interviewing-evaluating-candidates

interviewing-evaluating-candidates is a skill for Claude Code, Codex from RefoundAI/lenny-skills. It costs 32 tokens per session (987 once invoked), scanned A, original, MIT.

A guide for building a structured job interview and candidate evaluation process. It focuses on evidence from practical work, consistent questions, scoring guides, and references from former collaborators.

In plain words
What is it for?
Use it to define role requirements, create realistic work trials, standardize interviews and scoring, and conduct detailed reference checks.
Why use it?
It reduces reliance on resumes, charisma, personal intuition, and unstructured conversations when deciding who can do the job.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to define role requirements, create realistic work trials, standardize interviews and scoring, and conduct detailed reference checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/refoundai/lenny-skills/interviewing-evaluating-candidates
About the project

Lenny Skills is a collection of product-management and engineering workflows for Claude Code and other AI agents, covering areas such as strategy, research, planning, shipping, growth, and hiring. Each skill gives an agent specialized guidance, frameworks, checklists, or templates for product work, and the catalogue contains many of these skills.

RefoundAI/lenny-skills · 1,321 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add RefoundAI/lenny-skills --skill interviewing-evaluating-candidates
Clone the repo
git clone --depth 1 https://github.com/RefoundAI/lenny-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for interviewing-evaluating-candidates

README.md
[![agentmods](https://agentmods.dev/badge/skills/refoundai/lenny-skills/interviewing-evaluating-candidates/github.svg)](https://agentmods.dev/skills/refoundai/lenny-skills/interviewing-evaluating-candidates)
Your own site
<a href="https://agentmods.dev/skills/refoundai/lenny-skills/interviewing-evaluating-candidates"><img src="https://agentmods.dev/badge/skills/refoundai/lenny-skills/interviewing-evaluating-candidates/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for interviewing-evaluating-candidates

Your own site · 80×15
<a href="https://agentmods.dev/skills/refoundai/lenny-skills/interviewing-evaluating-candidates"><img src="https://agentmods.dev/badge/skills/refoundai/lenny-skills/interviewing-evaluating-candidates.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 987 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.00987
Opus 5 $0.00016 $0.00494
Sonnet 5 $0.00006 $0.00197
Haiku 4.5 $0.00003 $0.00099

Measured 12d ago against content hash 43adae406931, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

interviewing-evaluating-candidates scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/interviewing-evaluating-candidates/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Interviewing and Evaluating Candidates

Move beyond resumes to assess high-fidelity signals like agency, first-principles thinking, and actual craft.

Help the user with interviewing and evaluating candidates using insights from 27 guests and posts across Lenny's Podcast and Newsletter.

How to Help

  1. Define the Role Core - Identify specific competencies and core jobs the candidate must perform based on your unique organizational needs.
  2. Design Practical Assessments - Move from abstract case studies to almost-real-life assignments or paid work trials that mimic the actual job.
  3. Apply Standardized Evaluation - Implement consistent rubrics and thematic questioning to reduce bias and increase signal quality.
  4. Conduct High-Fidelity Reference Checks - Verify performance with past collaborators to triangulate interview signals and uncover long-term patterns.

Core Principles

Prioritize Enthusiastic Rehires

Brian Halligan: "I think CEOs and everyone dramatically overrates their ability to interview, and overrates their gut feeling, and underrates a really high quality blind reference."

The most effective hiring signal is asking a reference if the candidate was in the top 1 percent of employees and if they would enthusiastically rehire them.

Use the Unsell Email

Kevin Yien: "When you get to offer stage, I send an email and I say all the terrible things that are probably going to reinforce their fears. If you can tell them that upfront and they can read that whole email and still be equally excited to join you, find yourself a A+ hire."

Send an email at the offer stage detailing your company's biggest flaws and challenges to ensure the candidate's commitment is based on reality.

Screen for First-Principles Thinking

Melissa Tan: "I think they looked for two main things. They looked for first principles thinkers, so not necessarily your experience, but how do you approach problems, how do you know the right questions to ask? And then create your own framework around that. Dropbox also hired for people that were just really humble, collaborative and team oriented."

Read the full file on GitHub · 72 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 72 lines · 32 tokens per session scan A 43adae406931

Subscribe to this mod's changes

interviewing-evaluating-candidates is a skill published in the GitHub repository RefoundAI/lenny-skills (1,321 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 987 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

llama-cpp

Run LLM inference with llama.cpp on CPU, Apple Silicon, AMD/Intel GPUs, or NVIDIA — plus GGUF model conversion and quantization (2–8 bit with K-quants and imatrix). Covers CLI, Python bindings, OpenAI-compatible server, and Ollama/LM Studio integration. Use for edge deployment, M1/M2/M3/M4 Macs, CUDA-less…

moltis-org/moltis · 91 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.

moltis-org/moltis · 33 tokens

github-auth

Set up GitHub authentication for the agent using git (universally available) or the gh CLI. Covers HTTPS tokens, SSH keys, credential helpers, and gh auth — with a detection flow to pick the right method automatically.

moltis-org/moltis · 48 tokens

ideation

Generate project ideas through creative constraints. Use when the user says 'I want to build something', 'give me a project idea', 'I'm bored', 'what should I make', 'inspire me', or any variant of 'I have tools but no direction'. Works for code, art, hardware, writing, tools, and anything that can be made.

moltis-org/moltis · 75 tokens

notion

Notion API for creating and managing pages, databases, and blocks via curl. Search, create, update, and query Notion workspaces directly from the terminal.

moltis-org/moltis · 36 tokens

ocr-and-documents

Extract text from PDFs and scanned documents. Use webextract for remote URLs, pymupdf for local text-based PDFs, marker-pdf for OCR/scanned docs. For DOCX use python-docx, for PPTX see the powerpoint skill.

moltis-org/moltis · 54 tokens