What do I need to use Purchase Justification?

The problem's evidence; The approver and their currency; The real numbers; The approval tiers.

Is Purchase Justification 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.

Purchase Justification

Q: How do I know the Purchase Justification output is good?

The skill verifies itself against its own quality checks: The status quo carries a conservative price in the approver's currency; ROI assumptions are labeled and the worst-case line appears; The cheaper alternative was steelmanned, not strawmanned; The ask fits its approval tier honestly (scoped, never split).

🔵 Stable🕐 updated 2026-07-19 🔷 SkillSpec L3 pm-cowork

Write the purchase request that gets approved — the cost-of-not-buying framing, the ROI math at the approver's altitude, the alternatives-considered section that preempts the obvious pushback, and the right-sized ask for the approval tier. Use when asked justify this tool/hire/equipment purchase, write the budget request, my requests keep getting deferred, or make the business case for this spend. Produces the justification memo: the problem priced, the ROI shown, alternatives dispatched, and the ask sized to its approval path.

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

What to give it

▸The problem's evidence — the hours lost, the incidents, the workaround's cost ([meeting-cost-meter](../meeting-cost-meter/SKILL.md)-style arithmetic on the status quo); requests without a priced problem are wishes with quotes attached

▸The approver and their currency — who signs at this amount, what they weigh (cost-saving? risk? team velocity?), and what's burned them before ([exec-vs-working-deck](../exec-vs-working-deck/SKILL.md) audience-currency logic)

▸The real numbers — the quote ([vendor-comparison-matrix](../vendor-comparison-matrix/SKILL.md) TCO, not license price), and the honest benefit estimate with its assumptions

▸The approval tiers — where the thresholds sit ($5k? $25k?); the sizing strategy needs the map

✅ 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.

✓The status quo carries a conservative price in the approver's currency

✓ROI assumptions are labeled and the worst-case line appears

✓The cheaper alternative was steelmanned, not strawmanned

✓The ask fits its approval tier honestly (scoped, never split)

✓Yes is the low-effort path: specific, dated, reversible where true

⚠️ What it refuses to do

Do not request against an unpriced status quo — free inertia beats every paid tool

Do not inflate the ROI — the first checked exaggeration taxes all future requests

Do not leave "use what we have" for the meeting — dispatch it in the memo or lose to it live

Do not split invoices to dodge thresholds — scope real pilots instead

Do not end with "thoughts?" — the ask is specific or the answer is deferral

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="purchase-justification"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Purchase Justification is one of 750 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog