Agent skill

Interview Kit

by shawnpang in shawnpang/startup-founder-skills

When the user needs to design an interview process, create interview questions, build scorecards, calibrate interviewers, or evaluate candidates for a role.

MITAuto-check passedBusiness, Finance & HR

Install Interview Kit

skills CLI
$ npx skills add shawnpang/startup-founder-skills --skill interview-kit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install shawnpang/startup-founder-skills interview-kit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/shawnpang/startup-founder-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/interview-kit .claude/skills/interview-kit && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
interview-kit
GitHub stars
342
Token cost
~2.1k tokens
SKILL.md length
920 words
Files
1
Skills in repo
50
Repo updated
First seen
Licence
MIT

At a glance

When the user needs to design an interview process, create interview questions, build scorecards, calibrate interviewers, or evaluate candidates for a role.

  • Works in 7 steps: Define competencies — Extract 4-6 core… → Design the interview loop — Map… → Write structured questions — For each… → …
  • Needs to design an interview process
  • SKILL.md covers When to Use, Context Required, Workflow and Output Format, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Interview Kit is an agent skill from shawnpang/startup-founder-skills. When the user needs to design an interview process, create interview questions, build scorecards, calibrate interviewers, or evaluate candidates for a role.

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Business, Finance & HR, covering Interview preparation. The repository describes itself as: AI agent skills for tech startup founders — fundraising, sales, product, recruiting, engineering, legal, ops, and growth. Works with Claude Code, Cursor, Codex, and any Agent… The licence is MIT.

When your agent uses it

  • Needs to design an interview process
  • Create interview questions
  • Build scorecards
  • Calibrate interviewers

Example prompts

  • “/interview-kit”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Define competencies — Extract 4-6 core competencies from the job description. Split into technical skills, domain knowledge, collaboration…
  2. Design the interview loop — Map competencies to interview stages with explicit, non-overlapping objectives per round. Typical startup…
  3. Write structured questions — For each stage, write 3-5 primary questions with follow-up probes. Every question must map to a specific…
  4. Build scorecards — Create a 1-4 rating scale (not 1-5 — it creates a "3 means fine" dead zone). Define behavioral anchors at each level…
  5. Design take-home or live exercise — If applicable, create a practical assessment that mirrors real work. Time-cap it (2-4 hours max)…
  6. Add anti-bias guardrails — Require structured debrief instructions, independent scoring protocol, and a checklist of common bias traps…
  7. Plan calibration cadence — Set quarterly recalibration using hiring outcome data. Review whether loop design still surfaces the right…

What it can do on your machine

Read from SKILL.md and the folder at commit 4ad31b4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Interview Kit loads about 2.1k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 920 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from shawnpang/startup-founder-skills at commit 4ad31b4, republished under its MIT licence (© shawnpang). 920 words, ~2,126 tokens.

Download SKILL.mdSave it as .claude/skills/interview-kit/SKILL.md (or your agent's skills folder).
name
interview-kit
description
When the user needs to design an interview process, create interview questions, build scorecards, calibrate interviewers, or evaluate candidates for a role.
related
job-description, sourcing-outreach
reads
startup-context

Interview Kit

When to Use

  • Designing a structured interview loop for a specific role and level
  • Creating standardized question banks organized by interview round type
  • Building scoring rubrics for consistent candidate evaluation across interviewers
  • Reducing interviewer bias with process controls and calibration
  • Turning a job description into a repeatable evaluation process
  • Calibrating interview panels after quarterly hiring outcome reviews

Context Required

  • From startup-context: Company stage, team size, engineering culture, current interview process (if any), hiring velocity
  • From user: Role title, level (junior/mid/senior/staff), key competencies to evaluate, number of interview rounds the team can support, whether a take-home or live exercise is preferred

Workflow

  1. Define competencies — Extract 4-6 core competencies from the job description. Split into technical skills, domain knowledge, collaboration traits, and startup-fit signals. Each competency must be evaluable with observable evidence.
  2. Design the interview loop — Map competencies to interview stages with explicit, non-overlapping objectives per round. Typical startup loop: recruiter/founder screen, technical assessment, team interview, values interview. Assign timing and interviewers to each stage.
  3. Write structured questions — For each stage, write 3-5 primary questions with follow-up probes. Every question must map to a specific competency. Include "what good looks like" answer guidance so interviewers know what signal they are looking for.
  4. Build scorecards — Create a 1-4 rating scale (not 1-5 — it creates a "3 means fine" dead zone). Define behavioral anchors at each level specific to the role. Interviewers must score independently before the debrief.
  5. Design take-home or live exercise — If applicable, create a practical assessment that mirrors real work. Time-cap it (2-4 hours max), share the evaluation rubric with the candidate upfront, and always follow up with a live walkthrough.
  6. Add anti-bias guardrails — Require structured debrief instructions, independent scoring protocol, and a checklist of common bias traps. Every candidate for the same role gets the same core questions in the same order.
  7. Plan calibration cadence — Set quarterly recalibration using hiring outcome data. Review whether loop design still surfaces the right signals based on quality-of-hire metrics.

Output Format

A complete interview kit document containing:

  • Role summary and competency matrix (4-6 competencies with definitions)
  • Interview loop overview (stages, duration, interviewers, competency mapping)
  • Per-stage question sets with follow-up probes and scoring rubrics
  • Take-home or live exercise brief with time cap and evaluation criteria
  • Scorecard template (1-4 scale with behavioral anchors)
  • Debrief protocol with independent scoring and evidence-based discussion rules
  • Compensation benchmarking notes (if requested)

Frameworks & Best Practices

Competency Categories by Role Type
  • Engineering: System design, code quality, debugging approach, technical communication, ownership/initiative
  • Product: Customer empathy, prioritization frameworks, cross-functional communication, data-informed thinking, shipping velocity
  • Go-to-market: Discovery/qualification, storytelling, objection handling, pipeline management, customer orientation
  • Design: Design process, craft quality, user research fluency, systems thinking, collaboration with engineering
Scorecard Design (1-4 Scale)
  • 1 — Does not meet bar: Could not demonstrate the competency. Clear concerns.
  • 2 — Below bar: Showed partial ability but gaps are significant for the level.
  • 3 — Meets bar: Demonstrated the competency at the expected level. Solid hire signal.
  • 4 — Exceeds bar: Demonstrated exceptional strength. Would raise the team's capability.

Each score level must include 1-2 concrete behavioral anchors specific to the role being evaluated.

Show full SKILL.md (401 more words)Show less
The STAR-B Question Framework

Structure behavioral questions to elicit complete, pattern-revealing answers:

  • Situation: Set the scene
  • Task: What was your responsibility
  • Action: What specifically did you do
  • Result: What happened
  • Behavior pattern: Is this a repeatable pattern or a one-off

Example: "Tell me about a time you had to ship something with significant technical debt. What was the situation, what did you decide, and how did it play out? Would you make the same call again?"

Anti-Bias Techniques
  • Structured questions: Every candidate for the same role gets the same core questions in the same order
  • Independent scoring: Interviewers submit scores before the debrief meeting — no anchoring on a senior person's opinion
  • Blind resume review: Strip names, photos, school names, and company names in the initial screen where possible
  • Diverse interview panels: Include at least one interviewer from an underrepresented background when possible
  • Language check: Before writing feedback, ask "Would I say this about a different candidate?" to catch biased framing
  • Replace "culture fit" with "values alignment" and require specific behavioral evidence
Take-Home Assignment Guidelines
  • Time-capped: 2-4 hours maximum. State this explicitly and mean it.
  • Mirrors real work: The exercise should resemble an actual task the person would do in the role
  • Transparent criteria: Share the rubric with the candidate upfront so they know what you value
  • Equitable access: Offer a paid alternative if the candidate cannot invest unpaid time
  • Debrief required: Always follow up with a live walkthrough where the candidate explains their choices
Common Pitfalls
  • Overweighting one round while ignoring other competency signals
  • Using unstructured interviews without standardized scoring
  • Skipping calibration sessions for interviewers
  • Changing the hiring bar without documenting rationale
  • Letting round objectives overlap so multiple stages test the same thing
Compensation Benchmarking Framework

Use three inputs to triangulate:

  1. Market data: Levels.fyi, Pave, Carta Total Comp, Glassdoor as directional
  2. Stage multiplier: Seed pays 70-85% of big-co base with 0.5-2% equity; Series A narrows to 80-95%
  3. Candidate calibration: Adjust for experience, competing offers, and location within the level band

Always present comp as a range with a target midpoint, not a single number.

  • job-description — Use the JD's competency requirements as input for the interview loop
  • sourcing-outreach — Align outreach messaging with the interview process so candidates know what to expect

Examples

Prompt: "Design an interview loop for a senior backend engineer. 15-person startup."

Good output snippet:

## Interview Loop — Senior Backend Engineer

### Competencies to Evaluate
1. System design & architecture (technical depth)
2. Code quality & testing practices (craft)
3. Debugging & production thinking (operational maturity)
4. Technical communication (collaboration)
5. Ownership & initiative (startup fit)

### Stage 1: Founder Screen (30 min)
- Evaluate: Motivation, communication, logistics
- Questions:
  - "What's drawing you to an early-stage company right now?"
  - "Walk me through the most impactful project you led in the last year."
- Scorecard: 1-4 on communication, motivation, startup-fit

### Stage 2: Technical Deep-Dive (60 min)
- Evaluate: System design, code quality
- Format: Live system design discussion + code review exercise
- Scorecard: 1-4 on architecture thinking, code craft, trade-off reasoning

Prompt: "Our interviewers keep disagreeing on candidates."

Good output snippet:

This usually means you lack structured evaluation criteria. Three-step fix:

1. Define 4-5 competencies per role with written behavioral descriptions
2. Give each interviewer a scorecard to fill out independently BEFORE debrief
3. In the debrief, discuss only scores that diverge by 2+ points —
   focus on evidence, not impressions

The goal is calibrated, evidence-based evaluation — not consensus.

© shawnpang, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/interview-kit of shawnpang/startup-founder-skills.

Open the folder on GitHubat commit 4ad31b4

Compare with similar skills

Interview Kit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Interview Kit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Interview Kit this skillshawnpang/startup-founder-skills342—~2.1kAutomated safety check: PassMIT
Career-Ops Job Search Centercareer-ops-hq/career-ops74k—~3.6kAutomated safety check: PassMIT
Internship Project Preparation ToolLiuMengxuan04/shushu-internship-tool2.1k—~2.3kAutomated safety check: PassCustom licence
Interview Coachnoamseg/interview-coach-skill2.3k—~3.7kAutomated safety check: PassMIT
Job Application AssistantMadsLorentzen/ai-job-search45k—~1.2kAutomated safety check: NotesMIT
Algo Senseikaranb192/algo-sensei286—~1.7kAutomated safety check: PassMIT

Similar skills

  • Career-Ops Job Search Center

    career-ops-hq/career-ops

    Routes job-search requests to modes for evaluating offers, scanning portals, generating tailored CVs, tracking applications and drafting outreach, starting from a pasted job URL or description.

    74k GitHub stars~3.6k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Internship Project Preparation Tool

    LiuMengxuan04/shushu-internship-tool

    Turns a target internship job description into a resume-ready, interview-ready project by finding and auditing GitHub projects and drafting resume bullets and interview Q&A.

    2.1k GitHub stars~2.3k tokensUpdated 3 mo ago
    Business, Finance & HRAuto-check passed
  • Interview Coach

    noamseg/interview-coach-skill

    High-rigor interview coaching skill for job seekers. An agent skill from noamseg/interview-coach-skill.

    2.3k GitHub stars~3.7k tokensUpdated 4 mo ago
    Business, Finance & HRAuto-check passed
  • Job Application Assistant

    MadsLorentzen/ai-job-search

    Evaluates job postings against your profile, then tailors a LaTeX CV and cover letter and prepares interview answers for the roles you pursue.

    45k GitHub stars~1.2k tokensUpdated today
    Business, Finance & HRAuto-check: notes
  • Algo Sensei

    karanb192/algo-sensei

    Your personal DSA & LeetCode mentor. An agent skill from karanb192/algo-sensei.

    286 GitHub stars~1.7k tokensUpdated 7 days ago
    Business, Finance & HRAuto-check passed
  • Backend and Agent Project Selector

    lishuangqiang/backend-agent-resume-scout

    Finds backend or AI agent projects on GitHub that are worth putting on a resume, checks them against local source and writes a Markdown resume package.

    349 GitHub stars~1.4k tokensUpdated 3 mo ago
    Business, Finance & HRAuto-check passed

More from shawnpang/startup-founder-skills

All 50 skills in this repo
  • Accelerator Application

    shawnpang/startup-founder-skills

    When the user wants to apply to startup accelerators, incubators, or fellowship programs.

    342 GitHub stars~2.7k tokensUpdated 6 mo ago
    Auto-check passed
  • Architecture Design

    shawnpang/startup-founder-skills

    When the user needs to design or evaluate system architecture — service boundaries, data models, API contracts, infrastructure topology, database selection, or dependency analysis.

    342 GitHub stars~2.1k tokensUpdated 6 mo ago
    Auto-check passed
  • Board Update

    shawnpang/startup-founder-skills

    When the user needs to write a monthly or quarterly investor update, prepare a board deck, or communicate company progress to stakeholders.

    342 GitHub stars~2.3k tokensUpdated 6 mo ago
    Auto-check passed
  • Churn Analysis

    shawnpang/startup-founder-skills

    When the user needs to identify at-risk accounts, understand why customers are leaving, reduce churn rate, build health scores, design save plays, or create win-back campaigns.

    342 GitHub stars~2.3k tokensUpdated 6 mo ago
    Auto-check passed
  • Cicd Setup

    shawnpang/startup-founder-skills

    When the user needs to set up or improve CI/CD pipelines — GitHub Actions, GitLab CI, deployment automation, or says "set up CI", "automate deployment", "add tests to pipeline", "fix my build".

    342 GitHub stars~1.7k tokensUpdated 6 mo ago
    Auto-check passed
  • Code Review

    shawnpang/startup-founder-skills

    When the user asks for a code review, shares code for feedback, or says "review this", "check my code", "what's wrong with this".

    342 GitHub stars~1.9k tokensUpdated 6 mo ago
    Auto-check passed

Questions about Interview Kit

What does Interview Kit do?

When the user needs to design an interview process, create interview questions, build scorecards, calibrate interviewers, or evaluate candidates for a role. Interview Kit is an agent skill from shawnpang/startup-founder-skills. When the user needs to design an interview process, create interview questions, build scorecards, calibrate interviewers, or evaluate candidates for a role.

When should I use Interview Kit?

Interview Kit fits situations like: needs to design an interview process; create interview questions; build scorecards; calibrate interviewers.

How do I install Interview Kit in Claude Code?

Run `npx skills add shawnpang/startup-founder-skills --skill interview-kit -a claude-code`. Or copy the skill folder (skills/interview-kit in shawnpang/startup-founder-skills) into .claude/skills/interview-kit in your project. Claude Code loads it when a task matches its description.

How do I install Interview Kit in Codex?

Run `npx skills add shawnpang/startup-founder-skills --skill interview-kit -a codex`. Or copy the skill folder (skills/interview-kit in shawnpang/startup-founder-skills) into .agents/skills/interview-kit in your project. Codex loads it when a task matches its description.

Can I use Interview Kit in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add shawnpang/startup-founder-skills --skill interview-kit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/interview-kit, .gemini/skills/interview-kit, .github/skills/interview-kit and .opencode/skills/interview-kit in your project.

What does Interview Kit need to run?

SKILL.md names no scripts, command-line tools or credentials: Interview Kit is instructions for the agent only.

Does Interview Kit access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Interview Kit safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Interview Kit use?

Interview Kit is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Interview Kit use?

About 2.1k tokens (SKILL.md is roughly 8.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Interview Kit?

Skills that share tags, products or a category with Interview Kit: Career-Ops Job Search Center (career-ops-hq/career-ops, 74k stars), Internship Project Preparation Tool (LiuMengxuan04/shushu-internship-tool, 2.1k stars), Interview Coach (noamseg/interview-coach-skill, 2.3k stars) and Job Application Assistant (MadsLorentzen/ai-job-search, 45k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Interview Kit?

shawnpang (a GitHub user) maintains it in shawnpang/startup-founder-skills, which has 342 GitHub stars. The repository holds 50 skills in this directory. The repository was last updated on March 16, 2026.

Source: shawnpang/startup-founder-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.