Agent skill

Gelman Perspective

by Exekiel179 in Exekiel179/psyclaw

安德鲁·格尔曼(Andrew Gelman)的思维框架。基于公开著作、论文与统计沟通实践提炼(多层模型、Bayesian 工作流、forking paths、可视化与不确定性沟通)。

MITAuto-check passed

Install Gelman Perspective

skills CLI
$ npx skills add Exekiel179/psyclaw --skill gelman-perspective -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Exekiel179/psyclaw gelman-perspective --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Exekiel179/psyclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/scholars/gelman-perspective .claude/skills/gelman-perspective && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
gelman-perspective
GitHub stars
103
Token cost
~384 tokens
SKILL.md length
97 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

安德鲁·格尔曼(Andrew Gelman)的思维框架。基于公开著作、论文与统计沟通实践提炼(多层模型、Bayesian 工作流、forking paths、可视化与不确定性沟通)。

  • Works in 4 steps: Multilevel structure first → Garden of forking paths → Model checking / predictive thinking → …
  • SKILL.md covers 使用说明, 角色规则, 核心心智模型 and 决策启发式, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Gelman Perspective is an agent skill from Exekiel179/psyclaw. 安德鲁·格尔曼(Andrew Gelman)的思维框架。基于公开著作、论文与统计沟通实践提炼(多层模型、Bayesian 工作流、forking paths、可视化与不确定性沟通)。 用途:统计建模诚实性、层级数据、多重性/分析路径、结果沟通的思维顾问。 触发:「Gelman」「格尔曼」「多层模型」「forking paths」「用 Gelman 的视角」「花园分叉小径」。 由 Still · 学者蒸馏合同生成的方法学人物镜头;非本人、非数字分身。

Its SKILL.md is about 380 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The licence is MIT.

Example prompts

  • “/gelman-perspective”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Multilevel structure first
  2. Garden of forking paths
  3. Model checking / predictive thinking
  4. Uncertainty is the product

What it can do on your machine

Read from SKILL.md and the folder at commit 452ec79. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gelman Perspective loads about 384 tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 97 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~61
When it runs · the whole SKILL.md, loaded when a task matches
~384

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Exekiel179/psyclaw at commit 452ec79, republished under its MIT licence (© Exekiel179). 97 words, ~384 tokens.

Download SKILL.mdSave it as .claude/skills/gelman-perspective/SKILL.md (or your agent's skills folder).
name
gelman-perspective
description
安德鲁·格尔曼(Andrew Gelman)的思维框架。基于公开著作、论文与统计沟通实践提炼(多层模型、Bayesian 工作流、forking paths、可视化与不确定性沟通)。 用途:统计建模诚实性、层级数据、多重性/分析路径、结果沟通的思维顾问。 触发:「Gelman」「格尔曼」「多层模型」「forking paths」「用 Gelman 的视角」「花园分叉小径」。 由 Still · 学者蒸馏合同生成的方法学人物镜头;非本人、非数字分身。
license
MIT

Gelman · 思维操作系统

“The difference between ‘significant’ and ‘not significant’ is not itself statistically significant.”

使用说明

这不是 Gelman 本人。这是按 Still · 学者蒸馏合同、基于公开统计方法学材料蒸馏的框架。

擅长:层级/重复测量数据结构、把模型写清楚、forking paths、用图与预测检查沟通、拆穿「只报漂亮模型」。
不擅长:在你没数据时发明系数;假装 SPSS 点选等于完整贝叶斯工作流。

🛑 首次免责声明一次。退出词:退出 / 切回正常 / 不用扮演了。

角色规则

  • 用「我」;偏好具体数据情景而非口号。
  • 先画(或描述)数据结构:谁嵌在谁里面。
  • 没搜到/没看到的数据就说不知道,并要求脚本与图。

核心心智模型

1. Multilevel structure first

一句话:先尊重聚类/重复测量的层级,再谈「平均效应」。
应用:学生嵌班级、试次嵌被试、站点嵌研究。
局限:层级不是万能;有时部分池化不必要。

2. Garden of forking paths

一句话:即使没有显式「p-hacking」,研究者自由度仍使显著性难解释。
应用:要求预声明或完整披露分析路径。
证据锚:公开论文/博客主题 forking paths。

3. Model checking / predictive thinking

一句话:模型要能对数据做可检查的预测,而非只产出一张星号表。
应用:残差、后验预测、复制与稳健性。

4. Uncertainty is the product

一句话:区间、层级方差、预测分布比二元显著更有信息。
应用:改写结果段语言;拒绝「不显著=没有效应」。

决策启发式

  1. 写出数据生成过程 — 再选软件按钮。
  2. 一张图胜过一排 p — 要求可复核图脚本。
  3. 问还有哪些模型你没跑 — 暴露 forking paths。
  4. 探索性与确证性分家 — 语言上必须分开。
  5. 小样本别装大样本腔 — 部分池化与正则化思维。

表达 DNA

  • 语气:直率、技术、带统计幽默。
  • 禁忌:伪造拟合优度;用「贝叶斯」当装饰词而无先验/检查。

与 PsyClaw 协作

© Exekiel179, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/scholars/gelman-perspective of Exekiel179/psyclaw.

Open the folder on GitHubat commit 452ec79

Compare with similar skills

Gelman Perspective next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Gelman Perspective compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gelman Perspective this skillExekiel179/psyclaw103—~384Automated safety check: PassMIT
Perspectivebergside/awesome-design-skills3.1k1 repos~904Automated safety check: PassMIT
Review Hog Perspective Contracts SecurityPostHog/posthog40k—~1kAutomated safety check: PassCustom licence
Review Hog Perspective Logic CorrectnessPostHog/posthog40k—~988Automated safety check: PassCustom licence
Review Hog Perspective Performance ReliabilityPostHog/posthog40k—~1kAutomated safety check: PassCustom licence
Andrew Von Nagy Perspectiveswaylq/master-skill148—~4.5kAutomated safety check: NotesMIT

Similar skills

  • Perspective

    bergside/awesome-design-skills

    Spatial depth design with isometric views, vanishing points, and layered elements that guide attention through 3D-like realism.

    3.1k GitHub starsUsed in 1 repo~904 tokens
    Frontend & DesignAuto-check passed
  • The Logic & Correctness review perspective for PostHog Review.

    40k GitHub stars~988 tokensUpdated yesterday
    Data & AnalyticsAuto-check passed
  • Andrew Von Nagy Perspective

    swaylq/master-skill

    Andrew von Nagy 视角 — 高密度 Wi-Fi 工程的容量优先设计学派代表 (Revolution Wi-Fi 博客, ex-Target Senior Wireless Architect, 现 Nile Principal Architect, CCIE-Wireless + CWNE).

    148 GitHub stars~4.5k tokensUpdated 1 mo ago
    Auto-check: notes
  • digoal/德哥的思维框架与表达方式。基于本地 digoal/blog 长文、ASK/访谈、 技术课程、公开履历、社区活动页和近年 AI skill 行动记录的调研, 提炼5个核心心智模型、8条决策启发式和表达DNA。

    8.6k GitHub stars~1.8k tokensUpdated 2 days ago
    DatabasesAuto-check passed

More from Exekiel179/psyclaw

All 10 skills in this repo
  • Academic Grill

    Exekiel179/psyclaw

    Stress-test an academic research question, proposal, study design, analysis plan, manuscript claim, review protocol, or AI research project through a one-question-at-a-time interview until its…

    103 GitHub stars~2k tokensUpdated 2 days ago
    Auto-check passed
  • Verify Feature

    Exekiel179/psyclaw

    跑 PsyClaw 的 Definition-of-Done 验证(init.sh:compile + pytest + gates),把命令与输出作为 evidence 记入 featurelist.json。当用户要验证/收尾一个 feature、宣称完成前、或说 "verify" / "跑验证" / "记 evidence" 时使用。

    103 GitHub stars~328 tokensUpdated 2 days ago
    Auto-check passed
  • Analysis Plan

    Exekiel179/psyclaw

    Soft-takeover stats planning in analysis mode — light EDA, per-analysis human choices, typed ritual approval before execute, optional auto mode, then local scripts (MCP only when needed).

    103 GitHub stars~646 tokensUpdated 2 days ago
    Auto-check passed
  • Freud Perspective

    Exekiel179/psyclaw

    西格蒙德·弗洛伊德(Sigmund Freud)作为精神分析学派代表的思维框架蒸馏。基于公开著作与学派史材料提炼的概念透镜(无意识、防御、移情、释梦传统等),用于理论对话与文本/临床概念澄清——不是治疗工具。

    103 GitHub stars~440 tokensUpdated 2 days ago
    Auto-check passed
  • Kahneman Perspective

    Exekiel179/psyclaw

    丹尼尔·卡尼曼(Daniel Kahneman)的思维框架。基于公开著作与演讲提炼的心智模型、启发式与表达DNA(Thinking, Fast and Slow; Judgment under Uncertainty; Noise 等公开材料)。

    103 GitHub stars~426 tokensUpdated 2 days ago
    Auto-check passed
  • Run Stats MCP

    Exekiel179/psyclaw

    需要跑统计(t 检验/方差/回归/因子/SEM/生存/EEG…)时,路由到正确的外部 MCP 服务器或 [stats] extra,而不是在 psyclaw 仓内重新实现算法。当任务涉及统计计算、选择统计方法、或有人想在 psyclaw 里写统计代码时使用。

    103 GitHub stars~384 tokensUpdated 2 days ago
    Auto-check passed

Questions about Gelman Perspective

What does Gelman Perspective do?

安德鲁·格尔曼(Andrew Gelman)的思维框架。基于公开著作、论文与统计沟通实践提炼(多层模型、Bayesian 工作流、forking paths、可视化与不确定性沟通)。. Gelman Perspective is an agent skill from Exekiel179/psyclaw.

How do I install Gelman Perspective in Claude Code?

Run `npx skills add Exekiel179/psyclaw --skill gelman-perspective -a claude-code`. Or copy the skill folder (skills/scholars/gelman-perspective in Exekiel179/psyclaw) into .claude/skills/gelman-perspective in your project. Claude Code loads it when a task matches its description.

How do I install Gelman Perspective in Codex?

Run `npx skills add Exekiel179/psyclaw --skill gelman-perspective -a codex`. Or copy the skill folder (skills/scholars/gelman-perspective in Exekiel179/psyclaw) into .agents/skills/gelman-perspective in your project. Codex loads it when a task matches its description.

Can I use Gelman Perspective in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Exekiel179/psyclaw --skill gelman-perspective -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gelman-perspective, .gemini/skills/gelman-perspective, .github/skills/gelman-perspective and .opencode/skills/gelman-perspective in your project.

What does Gelman Perspective need to run?

SKILL.md names no scripts, command-line tools or credentials: Gelman Perspective is instructions for the agent only.

Does Gelman Perspective access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Gelman Perspective safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Gelman Perspective use?

Gelman Perspective is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gelman Perspective use?

About 384 tokens (SKILL.md is roughly 1.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Gelman Perspective?

Skills that share tags, products or a category with Gelman Perspective: Perspective (bergside/awesome-design-skills, 3.1k stars), Review Hog Perspective Contracts Security (PostHog/posthog, 40k stars), Review Hog Perspective Logic Correctness (PostHog/posthog, 40k stars) and Review Hog Perspective Performance Reliability (PostHog/posthog, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gelman Perspective?

Exekiel179 (a GitHub user) maintains it in Exekiel179/psyclaw, which has 103 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 9, 2026.

Source: Exekiel179/psyclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.