What do I need to use Decision Helper?

The options; What matters to you; The stakes & reversibility; Any hard constraints.

Is Decision Helper 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.

Decision Helper

Q: How do I know the Decision Helper output is good?

The skill verifies itself against its own quality checks: Criteria were drawn from what the user cares about, then weighted (not equal by default); Each option is scored against each criterion; A clear recommendation is given, with confidence — not "it depends"; The single decision-flipping unknown is named.

🔵 Stable🕐 updated 2026-08-04 🔷 SkillSpec L3 pm-personal

Help me decide between options with a weighted pros/cons that actually reaches a recommendation — not just two lists. Use when asked should I take job A or B, which one should I buy, help me decide, or make a pro/con list. Produces the criteria that matter (weighted by what you care about), the options scored against them, a clear recommendation with its confidence, and the single question that would flip the decision if you're still torn.

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

🗣 Say this to your agent

“Help me decide between two job offers.”“Which laptop should I buy — here are three?”“Should I move cities for this role? Make it a weighted decision.”“I'm torn between two apartments — help me choose.”“Make a real pro/con list and actually tell me what to pick.”

What to give it

▸The options — what you're choosing between (2+ concrete choices)

▸What matters to you — money, growth, stress, location, values… (or the skill will propose criteria and ask you to weight them)

▸The stakes & reversibility — one-way door or easily undone? (changes how much rigor is worth)

▸Any hard constraints — deal-breakers that filter options before scoring

✅ 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.

✓Criteria were drawn from what the user cares about, then weighted (not equal by default)

✓Each option is scored against each criterion

✓A clear recommendation is given, with confidence — not "it depends"

✓The single decision-flipping unknown is named

✓Reversibility is factored into how much certainty is worth chasing

✓The gut-check prompt is included

⚠️ What it refuses to do

**A flat pro/con list** with no weights and no decision.

**False precision** — inventing exact scores for things you can't know; use ranges and label assumptions.

**Refusing to recommend** — "both have merits" is the one thing the user came to avoid.

**Ignoring reversibility** — agonising over an easily-undone choice, or rushing a one-way door.

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

💬 Discussion

Decision Helper is one of 1078 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog