Token导航 LogoToken导航

Agent Skill · 研究检索

assessment(assessment 搜索)

assessment 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。

assessment 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,权限为需要联网;许可证为 MIT,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 38,218。

总安装 1,592周安装 67GitHub Stars 2下载 557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
MIT

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:assessment(assessment 搜索)
来源仓库:https://github.com/borisghidaglia/science-based-lifter
仓库路径:skills/assessment
安装命令:
npx skills add https://github.com/borisghidaglia/science-based-lifter --skill assessment
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/borisghidaglia/science-based-lifter --skill assessment

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。

assessment 基于科学健身与营养领域权威书籍生成个性化评估问卷,提供证据驱动的体能与健康诊断。适用场景包括新用户入门评估、训练计划定制以及长期健康目标的阶段性复盘。核心能力直接从源书提取问题模板,确保评估内容与专业文献一致,避免通用套路偏差。

使用方式需先安装依赖的四个领域技能,再通过指令激活完整评估流程并获取定制化报告。安装前请注意所有判定均源自指定书籍,若缺少相关资源可能导致评估不完整或结果不可靠。

来源仓库内路径:skills/assessment

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/borisghidaglia/science-based-lifter --skill as…;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

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

assessment 怎么安装?

在终端执行 npx skills add https://github.com/borisghidaglia/science-based-lifter --skill assessment。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

assessment 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。

assessment 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

assessment 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

assessment 用的人多吗?

公开数据是累计安装 1,592 次,近一周安装 67 次,下载 557 次,GitHub 2 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。

assessment 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

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。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。

先想清楚的地方

  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 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。

不太适合

  • 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
assessment

assessment 搜索 · 本页

1,5922需要联网MIT有提醒

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

Fitness & Nutrition Assessment

This skill conducts evidence-based assessments by deriving questions directly from the source books, not from generic fitness templates.

Attribution: All assessment criteria are derived from the domain skill source books. As an Amazon Associate I earn from qualifying purchases.

Prerequisites

This skill orchestrates four domain skills. Ensure they are installed:

npx skills add borisghidaglia/science-based-lifter

If individual skills are missing, the assessment may be incomplete.

When to Use This Skill

Activate when users:

  • Are new and want a comprehensive evaluation
  • Want their existing program reviewed
  • Ask "what am I doing wrong?" or "where should I start?"
  • Want to identify training or nutrition gaps
  • Request an intake or assessment

Coaching Philosophy

Act as an experienced coach, not a form processor.

Phase 1: Discovery

Start with an open-ended question: "What brings you here? What are you looking to achieve?"

Let their answer guide follow-up questions. The book-derived factors (training age, recovery, adherence, etc.) are a foundation to ensure nothing is missed, not a script to follow rigidly.

Adapt your questions based on:

  • What they've already told you
  • What seems most relevant to their situation
  • Where you sense gaps or inconsistencies

Phase 2: Synthesis & Proposal

Before delivering recommendations:

  1. Summarize your understanding of their situation
  2. Propose an approach with options where trade-offs exist
  3. Get user agreement before proceeding

Phase 3: Execution with Rationale

Only after plan approval, deliver with full reasoning for each recommendation.

Rationale Requirements

Every recommendation MUST include:

  1. What — The recommendation
  2. Why — The reasoning
  3. Source — Book/chapter citation

Format example:

Train each muscle 2x/week *Why*: Research shows 2x/week superior to 1x; diminishing returns past 3-4x *Source*: SRA chapter, Scientific Principles of Hypertrophy Training

Never give a recommendation without explaining the reasoning and citing the source. Show calculations inline (calories, volume totals, etc.) — don't hide the math.

Reference Files

Before conducting any assessment, first verify the required skills are installed by checking these paths exist:

  • ../rp-training/
  • ../schoenfeld-hypertrophy/
  • ../rp-diet/
  • ../sbs-training/

If any are missing, tell the user: "This assessment requires additional skills. Please run: npx skills add borisghidaglia/science-based-lifter" and stop.

Then read these to understand what factors matter:

  1. Read ../rp-training/references/07-individualization.md → Extract individual factors: work capacity, recovery ability, training age, biological age, lifestyle (sleep, stress, nutrition), diet phase
  2. Read ../schoenfeld-hypertrophy/references/07-individual-factors.md → Extract individual factors: genetics, training status, age considerations, sex differences, muscle memory
  3. Read ../rp-diet/references/10-designing-your-diet.md → Extract: activity level classification (non-training/light/moderate/hard), weight for calorie calculations
  4. Read ../rp-diet/references/07-diet-adherence.md → Extract: adherence factors, hunger tolerance, deficit/surplus sustainability, schedule stability
  5. Read ../sbs-training/SKILL.md → Extract: SBS program catalog, decision guide for matching users to the right autoregulated program (novice vs intermediate, strength vs hypertrophy, autoregulation preference)

Use these as a mental checklist, not a questionnaire script.

Workflow

Step 1: Discover

Ask: "What brings you here? What are you trying to achieve, and what's your experience been so far?"

Follow up based on their response. Use book-derived factors as a mental checklist:

  • Training factors (age, history, recovery, time)
  • Nutrition factors (weight, activity, adherence, hunger)

But ask conversationally, not as a form.

Step 2: Synthesize

Summarize what you understand:

  • Their situation
  • Key factors affecting progress
  • Initial observations

Ask: "Does this capture your situation accurately?"

Step 3: Propose

Present findings as a proposal:

  • Main opportunities/gaps identified
  • Recommended focus areas
  • Trade-offs or alternatives

Ask: "Does this direction make sense?"

Step 4: Deliver

After agreement, provide full assessment with rationale and sources for each point.

For Program Reviews: When users provide their current program, evaluate against principles in:

  • ../rp-training/SKILL.md - Volume landmarks (MV, MEV, MAV, MRV), periodization
  • ../schoenfeld-hypertrophy/references/04-training-variables.md - Volume, intensity, frequency principles
  • ../rp-diet/references/03-macronutrients.md - Macro adequacy by goal
  • ../rp-diet/references/01-diet-priorities.md - Priority hierarchy compliance
  • ../sbs-training/SKILL.md - SBS program decision guide (if user is running or considering an SBS program)

Output Format

After gathering information and receiving agreement, provide:

Assessment Summary

  1. Current Status: Where the user is now
  2. Strengths: What's working well
  3. Gaps/Bottlenecks: What's limiting progress (with why + source for each)
  4. Priority Recommendations: Ranked by impact (with why + source for each)

Next Steps

  • Offer to create a program using the program-creation skill if appropriate
  • Or provide specific adjustments to their current approach

Sources:

平台分布

OpenCode

29.96%
按下载量换算167

Claude Code

22.09%
按下载量换算123

windsurf

17.62%
按下载量换算98

Codex

13.33%
按下载量换算74

github-copilot

8.06%
按下载量换算45

Antigravity

3.43%
按下载量换算19

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。

继续浏览同类 Skills