Options
asgeirtj/system_prompts_leaks
Present multiple design options as a vertical stack of anchored turns
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…
MITAuto-check passed
Install Franklin Decision Ledger
$ npx skills add mohitagw15856/pm-claude-skills --skill franklin-decision-ledger -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mohitagw15856/pm-claude-skills franklin-decision-ledger --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/franklin-decision-ledger .claude/skills/franklin-decision-ledger && rm -rf skills-srcUse ~/.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/
Install the "franklin-decision-ledger" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/franklin-decision-ledger into .claude/skills/franklin-decision-ledger/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "franklin-decision-ledger", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/franklin-decision-ledgerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mohitagw15856/pm-claude-skills --skill franklin-decision-ledger -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mohitagw15856/pm-claude-skills franklin-decision-ledger --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/franklin-decision-ledger .agents/skills/franklin-decision-ledger && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "franklin-decision-ledger" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/franklin-decision-ledger into .agents/skills/franklin-decision-ledger/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "franklin-decision-ledger", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mohitagw15856/pm-claude-skills --skill franklin-decision-ledger -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mohitagw15856/pm-claude-skills franklin-decision-ledger --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/franklin-decision-ledger .cursor/skills/franklin-decision-ledger && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "franklin-decision-ledger" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/franklin-decision-ledger into .cursor/skills/franklin-decision-ledger/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "franklin-decision-ledger", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mohitagw15856/pm-claude-skills.git --path skills/franklin-decision-ledger--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mohitagw15856/pm-claude-skills --skill franklin-decision-ledger -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mohitagw15856/pm-claude-skills franklin-decision-ledger --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/franklin-decision-ledger .gemini/skills/franklin-decision-ledger && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "franklin-decision-ledger" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/franklin-decision-ledger into .gemini/skills/franklin-decision-ledger/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "franklin-decision-ledger", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mohitagw15856/pm-claude-skills franklin-decision-ledgerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mohitagw15856/pm-claude-skills --skill franklin-decision-ledger -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/franklin-decision-ledger .github/skills/franklin-decision-ledger && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "franklin-decision-ledger" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/franklin-decision-ledger into .github/skills/franklin-decision-ledger/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "franklin-decision-ledger", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mohitagw15856/pm-claude-skills --skill franklin-decision-ledger -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mohitagw15856/pm-claude-skills franklin-decision-ledger --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/franklin-decision-ledger .opencode/skills/franklin-decision-ledger && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "franklin-decision-ledger" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/franklin-decision-ledger into .opencode/skills/franklin-decision-ledger/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "franklin-decision-ledger", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
franklin-decision-ledger- GitHub stars
- 1.4k
- Token cost
- ~1.3k tokens
- SKILL.md length
- 634 words
- Files
- 1
- Skills in repo
- 1,348
- Repo updated
- First seen
- Licence
- MIT
At a glance
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…
- Works in 5 steps: Divide the paper — one column Pro, one… → Collect over time, not in one sitting —… → Weight each motive — the user assigns… → …
- Weighing job offers
- SKILL.md covers What This Skill Produces, Required Inputs, Framework: the algebra, as… and Output Format, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Franklin Decision Ledger is an agent skill from mohitagw15856/pm-claude-skills. 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.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
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
- Weighing job offers
- Take-the-promotion
- Shut-it-down decisions
- Any I keep going back and forth
Example prompts
- “moral or prudential algebra”
- “I keep going back and forth”
- “/franklin-decision-ledger”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Divide the paper — one column Pro, one Con, for Option A over Option B.
- Collect over time, not in one sitting — Franklin's instruction is to gather
- Weight each motive — the user assigns weights (1–5 works), not the assistant.
- Strike out equals — the step that makes it algebra: one Pro-3 cancels one
- Find where the balance lies, then wait — if a day or two of further thought
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
Franklin Decision Ledger loads about 1.3k tokens when it runs. Until then it costs about 134 tokens; SKILL.md has 634 words of instructions outside code blocks.
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). 634 words, ~1,343 tokens.
Download SKILL.mdSave it as
.claude/skills/franklin-decision-ledger/SKILL.md (or your agent's skills folder).- name
- franklin-decision-ledger
- description
- 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.
Franklin Decision Ledger Skill
In a 1772 letter to Joseph Priestley, Franklin laid out why hard decisions feel impossible: the reasons for and against are never "present to the mind at the same time" — whichever set you thought about most recently feels decisive. His fix, which he called moral or prudential algebra, is a ledger kept over days, with weights, where reasons of equal weight are struck out in pairs until one column visibly outweighs. This skill runs the full method — not the flattened pros-and-cons list it degenerated into.
What This Skill Produces
- A two-column decision ledger with every motive the user can surface, weighted
- The cancellation pass: equal weights struck out in pairs, remainder shown
- The leaning the algebra produces, its strongest surviving counter-reason, and what evidence would flip it
- A sit-on-it plan: what to add to the ledger over the next 1–2 days before committing (Franklin's "farther consideration" step)
Required Inputs
Ask for (if not already provided):
- 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
Framework: the algebra, as Franklin described it
- Divide the paper — one column Pro, one Con, for Option A over Option B.
- Collect over time, not in one sitting — Franklin's instruction is to gather motives "during three or four days consideration" as they occur. In one session: do three passes — practical, emotional, reputational — because different passes surface different motives. Then schedule the real-time additions (see output).
- Weight each motive — the user assigns weights (1–5 works), not the assistant. Probe the suspicious ones: a 5 that can't survive one "why?" is a 2 wearing fear.
- Strike out equals — the step that makes it algebra: one Pro-3 cancels one Con-3; two Con-2s cancel a Pro-4. Cross them out visibly. What remains after cancellation is the actual decision surface — usually two or three motives, which is why the method clears heads.
- Find where the balance lies, then wait — if a day or two of further thought adds nothing new to either column, decide accordingly. Franklin's claim was modest and right: the weights aren't precise, but with each motive considered comparatively, "I think I can judge better, and am less liable to make a rash step."
Show full SKILL.md (222 more words)Show less
Output Format
## The decision
[Option A vs Option B, one line each, deadline]
## The ledger — A over B
| Pro | w | Con | w |
[every motive, user-weighted]
## Cancellation pass
[struck pairs listed: "quiet team (3) cancels commute (3)" …]
Remaining: Pro [names + total] · Con [names + total]
## The leaning
[Which way the remainder points · the strongest SURVIVING counter-reason, stated
better than the user stated it · what single piece of evidence would flip this]
## Before you commit (Franklin's waiting step)
[2-3 motives likely to surface late — prompts, not inventions: "you haven't priced
X yet" · a revisit date within the deadline]Quality Checks
- 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 is part of the method
Anti-Patterns
- 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 and a 5-point salary bump were made commensurable by feel, and say so
- Do not skip the emotional pass because the decision "should be rational"; Franklin put prudence and inclination in the same ledger on purpose
Related
Log the final call in [[decision-journal]] with its falsifiable predictions — the ledger decides, the journal keeps you honest later.
Example Trigger Phrases
- "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."
© 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/franklin-decision-ledger of mohitagw15856/pm-claude-skills.
Open the folder on GitHubat commit 1cbf1f0
Compare with similar skills
Franklin Decision Ledger 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Franklin Decision Ledger this skillmohitagw15856/pm-claude-skills | 1.4k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Optionsasgeirtj/system_prompts_leaks | 69k | — | ~918 | Automated safety check: Pass | CC0-1.0 | |
| Hard Callalirezarezvani/claude-skills | 28k | — | ~1.8k | Automated safety check: Pass | MIT | |
| Recursive Decision Ledgeraffaan-m/ECC | 277k | 1 repos | ~701 | Automated safety check: Pass | MIT | |
| Options Strategy BacktestingHKUDS/Vibe-Trading | 35k | — | ~2k | Automated safety check: Pass | MIT | |
| Party Ledger Reconciliationsickn33/agentic-awesome-skills | 47k | 1 repos | ~5.2k | Automated safety check: Pass | MIT |
Similar skills
Hard Call
alirezarezvani/claude-skills
/em:hard-call — Framework for decisions with no good options.
Recursive Decision Ledger
affaan-m/ECC
Run repeated rollouts ("Prime Gauss" style recursive prompting) while keeping an append-only decision ledger of trials, marks, coherence checks, and promotion gates, so recursive confidence never…
Options Strategy Backtesting
HKUDS/Vibe-Trading
Backtests multi-leg option strategies by synthesizing Black-Scholes prices from the underlying, simulating PnL, Greeks exposure and expiration for crypto and equity options.
Party Ledger Reconciliation
sickn33/agentic-awesome-skills
Party ledger reconciliation: party type, name and PAN/VAT, ledger against statement balance, difference and reason, duplicates, confirmation status and adjustment.
- Official
Remove Option Or Flag
getsentry/sentry
Remove a Sentry option or FlagPole feature flag whose rollout is finished, in the correct PR order across sentry, getsentry, and sentry-options-automator.
More from mohitagw15856/pm-claude-skills
All 1,348 skills in this repoCar Tco
mohitagw15856/pm-claude-skills
Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…
Cs Health Scorecard
mohitagw15856/pm-claude-skills
Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.
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.
Feature Prioritisation
mohitagw15856/pm-claude-skills
Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.
Fire Number
mohitagw15856/pm-claude-skills
Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.
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.
Questions about Franklin Decision Ledger
What does Franklin Decision Ledger do?
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…. Franklin Decision Ledger is an agent skill from mohitagw15856/pm-claude-skills. 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.
When should I use Franklin Decision Ledger?
Franklin Decision Ledger fits situations like: weighing job offers; take-the-promotion; shut-it-down decisions; any I keep going back and forth.
How do I install Franklin Decision Ledger in Claude Code?
Run `npx skills add mohitagw15856/pm-claude-skills --skill franklin-decision-ledger -a claude-code`. Or copy the skill folder (skills/franklin-decision-ledger in mohitagw15856/pm-claude-skills) into .claude/skills/franklin-decision-ledger in your project. Claude Code loads it when a task matches its description.
How do I install Franklin Decision Ledger in Codex?
Run `npx skills add mohitagw15856/pm-claude-skills --skill franklin-decision-ledger -a codex`. Or copy the skill folder (skills/franklin-decision-ledger in mohitagw15856/pm-claude-skills) into .agents/skills/franklin-decision-ledger in your project. Codex loads it when a task matches its description.
Can I use Franklin Decision Ledger 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 franklin-decision-ledger -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/franklin-decision-ledger, .gemini/skills/franklin-decision-ledger, .github/skills/franklin-decision-ledger and .opencode/skills/franklin-decision-ledger in your project.
What does Franklin Decision Ledger need to run?
SKILL.md names no scripts, command-line tools or credentials: Franklin Decision Ledger is instructions for the agent only.
Does Franklin Decision Ledger 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 Franklin Decision Ledger 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 Franklin Decision Ledger use?
Franklin Decision Ledger 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 Franklin Decision Ledger use?
About 1.3k tokens (SKILL.md is roughly 5.4k 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 Franklin Decision Ledger?
Skills that share tags, products or a category with Franklin Decision Ledger: Options (asgeirtj/system_prompts_leaks, 69k stars), Hard Call (alirezarezvani/claude-skills, 28k stars), Recursive Decision Ledger (affaan-m/ECC, 277k stars) and Options Strategy Backtesting (HKUDS/Vibe-Trading, 35k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Franklin Decision Ledger?
mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 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.