Evaluating Candidates logo

Evaluating Candidates

Community
cnfeat
evaluating-candidates

Help users make better hiring decisions. Use when someone is evaluating job candidates, making hiring decisions, conducting reference checks, reviewing work samples or take-homes, calibrating their hiring bar, or deciding between finalists.

Overview

Publishercnfeat
Repositorytop-pm-skills
Skill nameevaluating-candidates
Stars
55
Forks
6
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by cnfeat on GitHub. Read the source before you install it.

Installation

Install the Evaluating Candidates AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/cnfeat/top-pm-skills/tree/main/参考skill/lenny-skills-main%20(2)/lenny-skills-main/skills/evaluating-candidates
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Use it in TypingMind

Enable Evaluating Candidates in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Evaluating Candidates on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Evaluating Candidates is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Evaluating Candidates AI skill do?

Help users make better hiring decisions. Use when someone is evaluating job candidates, making hiring decisions, conducting reference checks, reviewing work samples or take-homes, calibrating their hiring bar, or deciding between finalists.

Why use Evaluating Candidates on TypingMind?

Because you install it once and use it with any model. Evaluating Candidates is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Evaluating Candidates in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cnfeat/top-pm-skills/tree/main/参考skill/lenny-skills-main%20(2)/lenny-skills-main/skills/evaluating-candidates. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Evaluating Candidates?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Evaluating Candidates?

As many as you like. As long as a model supports skills, you can use Evaluating Candidates with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Evaluating Candidates AI skill free?

Yes. It is published on GitHub by cnfeat under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇