New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Interview Task

by polarsource in polarsource/polar

Prepare an interview task for a candidate, as part of our hiring process.

Apache-2.0Auto-check passedData & Analytics

Install Interview Task

skills CLI
$ npx skills add polarsource/polar --skill interview-task -a claude-code

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

GitHub CLI
$ gh skill install polarsource/polar interview-task --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/polarsource/polar.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/interview-task .claude/skills/interview-task && 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-task
GitHub stars
10k
Token cost
~933 tokens
SKILL.md length
394 words
Files
3 (incl. scripts)
Skills in repo
18
Repo updated
First seen
Licence
Apache-2.0

At a glance

Prepare an interview task for a candidate, as part of our hiring process.

  • Works in 5 steps: fork the Polar repository to a private… → create a branch for the PR → make changes to the codebase using LLM… → …
  • Data & Analytics work in your project
  • SKILL.md covers Input, Step 1: fork the Polar…, Step 2: create a branch for… and Step 3: make changes to the…, plus 2 more sections
  • Calls gh and git

What it does

Interview Task is an agent skill from polarsource/polar. Prepare an interview task for a candidate, as part of our hiring process.

Its SKILL.md is about 930 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts.

It sits in Data & Analytics. The repository describes itself as: Polar — A billing platform for the intelligence era. The licence is Apache-2.0.

When your agent uses it

  • Data & Analytics work in your project

Example prompts

  • “/interview-task”

Requirements

  • Pre-approved tools (allowed-tools): Bash(gh:*), Bash(git:*)

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. fork the Polar repository to a private GitHub repository dedicated to the candidate
  2. create a branch for the PR
  3. make changes to the codebase using LLM agent
  4. create a pull request
  5. add a comment to the PR asking the candidate to review it

What it can do on your machine

Read from SKILL.md and the folder at commit 599c727. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(gh:*)
    • Bash(git:*)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/, which the agent can run.

    Shell commands in SKILL.md call:

    • gh
    • git

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

  • Network

    No URLs in SKILL.md. Its commands use gh and git, which can reach the network depending on how they are called.

    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 Task loads about 933 tokens when it runs. Until then it costs about 22 tokens; SKILL.md has 394 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~22
When it runs · the whole SKILL.md, loaded when a task matches
~933

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); the scripts in this folder are not scanned.

SKILL.md

The full file from polarsource/polar at commit 599c727, republished under its Apache-2.0 licence (© polarsource). 394 words, ~933 tokens.

Download SKILL.mdSave it as .claude/skills/interview-task/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
interview-task
description
Prepare an interview task for a candidate, as part of our hiring process.
allowed-tools
Bash(gh:*), Bash(git:*)
user-invocable
true

Interview Task

This skill is a complete cookbook for creating an interview task for a candidate. It includes steps to create the necessary materials. The idea is to create a private repository for the candidate, and have an LLM agent draft a PR for a given task. The candidate will then be asked to review the PR, and provide feedback on it. This will allow us to evaluate the candidate's ability to understand the codebase, provide constructive feedback and good insights to get the task to the finish line.

Input

If not provided in the invocation prompt, you should ask the user for the following information:

  • Candidate's name
  • A prompt describing the PR that the LLM agent should draft. This should be a clear and concise description of the task that the candidate will be asked to review.

Step 1: fork the Polar repository to a private GitHub repository dedicated to the candidate

Run the script provided in this skill .claude/skills/interview-task/scripts/fork-repository with the candidate's name as an argument. This will create a private repository for the candidate.

The name of the candidate should be slugified (lowercase, ASCII, spaces replaced with hyphens) to be used in the repository name.

Example

  • Candidate's name: François Voron
bash
.claude/skills/interview-task/scripts/fork-repository francois-voron

Step 2: create a branch for the PR

Run the script provided in this skill .claude/skills/interview-task/scripts/setup-remote with the candidate's slug and the branch name as arguments. This will add a remote pointing to the candidate's fork, fetch it, create the branch, and push it to the remote. The branch name should be descriptive of the task.

Example

bash
.claude/skills/interview-task/scripts/setup-remote francois-voron add-new-feature
Show full SKILL.md (134 more words)Show less

Step 3: make changes to the codebase using LLM agent

Use an LLM agent to draft a PR in the candidate's repository. The PR should be based on the prompt provided by the user. The LLM agent should create one or more commits that implement the changes described in the prompt.

Step 4: create a pull request

Once the changes have been made, push the changes and create a pull request in the candidate's repository. The PR should be titled and described in a way that clearly communicates the changes that were made.

bash
git push && gh pr create --title "Add new feature" --body "This PR adds a new feature that allows users to do X, Y, and Z."

Step 5: add a comment to the PR asking the candidate to review it

Post a comment to this PR following the template below, asking the candidate to review the PR and provide feedback on it.

md
Hi <candidate>,

We have created this PR as part of our interview process. We would like you to review the changes and provide feedback on it. Please take your time to understand the codebase, and provide constructive feedback and good insights to get the task to the finish line.

## Expected Outcome

- A clear understanding of the changes made in the PR
- Constructive feedback on the implementation, including any potential issues or improvements that could be made
- A discussion on how to get the task to the finish line, including any additional changes that may be needed to complete the task

We **don't** expect you to actually implement the changes.

## Next Steps

Post your feedback as a comment on this PR, and we will review it together during our next interview session.

Command to post the comment:

bash
gh pr comment <pr-number> --body '<body>'

© polarsource, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts) in .agents/skills/interview-task of polarsource/polar.

  • SKILL.md
  • scripts/fork-repository
  • scripts/setup-remote

Open the folder on GitHubat commit 599c727

Compare with similar skills

Interview Task 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 Task compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Interview Task this skillpolarsource/polar10k—~933Automated safety check: PassApache-2.0
AI Daily DigestvigorX777/ai-daily-digest1.6k—~1.3kAutomated safety check: PassNone
Documd Visualsmarkdown-viewer/skills3.4k—~3.3kAutomated safety check: PassCC-BY-4.0
Retentioneering Contributingretentioneering/retentioneering-tools920—~1.8kAutomated safety check: PassApache-2.0
Agentic Kaggle WorkflowFrankS-IntelLab/agentic-kaggle-skill188—~4kAutomated safety check: PassMIT
Academic Figurejoshua-zyy/academic-paper-writer1141 repos~816Automated safety check: PassMIT

Similar skills

  • AI Daily Digest

    vigorX777/ai-daily-digest

    Fetches RSS feeds from 90 top Hacker News blogs (curated by Karpathy), uses AI to score and filter articles, and generates a daily digest in Markdown with Chinese-translated titles, category…

    1.6k GitHub stars~1.3k tokensUpdated 7 mo ago
    Data & AnalyticsAuto-check passed

  • Documd Visuals

    markdown-viewer/skills

    Create text-driven visuals in Markdown: charts, diagrams, cards, architecture and page layouts.

    3.4k GitHub stars~3.3k tokensUpdated 2 days ago
    Data & AnalyticsAuto-check passed

  • Retentioneering Contributing

    retentioneering/retentioneering-tools

    Help the user turn their Retentioneering ideas, friction reports, bug findings, or feature needs into high-quality upstream contributions: from capturing and validating the idea, through minimal…

    920 GitHub stars~1.8k tokensUpdated yesterday
    Data & AnalyticsAuto-check passed

  • Agentic Kaggle Workflow

    FrankS-IntelLab/agentic-kaggle-skill

    Takes a Kaggle competition from rules and validation design through baselines, ensembling and notebook architecture to a scored submission.

    188 GitHub stars~4k tokensUpdated 3 mo ago
    Data & AnalyticsAuto-check passed

  • Academic Figure

    joshua-zyy/academic-paper-writer

    Create, revise, or audit academic data/result figures for CS/AI/ML papers.

    114 GitHub starsUsed in 1 repo~816 tokens
    Data & AnalyticsAuto-check passed

  • Fast Dash

    dkedar7/fast_dash

    Build a Fast Dash web app from a Python function. An agent skill from dkedar7/fast_dash.

    129 GitHub stars~1.9k tokensUpdated 3 days ago
    Data & AnalyticsAuto-check passed

More from polarsource/polar

All 18 skills in this repo

  • Polar Python SDK

    polarsource/polar

    Integrate Polar billing in server-side Python applications using the versioned Polar and PolarAsync clients.

    10k GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Polar Typescript SDK

    polarsource/polar

    Integrate Polar billing in server-side TypeScript applications using the versioned createPolar and createPolarCore clients.

    10k GitHub stars~2k tokensUpdated today
    Auto-check passed

  • Adr Check

    polarsource/polar

    Check a code change against the repo's Accepted Architecture Decision Records (ADRs) in handbook/engineering/decisions/ and report violations with citations.

    10k GitHub stars~771 tokensUpdated today
    Auto-check passed

  • API Surface Review

    polarsource/polar

    Review changes to Polar's API contract — Pydantic schemas, FastAPI endpoints, OpenAPI output and the generated SDKs.

    10k GitHub stars~1.3k tokensUpdated today
    Auto-check passed

  • Billing Review

    polarsource/polar

    Review a diff that touches Polar's billing domain — subscriptions, cycles and crons, orders, billing entries, meters and usage, discounts, checkout, payments and dunning, refunds, disputes, payouts…

    10k GitHub stars~2.3k tokensUpdated today
    Auto-check passed

  • Open PR

    polarsource/polar

    Open or update a draft GitHub pull request after Polar-specific review and cubic CLI review.

    10k GitHub stars~586 tokensUpdated today
    Auto-check passed

Categories

Questions about Interview Task

What does Interview Task do?

Prepare an interview task for a candidate, as part of our hiring process. Interview Task is an agent skill from polarsource/polar. Prepare an interview task for a candidate, as part of our hiring process.

When should I use Interview Task?

Interview Task fits situations like: data & Analytics work in your project.

How do I install Interview Task in Claude Code?

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

How do I install Interview Task in Codex?

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

Can I use Interview Task 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 polarsource/polar --skill interview-task -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-task, .gemini/skills/interview-task, .github/skills/interview-task and .opencode/skills/interview-task in your project.

What does Interview Task need to run?

Going by SKILL.md and its folder, Interview Task needs the command-line tools its instructions call (gh and git). Its frontmatter pre-approves these tools: Bash(gh:*), Bash(git:*).

Does Interview Task access the network?

SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Interview Task 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Interview Task use?

Interview Task is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Interview Task use?

About 933 tokens (SKILL.md is roughly 3.7k 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 Task?

Skills that share tags, products or a category with Interview Task: AI Daily Digest (vigorX777/ai-daily-digest, 1.6k stars), Documd Visuals (markdown-viewer/skills, 3.4k stars), Retentioneering Contributing (retentioneering/retentioneering-tools, 920 stars) and Agentic Kaggle Workflow (FrankS-IntelLab/agentic-kaggle-skill, 188 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Interview Task?

polarsource (a GitHub organization) maintains it in polarsource/polar, which has 10,336 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 7, 2026.

Source: polarsource/polar on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.