Hiring Panel logo

Hiring Panel

Community
alexyc9381
hiring-panel

Run a resume past a hiring panel of seven Claudes that try to reject it (an automated screen, a hiring manager and five readers who each judge it alone as someone different), then rebuild it with every mistake fixed. Use when the user types /hiring-panel followed by a resume (a file path or pasted text), optionally with a job posting.

Overview

Publisheralexyc9381
Repositoryhiring-panel-skill
Skill namehiring-panel
Stars
101
Forks
15
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by alexyc9381 on GitHub. Read the source before you install it.

Installation

Install the Hiring Panel 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/alexyc9381/hiring-panel-skill/tree/main/skills/hiring-panel
  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.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/alexyc9381/hiring-panel-skill.git /tmp/hiring-panel-skill
mkdir -p .claude/skills
cp -r /tmp/hiring-panel-skill/skills/hiring-panel .claude/skills/hiring-panel
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Hiring Panel 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 Hiring Panel 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 Hiring Panel 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.

/hiring-panel

The user gives you a resume after /hiring-panel. You will run seven reviewers against it, then rebuild the resume with every mistake fixed. Never flatter the resume.

1. Get the resume and the job

Everything after /hiring-panel is the resume: a file path (read it; PDF is fine) or pasted text. If the user also gives a job posting or a role, use it. If there is no role at all, ask ONE question first: what job are you applying for? Then continue. Use only what is in the resume and what the user told you. Never invent employers, titles, dates, numbers or skills. When you assume something, label it "assumed".

2. The automated screen

Start one sub-agent: the automated system that decides whether a real human should even see this resume. Give it the resume and the job (if any). It checks, in this order:

  • Can the text be read top to bottom (columns, tables, text in images, odd section names)?
  • Are the job titles, employers and dates clear?
  • If there is a job posting: which of its key skills and terms appear in the resume, and which are missing?
  • Contact details present, length sensible, no filler. It answers: PASS or REJECT, then at most five reasons, each quoting the line it is about.

3. The hiring manager

Start one sub-agent: the hiring manager who decides whether this person gets an interview. It answers: INTERVIEW or NO, what decided it in the first ten seconds, what it would ask in the interview, and the three weakest lines (quoted).

4. Five readers, alone

Start five sub-agents at once (one message, five calls). Give each ONLY the resume (and the job) and ONE reader below. Nobody sees anybody else's notes. Each answers in under 120 words: HIRE, MAYBE or PASS, the one line that hurt most (quoted), and two more problems.

  1. The hiring manager. Reads for one thing: can this person do the job on day one?
  2. Another applicant. Applied for the same job. Reads as a rival: where is this resume weaker than mine?
  3. The CEO. Reads for impact: what did this person change, and by how much?
  4. The recruiter. Has 30 seconds and 100 resumes today. Reads the top third only.
  5. The teammate. Would work next to this person. Reads for how they work with others.

5. What is wrong

Merge all seven answers into ONE numbered list of mistakes, worst first. Merge duplicates. For each: the quoted line, why it gets rejected, and which of the seven flagged it.

6. Rebuild it

Write the improved resume: the same facts, with every numbered mistake fixed. Do not add anything that is not in the original or in what the user told you. Where a fix needs a fact you do not have, leave [ADD: ...] and list those questions at the end. Then start the automated-screen sub-agent once more on the new version and report the before and after verdict.

7. Write the result

Create .hiring-panel/<date>-<name>/ with PANEL.md (the seven verdicts and the numbered mistakes) and RESUME-IMPROVED.md (the new resume). Then show the user, in chat: one line per reviewer, the five worst mistakes, the before and after screen verdict, and where the files are. Touch no other files. End both files with this line: Made with /hiring-panel by Alex Chen (@nocodealex) · chen.media

Rules

  • Be honest. If the resume is strong, say so and say which reviewer came closest to rejecting it, and why it still held.
  • Do not invent facts about the user, their employers or real companies. Say "assumed" when you guess.
  • This is a structured second opinion made by language models. It does not guarantee an interview or a job, and it is not career or legal advice.

Frequently asked questions

What does the Hiring Panel AI skill do?

Run a resume past a hiring panel of seven Claudes that try to reject it (an automated screen, a hiring manager and five readers who each judge it alone as someone different), then rebuild it with every mistake fixed. Use when the user types /hiring-panel followed by a resume (a file path or pasted text), optionally with a job posting.

Why use Hiring Panel on TypingMind?

Because you install it once and use it with any model. Hiring Panel 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 Hiring Panel in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/alexyc9381/hiring-panel-skill/tree/main/skills/hiring-panel. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Hiring Panel?

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 Hiring Panel?

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

Is the Hiring Panel AI skill free?

Yes. It is published on GitHub by alexyc9381 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 👇