New: 98,000+ 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

Reference Check Script

by mohitagw15856 in mohitagw15856/pm-claude-skills

Run a rigorous candidate reference check that surfaces real signal.

MITAuto-check passedEducation

Install Reference Check Script

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill reference-check-script -a claude-code

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

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills reference-check-script --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/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/reference-check-script .claude/skills/reference-check-script && 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
reference-check-script
GitHub stars
1.4k
Token cost
~1.1k tokens
SKILL.md length
544 words
Files
1
Skills in repo
1,322
Repo updated
First seen
Licence
MIT

At a glance

Run a rigorous candidate reference check that surfaces real signal.

  • Works in 6 steps: Relationship & context — how they worked… → Scope & performance — what the candidate… → Strengths — with a concrete example… → …
  • Asked to prepare
  • SKILL.md covers Working from a brief, Required Inputs, Output Format and Quality Checks, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Reference Check Script is an agent skill from mohitagw15856/pm-claude-skills. Run a rigorous candidate reference check that surfaces real signal. Use when asked to prepare or conduct reference calls for a job candidate, design reference questions, or build a reference-check rubric. Produces a structured question set, probing follow-ups, a red/yellow/green scoring rubric, and the legal guardrails — designed to get past 'they were great' without leading the referee.

Its SKILL.md is about 1.1k 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 Education, covering Quizzes and assessments and LLM guardrails. The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.

When your agent uses it

  • Asked to prepare
  • Conduct reference calls for a job candidate
  • Design reference questions
  • Build a reference-check rubric

Example prompts

  • “they were great”
  • “/reference-check-script”

Workflow steps

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

  1. Relationship & context — how they worked together, for how long, on what.
  2. Scope & performance — what the candidate actually owned; where they ranked among peers.
  3. Strengths — with a concrete example ("tell me about a time…").
  4. Growth areas — asked as "where did they most need to grow / what coaching helped?" (not "weaknesses").
  5. Working style — how they handle conflict, feedback, ambiguity, pressure.
  6. The rehire question — "Would you hire them again? For what kind of role?" — and listen to the hesitation.

What it can do on your machine

Read from SKILL.md and the folder at commit 1cbf1f0. 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

Reference Check Script loads about 1.1k tokens when it runs. Until then it costs about 103 tokens; SKILL.md has 544 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~103
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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 mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 544 words, ~1,080 tokens.

Download SKILL.mdSave it as .claude/skills/reference-check-script/SKILL.md (or your agent's skills folder).
name
reference-check-script
description
Run a rigorous candidate reference check that surfaces real signal. Use when asked to prepare or conduct reference calls for a job candidate, design reference questions, or build a reference-check rubric. Produces a structured question set, probing follow-ups, a red/yellow/green scoring rubric, and the legal guardrails — designed to get past 'they were great' without leading the referee.

Reference Check Script Skill

A reference check fails when it's a formality — you call, they say "great to work with," you tick the box. This skill writes a call that actually de-risks the hire: questions that make it safe and easy for a referee to be honest, follow-ups that open the gap between polite and true, and a rubric that turns what you hear into a defensible signal.

Working from a brief

Given the role and what you need to validate, write the full script — tailor the questions to the specific concerns (the shaky interview signal, the seniority stretch, the manager-vs-IC question). Default to a ~20–25 minute call structure.

Required Inputs

Ask for (if not provided, else infer and label the assumption):

  • Role and level, and the 1–3 things to validate or de-risk (the open questions from interviews)
  • Referee relationship to the candidate (former manager / peer / report / client)
  • Reference type — candidate-provided or back-channel (changes how candid you probe)

Output Format

Framing (how to open)

A 2–3 sentence opener that sets candor: confidential, no scripted "sales pitch" needed, you're calibrating not gatekeeping. The single most important move — referees mirror the tone you set.

Question set (in order)

Grouped, with the intent of each noted:

  1. Relationship & context — how they worked together, for how long, on what.
  2. Scope & performance — what the candidate actually owned; where they ranked among peers.
  3. Strengths — with a concrete example ("tell me about a time…").
  4. Growth areas — asked as "where did they most need to grow / what coaching helped?" (not "weaknesses").
  5. Working style — how they handle conflict, feedback, ambiguity, pressure.
  6. The rehire question — "Would you hire them again? For what kind of role?" — and listen to the hesitation.
Probing follow-ups

The second question that opens the gap: "Can you give me an example?" · "How did that compare to others at that level?" · "What would their harshest fair critic say?" · silence (let them fill it).

Show full SKILL.md (223 more words)Show less
Scoring rubric
Signal🟢 Green🟡 Yellow🔴 Red
Specificityconcrete examplesgeneric praiseevasive / can't recall
Rehireenthusiastic, unpromptedqualifiedhesitation or no
Growth honestycandid, coachablevaguedefensive / dodged

Plus a one-line overall read and any follow-up to run (e.g. a back-channel if listed refs are all glowing-but-generic).

Ask about job performance only. Do not ask about age, health/disability, family/pregnancy, religion, national origin, or other protected characteristics. Keep it consistent across candidates so it's comparable and defensible.

Quality Checks

  • The opener explicitly invites candor (not a box-tick)
  • Questions are open and non-leading — no "they were a great team player, right?"
  • At least one question forces a concrete example and one comparative ranking
  • The rehire question is included and its hesitation is scored, not just its answer
  • The rubric converts what's heard into 🟢🟡🔴 with an overall read
  • Protected-class questions are explicitly excluded; the script is consistent across candidates

Anti-Patterns

  • Leading questions that hand the referee the answer
  • Accepting "they were great" without a follow-up for a specific example
  • Only calling candidate-selected references (all curated to be positive)
  • Treating the call as confirmation, not investigation
  • Asking anything about protected characteristics
  • No rubric — a vibe instead of a comparable, documented signal

Example Trigger Phrases

  • "Prepare reference calls for this candidate."
  • "Design reference questions."
  • "Build a reference-check rubric."
  • "What should I ask this candidate's references?"

© mohitagw15856, 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/reference-check-script of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Reference Check Script 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.

Reference Check Script compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Reference Check Script this skillmohitagw15856/pm-claude-skills1.4k—~1.1kAutomated safety check: PassMIT
Matlab Apply Assignment Guardrailsmatlab/agent-skills-playground181—~1.4kAutomated safety check: PassCustom licence
Team Deliverablesslgoodrich/agents138—~2.2kAutomated safety check: PassCustom licence
AI Engineering Placement Quizrohitg00/ai-engineering-from-scratch66k—~2kAutomated safety check: PassMIT
AI Engineering Phase Quizrohitg00/ai-engineering-from-scratch66k—~2.1kAutomated safety check: PassMIT
Claude Certification Tutorrohitg00/ai-engineering-from-scratch66k—~3kAutomated safety check: PassMIT

Similar skills

  • Matlab Apply Assignment Guardrails

    matlab/agent-skills-playground

    A skill your agent uses when a learner asks for help with MATLAB homework, labs, projects, graded assignments, take-home exams, quizzes, or any programming task where academic integrity, course…

    181 GitHub stars~1.4k tokensUpdated 27 days ago
    EducationAuto-check passed

  • Team Deliverables

    slgoodrich/agents

    Output templates and scoring rubrics for multi-agent team workflows.

    138 GitHub stars~2.2k tokensUpdated 6 mo ago
    EducationAuto-check passed

  • AI Engineering Placement Quiz

    rohitg00/ai-engineering-from-scratch

    Runs a 10-question quiz across five areas to place a learner in the AI Engineering from Scratch curriculum, so they skip what they already know.

    66k GitHub stars~2k tokensUpdated yesterday
    EducationAuto-check passed

  • AI Engineering Phase Quiz

    rohitg00/ai-engineering-from-scratch

    Quizzes you on a completed phase of the AI Engineering from Scratch course, taking a phase number or name and mapping it to that phase's directory.

    66k GitHub stars~2.1k tokensUpdated yesterday
    EducationAuto-check passed

  • Claude Certification Tutor

    rohitg00/ai-engineering-from-scratch

    Guides a learner through one of four independent Claude certification tracks with onboarding, lessons, practice labs, mock exams and remediation.

    66k GitHub stars~3k tokensUpdated yesterday
    EducationAuto-check passed

  • Generate Verifiers Env

    adithya-s-k/FineEnvs

    Builds a Verifiers (PrimeIntellect) variant of an RL environment.

    443 GitHub starsUsed in 1 repo~2.3k tokens
    EducationAuto-check passed

More from mohitagw15856/pm-claude-skills

All 1,322 skills in this repo

  • Exit Waterfall

    mohitagw15856/pm-claude-skills

    Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.

    1.4k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated today
    Auto-check passed

  • Freelance Rate

    mohitagw15856/pm-claude-skills

    Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.

    1.4k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Offer Comparison

    mohitagw15856/pm-claude-skills

    Compare two or more job offers as total-comp curves over four years — vesting cliffs, bonuses, 401(k) match, and the crossover year computed, not vibed.

    1.4k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Refinance Breakeven

    mohitagw15856/pm-claude-skills

    Compute the month a refinance actually starts saving money — payment delta, breakeven month, and total interest on both paths including the term-reset trap.

    1.4k GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Rent Vs Buy

    mohitagw15856/pm-claude-skills

    Model rent-vs-buy honestly — year-by-year net position for both paths including the assumption everyone drops (the renter invests the difference), with a breakeven horizon instead of a verdict.

    1.4k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

Categories

Questions about Reference Check Script

What does Reference Check Script do?

Run a rigorous candidate reference check that surfaces real signal. Reference Check Script is an agent skill from mohitagw15856/pm-claude-skills. Run a rigorous candidate reference check that surfaces real signal.

When should I use Reference Check Script?

Reference Check Script fits situations like: asked to prepare; conduct reference calls for a job candidate; design reference questions; build a reference-check rubric.

How do I install Reference Check Script in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill reference-check-script -a claude-code`. Or copy the skill folder (skills/reference-check-script in mohitagw15856/pm-claude-skills) into .claude/skills/reference-check-script in your project. Claude Code loads it when a task matches its description.

How do I install Reference Check Script in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill reference-check-script -a codex`. Or copy the skill folder (skills/reference-check-script in mohitagw15856/pm-claude-skills) into .agents/skills/reference-check-script in your project. Codex loads it when a task matches its description.

Can I use Reference Check Script 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 mohitagw15856/pm-claude-skills --skill reference-check-script -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/reference-check-script, .gemini/skills/reference-check-script, .github/skills/reference-check-script and .opencode/skills/reference-check-script in your project.

What does Reference Check Script need to run?

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

Does Reference Check Script 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 Reference Check Script 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 Reference Check Script use?

Reference Check Script 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 Reference Check Script use?

About 1.1k tokens (SKILL.md is roughly 4.3k 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 Reference Check Script?

Skills that share tags, products or a category with Reference Check Script: Matlab Apply Assignment Guardrails (matlab/agent-skills-playground, 181 stars), Team Deliverables (slgoodrich/agents, 138 stars), AI Engineering Placement Quiz (rohitg00/ai-engineering-from-scratch, 66k stars) and AI Engineering Phase Quiz (rohitg00/ai-engineering-from-scratch, 66k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Reference Check Script?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,431 GitHub stars. The repository holds 1,322 skills in this directory. The repository was last updated on October 7, 2026.

Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.