Token导航 LogoToken导航

Agent Skill · 研究检索

grad-elm(等级榆树)

grad-elm 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

grad-elm 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 60,488。

总安装 367周安装 15GitHub Stars 125下载 119核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:grad-elm(等级榆树)
来源仓库:https://github.com/asgard-ai-platform/skills
仓库路径:skills/grad-elm
安装命令:
npx skills add https://github.com/asgard-ai-platform/skills --skill grad-elm
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/asgard-ai-platform/skills --skill grad-elm

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

grad-elm 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。适用于生态学、环境科学或系统建模研究场景。通过关键词和来源线索匹配,返回相关模型与研究成果。

安装方式:npx skills add https://github.com/asgard-ai-platform/skills --skill grad-elm 建议确认权限范围、维护状态,以及是否涉及联网或文件操作。

来源仓库内路径:skills/grad-elm

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/asgard-ai-platform/skills --skill grad-elm;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

grad-elm 怎么安装?

在终端执行 npx skills add https://github.com/asgard-ai-platform/skills --skill grad-elm。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

grad-elm 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

grad-elm 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

grad-elm 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

grad-elm 用的人多吗?

公开数据是累计安装 367 次,近一周安装 15 次,下载 119 次,GitHub 125 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

grad-elm 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
grad-elm

等级榆树 · 本页

367125只读未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Elaboration Likelihood Model (ELM)

Overview

The Elaboration Likelihood Model (Petty & Cacioppo, 1986) proposes that persuasion occurs through two distinct routes depending on the audience's motivation and ability to process a message. The central route relies on careful evaluation of argument quality, producing durable attitude change. The peripheral route relies on heuristic cues (source attractiveness, number of arguments), producing temporary and fragile attitude shifts.

When to Use

  • Designing marketing, policy, or internal communication strategies for different audience segments
  • Diagnosing why a well-reasoned message failed (audience lacked motivation/ability to process)
  • Predicting whether attitude change will persist and resist counter-persuasion
  • Choosing between investing in argument quality vs. source credibility or presentation style

When NOT to Use

  • When the goal is behavioral compliance rather than genuine attitude change (use compliance techniques)
  • For purely emotional appeals where cognitive processing models are insufficient (use affect-as-information)
  • When the audience has no prior schema on the topic and needs education before persuasion

Assumptions

IRON LAW: Attitude change via the central route is MORE durable
and resistant to counter-persuasion — but requires motivation
AND ability to process. When either is absent, only the
peripheral route is available, and its effects decay.

Key assumptions:

  1. Elaboration exists on a continuum from low to high, not a strict binary
  2. The same variable (e.g., source expertise) can serve as argument, cue, or affect elaboration direction depending on context
  3. Central-route attitudes predict behavior better than peripheral-route attitudes

Methodology

Step 1 — Assess Audience Elaboration Likelihood

FactorHigh ElaborationLow Elaboration
Personal relevanceHigh (topic matters to them)Low (distant from self)
Need for cognitionHigh (enjoys thinking)Low (avoids effortful thought)
Prior knowledgeSufficient to evaluate argumentsInsufficient to engage deeply
Distraction levelLow (can focus)High (divided attention)
Time pressureLow (can deliberate)High (must decide quickly)

Step 2 — Select Persuasion Route

  • Central route (high elaboration): invest in strong, evidence-based arguments
  • Peripheral route (low elaboration): invest in heuristic cues and presentation
  • Mixed (moderate elaboration): use both strong arguments and peripheral cues

Step 3 — Design the Message

Central route elements:

  • Logical argument structure, data, evidence
  • Two-sided messaging (acknowledge counterarguments)
  • Strong argument quality (scrutiny-resistant claims)

Peripheral route elements:

  • Source credibility, attractiveness, likability
  • Social proof (endorsements, testimonials, popularity)
  • Message length and formatting cues
  • Emotional tone and narrative framing

Step 4 — Predict Attitude Outcomes

RouteDurabilityBehavior PredictionCounter-Persuasion Resistance
CentralHighStrongHigh
PeripheralLowWeakLow

Output Format

## ELM Persuasion Strategy: [Context]

### Audience Elaboration Assessment
| Segment | Motivation | Ability | Elaboration Level |
|---------|-----------|---------|-------------------|
| [segment] | [High/Low] | [High/Low] | [High/Moderate/Low] |

### Route Selection: [Central / Peripheral / Mixed]

### Message Design
- Primary arguments: [if central route]
- Peripheral cues: [if peripheral route]
- Source selection: [credibility/attractiveness rationale]

### Predicted Outcomes
- Attitude durability: [High/Medium/Low]
- Behavioral impact: [Strong/Moderate/Weak]
- Counter-persuasion vulnerability: [High/Medium/Low]

### Risk Mitigation
- [What happens if audience elaboration is misjudged]

Gotchas

  • The same variable can play multiple roles: source expertise can be a peripheral cue (low elaboration) or bias argument processing direction (high elaboration)
  • Strong arguments under central processing can backfire if they are perceived as manipulative — reactance theory applies
  • Peripheral cues are not inherently inferior; in low-stakes decisions, they are efficient and adaptive
  • ELM assumes a relatively cognitive model of persuasion; purely visceral or embodied persuasion is not well-captured
  • Cultural differences affect what counts as a strong argument vs. a peripheral cue (e.g., authority weight varies by culture)
  • Repeated exposure can shift processing from peripheral to central as familiarity grows — one-shot message design is insufficient for campaigns

References

  • Petty, R. E. & Cacioppo, J. T. (1986). *Communication and persuasion: central and peripheral routes to attitude change*. Springer-Verlag.
  • Petty, R. E. & Wegener, D. T. (1999). The elaboration likelihood model: current status and controversies. In S. Chaiken & Y. Trope (Eds.), *Dual-process theories in social psychology* (pp. 37-72). Guilford Press.
  • Petty, R. E., Brinol, P. & Priester, J. R. (2009). Mass media attitude change. In J. Bryant & M. B. Oliver (Eds.), *Media effects: advances in theory and research* (3rd ed., pp. 125-164). Routledge.

平台分布

Codex

35.84%
按下载量换算43

Claude

32.36%
按下载量换算39

Cursor

19.92%
按下载量换算24

Gemini CLI

9.28%
按下载量换算11

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills