法因子检验 |
| 4 | 信度 | Cronbach's α ≥ .70 | 删题（看 CITC < .30） |
| 5 | EFA 适合性 | KMO ≥ .70，Bartlett p < .001 | 不适合做因子分析 → 检查量表 |
| 6 | 收敛效度 | 标准化载荷 ≥ .50（最好 ≥ .70）；CR ≥ .70；AVE ≥ .50 | 删低载荷题项 |
| 7 | 区分效度 | √AVE > 该因子与其他因子的相关；或 HTMT < .85 | 合并因子 / 重新界定构念 |
| 8 | 多重共线性 | VIF < 5；因子间相关 < .85 | 合并或删除 |
关键认知：CR 和 AVE 要在 CFA 之后用标准化载荷算，但载荷太低的题项在 EFA 阶段就该发现。 不要把不达标的数据硬塞进 AMOS，然后用 MI 加路径去救——救不回来，还会被审稿人抓住。
详见
references/02-readiness-checks.md（含每个指标的公式与 SPSS/Python 操作）
③ AMOS 自动化
AMOS 支持 .NET 编程接口，有两条自动化路线：
路线 A：AmosEngine —— 脚本化建模与估计（不用画图）
Dim Sem As New AmosEngineLib.AmosEngine
Sem.TextOutput()
Sem.Standardized() ' 标准化解
Sem.Smc() ' R²
Sem.Bootstrap(2000) ' Bootstrap
Sem.ConfidenceBC(90) ' 偏差校正置信区间（中介必备）
Sem.BeginGroup("data.sav")
Sem.AStructure("X1 = (1) F1 + (1) e1")
Sem.AStructure("X2 = F1 + (1) e2")
Sem.AStructure("Y = F1 + (1) e3")
Sem.Dispose()
What ships with it
9 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.
- references/01-data-cleaning.md 4.8 KB
- references/02-readiness-checks.md 7.5 KB
- references/03-amos-automation.md 8.7 KB
- references/04-model-fit-analysis.md 5.5 KB
- references/05-write-up.md 6.1 KB
- references/06-bibliography.md 5.7 KB
- templates/AmosEngine_SEM.vb 4.2 KB
- templates/AutoCFA_Plugin.vb 4.7 KB
- templates/readiness_check.py 5.9 KB runs code
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.
- 11d ago First seen · 250 lines · 385 tokens per session scan A 4890f0d1337a
amos-sem-workflow is a skill published in the GitHub repository maydengximin-sketch/amos-sem-workflow-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 385 tokens to every session and 3,417 once invoked, about $0.0019 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
anti-defensive-writing-en
Stops defensive writing across the entire paper lifecycle — writing, revising, cutting, and organizing experiments. Treats the paper as a press conference, not a project summary, lab log, or self-audit: identify the single most publishable strength of the work and build the most favorable, complete, and persuasive…
anti-defensive-writing
A Chinese-language writing guide for presenting a research paper around its strongest supported contribution. It treats the paper as a focused academic presentation rather than a project diary or complete lab record.
exploring-data
Exploratory data analysis. Use when users upload .csv/.xlsx/.json/.parquet files or request "explore data", "analyze dataset", "EDA", "profile data". Small files get ydata-profiling HTML/JSON reports; large files (over 200MB or 5M rows) get fixed-memory DuckDB/sketch profiling. Also covers near-duplicate row…
math-modeling-solver
A Chinese-language guide for solving mathematical modeling competition problems. It covers China’s CUMCM and America’s MCM/ICM, where teams use mathematics and code to answer real-world problem statements.
duan-jianye
A Chinese-language skill for discussing Bazi, a traditional Chinese birth-chart system, from Duan Jianye’s blind-school interpretation style. It reads the chart as symbolic scenes and relationships rather than starting with fixed categories or rules.
mathmodel-skill
An end-to-end workflow for mathematical-modeling competitions, including CUMCM, MCM/ICM, and the Electrical Cup. It guides teams from choosing a problem through modeling, solving, checking, writing, rule compliance, and final review.