Interview Candidate Assessment Report

A recruiter-side skill that turns a resume plus job requirements into an offline HTML report with a candidate profile, prioritized resume red flags, and 12–18 ready-to-read interview questions.

Docs & OfficeIntermediate★ 701⑂ 58AI score 9/10Last updated: Aug 23, 2026

What it does

Parses the resume (including page-by-page PDF checks) and the job requirements into a role model: work outputs → key tasks → competencies → acceptable evidence → verification method.
Builds an evidence ledger from each resume claim, clearly separating stated facts, external corroboration, inference, and unknowns.
Produces a fully offline HTML report with exactly three modules: candidate profile, resume gaps/red flags, and the question set. Each question supports "must ask / maybe ask / backup" flags plus good–average–poor ratings and notes, auto-saved in the local browser with export and clear.
Strong guardrails: no emails/phones/ID numbers in the report, no inferring age, hometown or marital status, and hard stops against automated rejection, ranking or personality diagnosis.
Full scoring, weights and source logs stay in backstage JSON files for audit and human review.

Who it's for

Recruiters, HR and hiring managers running structured, evidence-based interviews.
Team leads hiring for technical or AI/LLM roles that need deep capability probing.
Small teams that want a written record of answers for consistent decisions.
Not for candidates practicing mock interviews, background snooping, or auto-screening.

Examples

"Use this senior backend JD and this resume PDF to build an interview report" → creates a case folder and an HTML file with 15 prioritized questions.
Hiring an LLM engineer: the skill loads its AI/LLM role adapter and generates work-sample questions that separate original design from simple API calls.
During the interview, open the HTML, flag must-ask questions, record ratings and notes, then export the results for the panel.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/dongshuyan/compass-skills/HEAD/skills/assess-interview-candidate/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)

Download the ZIP with the button below.
In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.

↓ Download ZIP

Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/assess-interview-candidate folder from the GitHub repo dongshuyan/compass-skills into my ~/.claude/skills/assess-interview-candidate/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/dongshuyan/compass-skills.git && mkdir -p ~/.claude/skills && cp -r compass-skills/skills/assess-interview-candidate ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

Open a terminal.
Clone the repo: git clone https://github.com/dongshuyan/compass-skills.git
Create the skills folder: mkdir -p ~/.claude/skills
Copy the whole skill directory (references/scripts/assets must come along): cp -r compass-skills/skills/assess-interview-candidate ~/.claude/skills/
Verify Python 3.10 or newer: python3 --version
Restart Claude Code and ask something like "Build a candidate assessment report from this resume and this job description", giving the resume path and an output folder.
Open the generated HTML in output/ with your browser and use it live during the interview.

View source on GitHub ↗License: MIT