FD
Franklin Decision Ledger
🔵 Stable🕐 updated 2026-10-06
✅ 4/5
🔷 SkillSpec L3
pm-dead-mentors
Run a hard two-option decision through Benjamin Franklin's 'moral or prudential algebra' — the weighted pro/con method he described to Joseph Priestley in 1772 — including the part everyone skips: striking out reasons that cancel, and letting the ledger sit before deciding. Use when weighing job offers, relocations, build-vs-buy, take-the-promotion, shut-it-down decisions, or any 'I keep going back and forth'. Produces a completed decision ledger with a leaning, its strongest counter, and a revisit date.
▶ Run it free — no key needed
📝 Grade your existing draft
⬇ Add to Claude (works in Duet)
📱 Use as an app
View SKILL.md ↗
What changed
🗣 Say this to your agent
“Help me decide between these two options.”“Weigh the pros and cons properly.”“Run Franklin's pro and con method on this choice.”“I can't decide whether to take the job.”
What to give it
▸The two options, stated as the user would say them — if there are three, split the decision or run twice — the algebra is pairwise
▸Everything currently pulling them each way, however small — or embarrassing
▸The deadline, and what happens if they decide — nothing
▸Who else the decision lands on — (family, team) — their motives belong in the ledger
✅ 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.
✓Weights came from the user — the assistant proposed none, but challenged at
✓least one
✓The cancellation pass actually happened, pairs named — without it this is an
✓ordinary pros/cons list and the skill has failed
✓The strongest counter-reason is presented in its best form (steelman), not
✓its dismissible form
✓Motives affecting other people appear in the ledger, attributed
✓The output ends with a revisit date, not just a verdict — the waiting period
⚠️ What it refuses to do
Do not decide for the user — the algebra's output is a *leaning* plus its
strongest counter; the user decides
Do not fill the ledger with invented motives to look thorough; every entry
traces to something the user said or confirmed
Do not let weights masquerade as objectivity — surface that a 5-point fear
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 -p pm-claude-skills 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="franklin-decision-ledger"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>
💬 Discussion
Franklin Decision Ledger is one of 1326 open-source professional AI agent skills — all SkillSpec L3.
Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog