Token导航 LogoToken导航

Agent Skill · 研究检索

evaluating-candidates(评估候选人)

evaluating-candidates 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。

evaluating-candidates 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 5,822。

总安装 24,240周安装 1,016GitHub Stars 734下载 7,920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:evaluating-candidates(评估候选人)
来源仓库:https://github.com/refoundai/lenny-skills
仓库路径:skills/evaluating-candidates
安装命令:
npx skills add https://github.com/refoundai/lenny-skills --skill evaluating-candidates
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/refoundai/lenny-skills --skill evaluating-candidates

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。

构建了 94 位产品领导者的结构化招聘框架,以做出更强有力的候选人决策。

运用背景调查、工作试用、机构评估和T型招聘等12条核心原则来系统地评估候选人 使用诊断问题来了解招聘阶段、团队差距以及决策是基于结构化规则还是仅基于直觉 挑战常见的偏见,如血统捷径、凭直觉做出的决定和独角兽招聘;优先考虑推荐人、带薪工作试验和现实世界的行为信号而不是面试表现 获取来自产品领导者的 151 条详细见解,主题包括任务调整、应对混乱、堆栈排名练习和提高决策模型

来源仓库内路径:skills/evaluating-candidates

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/refoundai/lenny-skills --skill evaluating-cand…;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

evaluating-candidates 怎么安装?

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

evaluating-candidates 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。

evaluating-candidates 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。

evaluating-candidates 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。

evaluating-candidates 用的人多吗?

公开数据是累计安装 24,240 次,近一周安装 1,016 次,下载 7,920 次,GitHub 734 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。

evaluating-candidates 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
evaluating-candidates

评估候选人 · 本页

24,240734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

Evaluating Candidates

Help the user make stronger hiring decisions using battle-tested frameworks from 94 product leaders.

How to Help

When the user asks for help evaluating candidates:

  1. Understand their context - Ask what stage they're at (screening resumes, reviewing work samples, conducting references, making final decisions) and what role they're hiring for
  2. Apply relevant principles - Use the frameworks below to help them think through the decision
  3. Challenge their assumptions - Push back on shortcuts like pedigree bias or gut-feel-only decisions
  4. Help them structure the process - Suggest interview questions, reference check approaches, or evaluation rubrics based on the principles

Core Principles

Reference checks trump interviews

Shishir Mehrotra: "I generally value the reference check over interview signals. Those people worked with this person for years—what you get from 30 minutes of interviewing doesn't compare." Prioritize references in final decisions, and dig deep with people who've worked closely with the candidate.

Hire for team balance, not unicorns

Adam Fishman: "The goal is not to find someone who's 11/10 on everything—that person doesn't exist. Create a well-rounded team by hiring to fill gaps in your portfolio." Before opening a role, map your team's current strengths and weaknesses.

Use paid work trials

Elena Verna: "We do 2-3 day paid work trials to see candidates in action—how they handle chaos and lack of clarity. This company is not for everybody." Work trials reveal what interviews cannot: how someone actually operates.

Prioritize agency over experience

Albert Cheng: "High agency and 'clock speed' are better predictors than deep experience. Sometimes experience is a crutch, especially when the ground is shifting fast." Look for candidates who took initiative outside formal channels.

Structure first, intuition after

Annie Duke: "If you use intuition after a structured evaluation—not before—you drastically improve your hit rate." Complete your rubric before letting gut feel influence the decision.

Look for world-class strengths, not lack of weaknesses

Ben Horowitz: "We're investing in strength, not lack of weakness. Does this person have a world-class strength that can beat anybody? Surround them with people who cover their gaps."

Test for comfort with chaos

Adam Grenier: "Comfort with chaos and willingness to do things they haven't done in 15 years are huge signals. People from traditional environments often can't handle startup unpredictability."

Identify the T-shape

Adam Grenier: "Every senior hire has a T-shaped career. Find their deep expertise (the vertical), then ask how they'll cover areas where they're weaker."

Watch behavior outside the interview

Albert Cheng: "High agency shows up outside formal interviews—the questions they ask, whether they've actually tried your product, the energy in their scheduling emails."

Avoid pedigree shortcuts

Austin Hay: "School prestige or resume gaps are bad shortcuts. Investigate gaps—they may represent intense self-directed learning."

Use the Bar Raiser model

Bill Carr (Amazon): "Have someone outside the hiring manager's chain run the debrief meeting with veto power. This counteracts urgency bias and keeps the bar high."

Hire for person-product fit

Brian Tolkin: "Match the candidate's specific background to the product's needs. A technical product needs a technical PM. Avoid hiring generalists for roles where specific context drives success."

Force stack-ranking

Bangaly Kaba: "Ask candidates to stack-rank five skills from strongest to weakest. It reveals self-awareness and opens deeper conversation about their actual capabilities."

Mission alignment retains talent

Benjamin Mann (Anthropic): "People stay when they're mission-oriented. They get offers from Meta but don't leave because their best case here is affecting humanity's future."

Questions to Help Users

Use these to diagnose where they need help:

  • "What stage of the process are you in?"
  • "What does your current team lack that this person needs to bring?"
  • "Have you done reference checks yet? What did you learn?"
  • "Did you use a structured rubric, or are you going on gut feel?"
  • "Have you seen them actually work, or only interviewed them?"
  • "What's their world-class strength?"

Deep Dive

For all 151 insights from 94 guests, see references/guest-insights.md

Related Skills

  • Writing Job Descriptions
  • Conducting Interviews
  • Onboarding New Hires
  • Building Team Culture

平台分布

Codex

34.72%
按下载量换算2,750

Claude

31.77%
按下载量换算2,516

Cursor

16.96%
按下载量换算1,343

Gemini CLI

9.11%
按下载量换算722

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