What do I need to use Reference Request Kit?

The circumstances; Candidate referees; The target roles; The stories.

Is Reference Request Kit free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Reference Request Kit

Q: How do I know the Reference Request Kit output is good?

The skill verifies itself against its own quality checks: Every target-role claim has a referee who witnessed it; Warmth is assessed honestly and lukewarm candidates are cut or comfort-tested; Every ask contains a graceful out; Each briefing sheet cites only what that referee actually saw.

🔵 Stable🕐 updated 2026-07-17 🔷 SkillSpec L3 pm-layoff

Secure strong references after a departure — who to ask, the ask messages, the briefing sheet that makes their reference specific, and the LinkedIn recommendation swap. Use when asked to help me get references, write a reference request, prep my referee, or ask my old manager for a recommendation. Produces the referee shortlist with rationale, tailored ask messages, a one-page referee briefing sheet, and the follow-up etiquette.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

What to give it

▸The circumstances — layoff, resignation, complicated exit (this shapes who's safe to ask)

▸Candidate referees — names, roles, relationship, and honestly: how warm is each?

▸The target roles — references are chosen per claim the next job needs proven

▸The stories — 2–3 achievements each referee actually witnessed (a referee can't cite what they never saw)

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓Every target-role claim has a referee who witnessed it

✓Warmth is assessed honestly and lukewarm candidates are cut or comfort-tested

✓Every ask contains a graceful out

✓Each briefing sheet cites only what that referee actually saw

✓The per-use heads-up template exists

⚠️ What it refuses to do

Do not rank referees by title — checkers discount name-recognizers who can't give specifics

Do not send one generic ask to everyone — the relationship register is the persuasion

Do not skip the briefing sheet — unprepared enthusiasm comes out as "great person to work with," which checkers hear as nothing

Do not put words in a referee's mouth they can't own — briefing is reminding, not scripting fiction

Do not burn a complicated-exit bridge by asking the wrong person — the risk notes exist to be read

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="reference-request-kit"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Reference Request Kit is one of 599 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog