pm-claude-skills 62.2.0 → 63.0.0

package/README.md

@@ -1,8 +1,8 @@
-# 🧠 PM Skills — 771 Professional Agent Skills for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes
+# 🧠 PM Skills — 776 Professional Agent Skills for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes
 
 <p align="center">
   <a href="https://mohitagw15856.github.io/pm-claude-skills/">
-    <img src="web/docs-assets/hero.svg" width="100%" alt="PM Skills — 771 professional skills your AI assistant can read. Plain markdown, works with Claude, ChatGPT, Gemini, Cursor, and Codex. MIT licensed." />
+    <img src="web/docs-assets/hero.svg" width="100%" alt="PM Skills — 776 professional skills your AI assistant can read. Plain markdown, works with Claude, ChatGPT, Gemini, Cursor, and Codex. MIT licensed." />
   </a>
 </p>
 
@@ -23,7 +23,7 @@
 ## What is PM Skills?
 
 <!-- AEO Answer Capsule — 68 words -->
-PM Skills is an open-source library of 771 Agent Skills — plain-markdown SKILL.md files that teach an AI assistant to do one professional task to a senior professional's standard, from writing a PRD to decoding a lease or running a blameless postmortem. Each skill bundles the framework, an output template, quality checks, and anti-patterns. It is MIT-licensed and works with Claude, ChatGPT, Gemini, Cursor, and Codex.
+PM Skills is an open-source library of 776 Agent Skills — plain-markdown SKILL.md files that teach an AI assistant to do one professional task to a senior professional's standard, from writing a PRD to decoding a lease or running a blameless postmortem. Each skill bundles the framework, an output template, quality checks, and anti-patterns. It is MIT-licensed and works with Claude, ChatGPT, Gemini, Cursor, and Codex.
 <!-- End AEO Capsule -->
 
 **Decode a lease before you sign it. Write a PRD your team can execute. Simulate the promotion committee before the real one meets. Check the weather with zero API keys.** Generic AI gives you filler; these give you the structure a senior professional actually uses.
@@ -70,7 +70,7 @@ Anything below is a real ask that activates a real skill — say it in your own
 | 🛂 *"prep me for the visa interview"* → [the-visa-interview](skills/the-visa-interview/SKILL.md) | 🔨 *"is this contractor quote fair?"* → [home-contractor-quote-decoder](skills/home-contractor-quote-decoder/SKILL.md) | 🏡 *"should we rent or buy?"* → [rent-vs-buy](skills/rent-vs-buy/SKILL.md) |
 | 📝 *"draft my self-review honestly"* → [performance-review](skills/performance-review/SKILL.md) | 🚀 *"are we ready to launch?"* → [product-launch-checklist](skills/product-launch-checklist/SKILL.md) | 📬 *"my inbox is 4,000 deep"* → [email-triage-system](skills/email-triage-system/SKILL.md) |
 
-…all 771 asks live in **[the catalog](SKILLS.md)**.
+…all 776 asks live in **[the catalog](SKILLS.md)**.
 
 ## ⚡ Quick start
 
@@ -86,7 +86,7 @@ No `npm install` needed — `npx pm-claude-skills …` always runs the latest. `
 
 ## 📚 The skills
 
-Every skill follows the same discipline: what it produces, the inputs it needs, a real framework (severity scales, decision rules — not vibes), a concrete output template, quality checks, and anti-patterns. All 771 pass the [SkillSpec](SKILLSPEC.md) L3 gate and a security audit in CI.
+Every skill follows the same discipline: what it produces, the inputs it needs, a real framework (severity scales, decision rules — not vibes), a concrete output template, quality checks, and anti-patterns. All 776 pass the [SkillSpec](SKILLSPEC.md) L3 gate and a security audit in CI.
 
 <table align="center">
   <tr align="center">
@@ -121,6 +121,7 @@ Every skill follows the same discipline: what it produces, the inputs it needs,
 | 📡 **Live data** (17) | Real-time answers with **zero API keys** — weather, rates, flights, scores, all over plain curl | [weather](skills/weather-now/SKILL.md) · [currency](skills/currency-rates/SKILL.md) · [crypto](skills/crypto-prices/SKILL.md) · [flights](skills/flight-tracker/SKILL.md) · [earthquakes](skills/earthquake-watch/SKILL.md) · [is-it-down](skills/site-check/SKILL.md) |
 | 🏠 **Life admin** | The unglamorous logistics, done in order | [relocation](skills/relocation-planner/SKILL.md) · [new parent](skills/new-parent-logistics/SKILL.md) · [caregiving](skills/caregiver-coordination/SKILL.md) · [doctor visits](skills/doctor-visit-prep/SKILL.md) · [records requests](skills/medical-records-request/SKILL.md) |
 | 💼 **Career moments** | The weeks that decide years | [layoff kit](plugins/pm-layoff/) · [resignation kit](plugins/pm-resignation/) · [PIP response](skills/pip-responder/SKILL.md) · [first 90 days as manager](skills/manager-first-90-days/SKILL.md) · [interview gauntlet](plugins/pm-jobsearch/) |
+| 🏛 **Dead mentors** (5) 🆕 | History's sharpest operators, resurrected — the *real* methods from public-domain classics, applied to modern work | [Machiavelli on office politics](skills/machiavelli-counsel/SKILL.md) · [Sun Tzu on picking your fights](skills/sun-tzu-strategy-brief/SKILL.md) · [Franklin's decision algebra](skills/franklin-decision-ledger/SKILL.md) · [Marcus Aurelius on bad days](skills/stoic-setback-debrief/SKILL.md) · [Bennett's 1908 time audit](skills/bennett-time-audit/SKILL.md) |
 | 🧾 **Freelance & renters & parents** | Small bundles for specific lives | [pricing your services](skills/pricing-your-services/SKILL.md) · [late invoices](skills/late-invoice-escalation/SKILL.md) · [deposit recovery](skills/security-deposit-recovery/SKILL.md) · [IEP meetings](skills/iep-504-meeting-kit/SKILL.md) · [students](plugins/pm-students/) |
 | 🤝 **Cowork** (100) | The office knowledge work an AI coworker actually does — the *frameworks* — [the whole bundle](plugins/pm-cowork/) | [email triage](skills/email-triage-system/SKILL.md) · [spreadsheet audit](skills/spreadsheet-audit/SKILL.md) · [meeting cost meter](skills/meeting-cost-meter/SKILL.md) · [deck outline first](skills/deck-outline-first/SKILL.md) · [saying no kindly](skills/saying-no-kindly/SKILL.md) · [delegation brief](skills/delegation-brief/SKILL.md) |
 | ⚡ **Cowork · Live** (12) | The same jobs, *done* — Claude Cowork acts on your **real data** via connectors + sandbox and returns an artifact — [the whole bundle](plugins/pm-cowork-live/) | [inbox triage (live)](skills/inbox-triage-live/SKILL.md) · [meeting prep (live)](skills/meeting-prep-live/SKILL.md) · [spreadsheet audit (live)](skills/spreadsheet-audit-live/SKILL.md) · [deck from doc](skills/deck-from-doc/SKILL.md) · [thread → decision](skills/thread-to-decision-live/SKILL.md) · [PR description (live)](skills/pr-description-live/SKILL.md) |
@@ -134,7 +135,7 @@ Every skill follows the same discipline: what it produces, the inputs it needs,
 | <img src="web/docs-assets/logos/pm-design.svg" width="20" alt=""/> [Design & UX](plugins/pm-design/) | <img src="web/docs-assets/logos/pm-legal.svg" width="20" alt=""/> [Legal](plugins/pm-legal/) | <img src="web/docs-assets/logos/pm-finance.svg" width="20" alt=""/> [Finance](plugins/pm-finance/) |
 | <img src="web/docs-assets/logos/pm-founders.svg" width="20" alt=""/> [Founders](plugins/pm-founders/) | <img src="web/docs-assets/logos/pm-security.svg" width="20" alt=""/> [Security](plugins/pm-security/) | <img src="web/docs-assets/logos/pm-gov.svg" width="20" alt=""/> [Government](plugins/pm-gov/) |
 
-…plus HR, sales, operations, research, healthcare, educators, writers, social media, and more — **[the full profession index](SKILLS.md)**, or by bundle in [`plugins/`](plugins/) (94 bundles). Install any bundle: `/plugin install pm-decoders@pm-skills`.
+…plus HR, sales, operations, research, healthcare, educators, writers, social media, and more — **[the full profession index](SKILLS.md)**, or by bundle in [`plugins/`](plugins/) (95 bundles). Install any bundle: `/plugin install pm-decoders@pm-skills`.
 
 ### Meta
 
@@ -238,13 +239,13 @@ The whole library on one poster — start path, standout features, and install o
 
 ## 🆕 Latest
 
-**v62.2.0 — the distribution wave:** **[SkillScan](mcp-remote/)** (the security scan as a free service for anyone's SKILL.md), **[opt-in usage telemetry](docs/TELEMETRY.md)** (counts, never content), **[SkillBench v2](skillbench/tasks-v2.json)** (deterministic ground-truth checks + cross-family judge panels), the **[starter-pack quiz](https://mohitagw15856.github.io/pm-claude-skills/starter-pack.html)**, the **[Wall of Wins](https://mohitagw15856.github.io/pm-claude-skills/wins.html)**, a **[WhatsApp bot](integrations/whatsapp/)** + **[Apple Shortcuts](integrations/shortcuts/)**, and honest **[glossary](https://mohitagw15856.github.io/pm-claude-skills/what-are-agent-skills.html)** / **[comparison](https://mohitagw15856.github.io/pm-claude-skills/compare.html)** pages. *Earlier — v62.1, nine frontiers* (MCP Apps widgets, the update bot, shared sessions, Telegram, local-model tier); *v62.0, adopt-a-profession.* Full history: **[CHANGELOG](CHANGELOG.md)** · [releases](https://github.com/mohitagw15856/pm-claude-skills/releases)
+**v63.0.0 — the dead mentors:** history's sharpest operators, resurrected as skills — **[Machiavelli](skills/machiavelli-counsel/SKILL.md)** reads your reorg (with the honest counterweight built in), **[Sun Tzu](skills/sun-tzu-strategy-brief/SKILL.md)** decides fight/reshape/decline, **[Franklin's decision algebra](skills/franklin-decision-ledger/SKILL.md)** settles the offer you keep flip-flopping on, **[Marcus Aurelius](skills/stoic-setback-debrief/SKILL.md)** debriefs the day that went badly, and **[Arnold Bennett (1908)](skills/bennett-time-audit/SKILL.md)** finds your inner day — real methods from public-domain classics, chapter-cited, never misquoted. *Earlier — v62.2, the distribution wave* (SkillScan, telemetry, SkillBench v2, quiz, wins, WhatsApp); *v62.1, nine frontiers.* Full history: **[CHANGELOG](CHANGELOG.md)** · [releases](https://github.com/mohitagw15856/pm-claude-skills/releases)
 
 ## ❓ First-timer questions, straight answers
 
 <details>
 <summary><b>Is it actually free?</b></summary>
-Yes — MIT, all 771 skills, forever. The skills are markdown; there is nothing to gate. Sponsors fund the playground's free model runs, not access.
+Yes — MIT, all 776 skills, forever. The skills are markdown; there is nothing to gate. Sponsors fund the playground's free model runs, not access.
 </details>
 
 <details>
@@ -287,4 +288,4 @@ MIT — use them, fork them, ship them at work. Skills are judgment, and judgmen
 
 ---
 
-*Built by [Mohit](https://github.com/mohitagw15856) with Claude. 771 skills · 94 bundles · 35 professions · every commit gated. The long version of this README — every feature, wave, and frontier bet — lives in the **[Showcase](docs/SHOWCASE.md)**.*
+*Built by [Mohit](https://github.com/mohitagw15856) with Claude. 776 skills · 95 bundles · 35 professions · every commit gated. The long version of this README — every feature, wave, and frontier bet — lives in the **[Showcase](docs/SHOWCASE.md)**.*

package/exports/README.md

@@ -8,7 +8,7 @@ by hand; edit the source skill and run:
 node scripts/build-exports.mjs
 ```
 
-Currently exporting **771 skills** to:
+Currently exporting **776 skills** to:
 
 - **ChatGPT — Custom GPT instructions** → `exports/chatgpt/`
 - **Google Gemini — Gem instructions** → `exports/gemini/`

package/exports/aider/README.md

@@ -3,7 +3,7 @@
 > Auto-generated from `skills/*/SKILL.md` by `scripts/build-exports.mjs`.
 > **Do not edit these files by hand** — edit the source skill and regenerate.
 
-771 skills exported. Copy a `.md rule` into the tool to use it.
+776 skills exported. Copy a `.md rule` into the tool to use it.
 
 | Skill | Bundle | Path |
 |---|---|---|
@@ -57,6 +57,7 @@
 | Behavior Intervention Plan | `pm-teaching` | `pm-teaching/behavior-intervention-plan/behavior-intervention-plan.md` |
 | Beneficiary Audit | `pm-estate` | `pm-estate/beneficiary-audit/beneficiary-audit.md` |
 | Benefits Decoder | `pm-decoders` | `pm-decoders/benefits-decoder/benefits-decoder.md` |
+| Bennett Time Audit | `pm-dead-mentors` | `pm-dead-mentors/bennett-time-audit/bennett-time-audit.md` |
 | Bid / Tender Review | `pm-construction` | `pm-construction/bid-tender-review/bid-tender-review.md` |
 | Blast Radius Drill | `pm-seatbelt` | `pm-seatbelt/blast-radius-drill/blast-radius-drill.md` |
 | Board Deck Narrative | `pm-business` | `pm-business/board-deck-narrative/board-deck-narrative.md` |
@@ -316,6 +317,7 @@
 | Form Filler Operator | `pm-operator` | `pm-operator/form-filler-operator/form-filler-operator.md` |
 | Formula Detangler | `pm-cowork` | `pm-cowork/formula-detangler/formula-detangler.md` |
 | Founder-Market Fit | `pm-founders` | `pm-founders/founder-market-fit/founder-market-fit.md` |
+| Franklin Decision Ledger | `pm-dead-mentors` | `pm-dead-mentors/franklin-decision-ledger/franklin-decision-ledger.md` |
 | Freelance Rate | `pm-calculators` | `pm-calculators/freelance-rate/freelance-rate.md` |
 | Frontend Design | `pm-design` | `pm-design/frontend-design/frontend-design.md` |
 | Fundraising FAQ | `pm-founders` | `pm-founders/fundraising-faq/fundraising-faq.md` |
@@ -411,6 +413,7 @@
 | Local Dev Setup | `pm-engineering` | `pm-engineering/local-dev-setup/local-dev-setup.md` |
 | Localization Brief | `pm-localization` | `pm-localization/localization-brief/localization-brief.md` |
 | Logistics Incident Report | `pm-supplychain` | `pm-supplychain/logistics-incident-report/logistics-incident-report.md` |
+| Machiavelli Counsel | `pm-dead-mentors` | `pm-dead-mentors/machiavelli-counsel/machiavelli-counsel.md` |
 | Manager First 90 Days | `pm-people` | `pm-people/manager-first-90-days/manager-first-90-days.md` |
 | Managing Up | `pm-comms` | `pm-comms/managing-up/managing-up.md` |
 | Marketing Funnel Plan | `pm-growth` | `pm-growth/marketing-funnel-plan/marketing-funnel-plan.md` |
@@ -671,6 +674,7 @@
 | Statement of Work | `pm-consulting` | `pm-consulting/statement-of-work/statement-of-work.md` |
 | Status Report Pipeline | `pm-cowork` | `pm-cowork/status-report-pipeline/status-report-pipeline.md` |
 | Stock Snapshot | `pm-live` | `pm-live/stock-snapshot/stock-snapshot.md` |
+| Stoic Setback Debrief | `pm-dead-mentors` | `pm-dead-mentors/stoic-setback-debrief/stoic-setback-debrief.md` |
 | Story Pitch | `pm-journalism` | `pm-journalism/story-pitch/story-pitch.md` |
 | Strategic Narrative Generator | `pm-strategy` | `pm-strategy/strategic-narrative-generator/strategic-narrative-generator.md` |
 | Strategy Memo | `pm-business` | `pm-business/strategy-memo/strategy-memo.md` |
@@ -685,6 +689,7 @@
 | Substack Notes Scraper | `pm-writers` | `pm-writers/substack-notes-scraper/substack-notes-scraper.md` |
 | Subtitle & Caption | `pm-localization` | `pm-localization/subtitle-caption/subtitle-caption.md` |
 | Sun and Moon | `pm-live` | `pm-live/sun-and-moon/sun-and-moon.md` |
+| Sun Tzu Strategy Brief | `pm-dead-mentors` | `pm-dead-mentors/sun-tzu-strategy-brief/sun-tzu-strategy-brief.md` |
 | Supplier Scorecard | `pm-supplychain` | `pm-supplychain/supplier-scorecard/supplier-scorecard.md` |
 | Support Macro | `pm-support` | `pm-support/support-macro/support-macro.md` |
 | Support Runbook | `pm-support` | `pm-support/support-runbook/support-runbook.md` |

package/exports/aider/pm-dead-mentors/bennett-time-audit/bennett-time-audit.md

@@ -0,0 +1,95 @@
+# Bennett Time Audit Skill
+
+Bennett wrote the original time-management book for commuters and clerks, and its
+opening reframe still cuts: time is "the inexplicable raw material of everything",
+delivered fresh daily — you cannot earn more of it, and you cannot waste it in
+advance. His program is deliberately unheroic: don't optimise the job; build a small
+**day within the day** from the hours around it, and start with ninety minutes three
+evenings a week, expecting it to be hard. This skill runs his audit and his program,
+including his warnings, which modern productivity advice quietly dropped.
+
+## What This Skill Produces
+
+- A **24-hour ledger** for a typical weekday: where the hours actually go, with the
+  "muddled margin" (commute, scrolling, the vague hour after dinner) made visible
+- One **inner-day block**: a concrete 90-minute, 3-evenings-a-week commitment with
+  a named purpose the user chose
+- A **protection plan** for that block (what it displaces, what threatens it, the
+  rule for missing it)
+- **Bennett's caveats**, applied — the book's own anti-burnout warnings
+
+## Required Inputs
+
+Ask for (if not already provided):
+- A typical weekday, hour by hour as best they can tell it (waking to sleep)
+- What they wish they had time for — the real want, not the respectable one
+- Their honest energy map: when in the day they are actually alert
+- What they've tried before and how it died
+
+## Framework: Bennett's program (1908), applied
+
+1. **The income reframe** (Ch. 1) — before the ledger, the accounting truth: everyone
+   gets exactly 24 hours; the feeling of "no time" is an allocation problem wearing a
+   scarcity costume. No blame — Bennett's tone is companionable, keep it.
+2. **The ledger, honestly** (Ch. 3–4) — map the stated day, then probe the margins he
+   names: the commute or its modern equivalent, the gap between waking and working,
+   and the evening's "vague, dark, sterile" stretch that disappears without record.
+   Most people find 2–4 unowned hours; the point is not to seize them all.
+3. **Start absurdly small** (Ch. 4) — his prescription is exact: **ninety minutes,
+   three evenings a week**, and treat it as inviolable. "Beware of undertaking too
+   much at the start" — the failure mode he predicts is enthusiasm, not laziness.
+4. **Give the block a discipline, not a vibe** (Ch. 8–10) — the block needs one named
+   pursuit that requires effort (his examples: serious reading, studying an art,
+   learning the causes of things). "Reading" isn't a program; "working through one
+   book of X with notes, Tue/Thu/Sun" is.
+5. **His caveats, verbatim in spirit** (Ch. 11–12) — the chapter modern summaries
+   skip: the program must not make you insufferable or turn the week into a
+   prison-timetable ("the risk of becoming a prig"); leave the margin human; if an
+   evening dies, the program isn't broken — rigidity about the wreck is.
+
+## Output Format
+
+```
+## Your 24-hour ledger (typical weekday)
+| Block | Hours | Actually spent on | Owned or muddled? |
+Muddled margin found: ~X hours/day
+
+## The inner day
+[The 90-minute block × 3 evenings: which evenings, which hours, matched to the
+energy map · the named pursuit, made concrete]
+
+## Protecting it
+[What it displaces (named honestly) · the two most likely killers and the
+counter-move for each · the missed-evening rule: skip, never reschedule-spiral]
+
+## Bennett's warnings, applied to you
+[Which of his failure modes this user is closest to — overreach, priggishness,
+or treating the margin as a second job — and the guard]
+
+## Review date
+[Two weeks in: keep, shrink, or move the block — shrinking is success, not failure]
+```
+
+## Quality Checks
+
+- [ ] The ledger accounts for all 24 hours — sleep and the muddled margin included;
+      a ledger that only lists productive blocks missed the book's point
+- [ ] The block is ≤90 minutes and ≤3 evenings to start, whatever the user's
+      enthusiasm — cite Bennett's overreach warning when trimming their ambition
+- [ ] The pursuit is named and effortful, chosen by the user, not assigned
+- [ ] The protection plan names what the block *displaces* — reclaimed time comes
+      from somewhere, and pretending otherwise is how programs die
+- [ ] The tone stays companionable — an audit, not an audit*ing*
+
+## Anti-Patterns
+
+- [ ] Do not optimise the working day itself — Bennett's insight is that the job is
+      the day's landlord and the margins are where freedom lives; day-job problems
+      route to deep-work-blocking and standing-meeting-audit
+- [ ] Do not fill every found hour — the program is one block; the rest of the
+      margin stays slack on purpose
+- [ ] Do not moralise about the scrolling the ledger surfaces; record it and move on
+- [ ] Do not build a schedule so tight that one bad Tuesday collapses it — that is
+      the exact failure Chapter 11 predicts
+- [ ] Do not promise transformed lives — Bennett's honest pitch was a fuller life at
+      the margins, and that's this skill's pitch too

package/exports/aider/pm-dead-mentors/franklin-decision-ledger/franklin-decision-ledger.md

@@ -0,0 +1,97 @@
+# 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
+
+1. **Divide the paper** — one column *Pro*, one *Con*, for Option A over Option B.
+2. **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).
+3. **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.
+4. **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.
+5. **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."
+
+## 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.

package/exports/aider/pm-dead-mentors/machiavelli-counsel/machiavelli-counsel.md

@@ -0,0 +1,93 @@
+# Machiavelli Counsel Skill
+
+Five hundred years before "stakeholder management," Machiavelli wrote the unsentimental
+manual on power: how it is gained, kept, and lost. This skill applies The Prince's
+actual analytical questions to a modern workplace situation — then, because flattery
+of the reader's cynicism is its own trap, pairs every Machiavellian read with the
+honest modern move. You get the clear-eyed analysis without the 16th-century ethics.
+
+## What This Skill Produces
+
+- A **power map** of the situation: who decides, who influences the decider, whose
+  support is load-bearing, who loses if you win
+- A **Machiavellian assessment** — what The Prince's framework actually says about
+  your position (not generic "office politics tips")
+- A **counterweight plan**: the ethical version of each move, and where the
+  Machiavellian and honest paths genuinely diverge
+- A one-line **fortuna check**: what part of your position depends on luck holding
+
+## Required Inputs
+
+Ask for (if not already provided):
+- The situation, in the user's words (reorg, new boss, rival team, stalled project…)
+- Who the key people are and what each controls (budget, headcount, the CEO's ear)
+- What the user wants to happen, and by when
+- What the user has already tried
+
+## Framework: the questions The Prince actually asks
+
+Work through these five, in order — each is drawn from the book's recurring analysis:
+
+1. **New prince or established?** (Ch. III, VI–VII) — Is the user (or their rival, or
+   the new leader) newly arrived in the role? New power is fragile: it must build its
+   own support and cannot rely on inherited loyalty. A new exec's first 90 days follow
+   Ch. III dynamics almost embarrassingly well.
+2. **Whose arms?** (Ch. XII–XIII) — Does the user's position rest on their *own*
+   capability and relationships ("own arms"), or on a sponsor's protection
+   ("auxiliaries")? Borrowed power vanishes with the sponsor. Name what is borrowed.
+3. **Feared, loved, or despised?** (Ch. XVII, XIX) — Machiavelli's real claim is
+   narrower than the famous line: aim to be *respected* and above all avoid being
+   *despised or resented* — contempt, not strength, is what kills princes.
+   Translate: is the user seen as competent-and-fair, soft, or self-serving?
+4. **The friends of the old order** (Ch. VI) — Who benefits from things staying as
+   they are? Change makes enemies of everyone the current arrangement feeds, and only
+   lukewarm allies of its beneficiaries-to-be. List both columns for the user's plan.
+5. **Fortuna vs virtù** (Ch. XXV) — Roughly half of outcomes are outside anyone's
+   control; the skill of the operator is building levees before the river floods.
+   What is the user treating as stable that is actually luck?
+
+## Output Format
+
+```
+## The situation, read plainly
+[2-3 sentences, no euphemism]
+
+## Power map
+| Person / group | Controls | Wants | Load-bearing for you? |
+
+## The Machiavellian read
+[Each of the five questions above, answered for THIS situation, chapter noted]
+
+## Where Machiavelli is right — and where to ignore him
+[The 2-3 insights that hold up · the moves he'd endorse that you shouldn't make,
+and what to do instead. Be specific: "he'd say X; the durable version is Y."]
+
+## The next two weeks
+[3-5 concrete actions from the honest column]
+
+## Fortuna check
+[The one dependency that is luck, and its levee]
+```
+
+## Quality Checks
+
+- [ ] Every assessment traces to one of the five framework questions, chapter cited
+- [ ] The power map includes at least one person the user didn't mention (asked for,
+      not invented) — the missing stakeholder is usually the story
+- [ ] The counterweight section names a real divergence, not "be ethical" filler —
+      if the honest move and the Machiavellian move are the same, say so
+- [ ] No invented quotes: paraphrase the book; quote only what you can quote exactly
+- [ ] The advice would survive being read aloud to everyone named in it — that test
+      is itself the ethical line this skill holds
+
+## Anti-Patterns
+
+- [ ] Do not recommend manipulation, deception, or briefing against colleagues — the
+      skill analyses power honestly; it does not coach bad faith. When the user asks
+      for the dark version, give the analysis and decline the execution.
+- [ ] Do not serve generic office-politics advice ("build relationships!") wearing a
+      Machiavelli hat — every claim should need the book to make it
+- [ ] Do not repeat the famous misquotes as the book ("the ends justify the means"
+      appears nowhere in it)
+- [ ] Do not flatter the user's read of their own situation — Machiavelli's entire
+      value is that he didn't

package/exports/aider/pm-dead-mentors/stoic-setback-debrief/stoic-setback-debrief.md

@@ -0,0 +1,101 @@
+# Stoic Setback Debrief Skill
+
+Meditations was never a book — it was a working notebook of a man with an
+overwhelming job talking himself back to steadiness, entry by entry. That makes it
+the right tool for the bad professional day: not consolation, but a repeatable
+procedure. This skill runs the notebook's actual exercises on a specific setback,
+in order, and refuses to end without a next action. It is a debrief, not therapy —
+and it says so when therapy is what's actually needed.
+
+## What This Skill Produces
+
+- A **facts vs. story split**: what verifiably happened, separated from the
+  narrative currently running
+- A **control sort** of every element of the situation (yours / partly yours /
+  not yours), with effort reassigned accordingly
+- The **obstacle-turn**: what this setback now makes possible or necessary — the
+  Stoic move of converting the blocker into the task itself
+- **One next action** sized for today, and a line for [[decision-journal]] if a
+  real decision was surfaced
+
+## Required Inputs
+
+Ask for (if not already provided):
+- What happened, as the user tells it (take the vent — it's data)
+- What they're most worried it means (reputation, the project, the job)
+- Anything irreversible already done (sent the reply? resigned? nothing yet?)
+- Whether anything needs handling *tonight*, or whether this can use a day
+
+## Framework: the notebook's exercises, applied
+
+1. **Strip the event to what happened** (Book IV; VIII.49) — Aurelius' discipline of
+   "objective judgment": describe the event as a camera would, no adjectives, no
+   mind-reading. "The launch converted 0.4% against a 2% target and the VP asked for
+   a plan by Friday" — not "the launch humiliated us." Write both versions; the gap
+   between them is the story, and the story is optional.
+2. **Sort by control** (the Stoic dichotomy, throughout; Epictetus made it explicit) —
+   three columns for every element the user named: *yours* (your next reply, your
+   plan, your craft), *partly yours* (the team's morale, the VP's read — influence,
+   not control), *not yours* (the market, the past, other people's verdicts). The
+   rule: effort moves to column one; column three gets acknowledgment, not budget.
+3. **The obstacle becomes the task** (V.20) — Aurelius' working principle that what
+   blocks the path *becomes* the path: the mind adapts and converts the impediment
+   to its own purpose. Not silver-lining ("at least you learned!") — literally: what
+   is the new task this setback has set? A failed launch sets the diagnosis task; a
+   brutal review sets the evidence-gathering task; a layoff sets the search task.
+4. **The evening review** (Book I is the model — he opens by listing what he learned
+   from each person) — three questions, answered in writing: What did I handle well,
+   even today? Where did I act against my own standard? What does tomorrow's version
+   of me do differently at the same fork?
+5. **Zoom out, briefly** (IV.3; VII.47 — the view from above) — one honest sentence
+   on how this ranks at quarter-scale and at career-scale. Not to minimise; to size.
+
+## Output Format
+
+```
+## What happened (camera version)
+[2-3 sentences, verifiable facts only]
+
+## The story running alongside it
+[The narrative, named as narrative]
+
+## Control sort
+| Yours | Partly yours | Not yours |
+→ Effort reassignment: [where tonight's/tomorrow's energy actually goes]
+
+## The obstacle, turned
+[The specific new task this setback set — one paragraph]
+
+## Evening review
+[The three questions, answered]
+
+## One next action
+[Small, concrete, today-or-tomorrow · if a real decision surfaced, the
+decision-journal line to log]
+```
+
+## Quality Checks
+
+- [ ] The camera version contains zero judgments — read it back looking for hidden
+      adjectives ("disaster", "furious") and strip them
+- [ ] Every worry the user named appears in exactly one control column
+- [ ] The obstacle-turn names a task, not a lesson — "diagnose the funnel by
+      Thursday" not "resilience is important"
+- [ ] The next action is doable within 24 hours by the user alone
+- [ ] References are to real passages (book/section noted); paraphrase rather than
+      risk a misquote — Meditations is the most misquoted book on the internet
+
+## Anti-Patterns
+
+- [ ] Do not console first and sort second — run the procedure; steadiness comes
+      from the sorting, not the sympathy
+- [ ] Do not use the control sort to excuse what was the user's (column one gets
+      *more* scrutiny, not less — that's the honest half of Stoicism)
+- [ ] Do not produce "at least" sentences — the obstacle-turn is a task assignment,
+      never a bright side
+- [ ] Do not treat ongoing distress, burnout, or harassment as a debrief-sized
+      problem — say plainly that this needs a human (manager, HR, doctor, someone
+      trusted) and stop there
+- [ ] Do not let the user hit send on anything written while the story version was
+      driving — the reply drafted tonight gets reread through the camera version
+      tomorrow

package/exports/aider/pm-dead-mentors/sun-tzu-strategy-brief/sun-tzu-strategy-brief.md

@@ -0,0 +1,95 @@
+# Sun Tzu Strategy Brief Skill
+
+The Art of War's core insight is not aggression — it is that the outcome is mostly
+decided **before** the engagement, in the counting-house: the winning general "makes
+many calculations in his temple ere the battle is fought" (Ch. I, Giles translation).
+This skill runs those calculations for a modern contest and — the part most strategy
+decks skip — is willing to conclude *don't fight this one*.
+
+## What This Skill Produces
+
+- A **five-factor assessment** of you vs. the opponent for this specific contest
+- The **terrain read**: what kind of ground this fight is on, and who it favours
+- A **win-without-fighting scan**: the outcomes that get what you want with no
+  head-to-head at all
+- A **fight / reshape / decline verdict** with the reasoning shown
+
+## Required Inputs
+
+Ask for (if not already provided):
+- The contest: who, over what, decided by whom, by when
+- What winning actually gets you (revenue, the logo, the territory, precedent)
+- Your honest strengths and constraints; the opponent's, as far as known
+- What happens if you simply don't engage
+
+## Framework: the calculations (Art of War, Ch. I–IV)
+
+**1. The five factors** (Ch. I) — score both sides honestly on each:
+
+| Factor | Sun Tzu's term | Modern translation |
+|---|---|---|
+| Moral influence | Tao | Does each side's team actually believe in this fight? Alignment beats headcount. |
+| Heaven | Timing | Conditions outside anyone's control — budget cycles, market mood, regulation |
+| Earth | Terrain | Whose home ground is the deal/segment/standard being fought on? |
+| Command | The general | Who runs each side's effort — empowered operator or committee? |
+| Method | Discipline | Process and logistics: pricing authority, support capacity, follow-through |
+
+**2. Know the other and know yourself** (Ch. III) — mark each cell of the table as
+*known*, *assumed*, or *unknown*. The famous line is a probability statement: know
+both sides and the result holds no fear; know only yourself and you trade wins and
+losses; know neither and you lose. Count your unknowns before trusting your verdict.
+
+**3. Win without fighting** (Ch. III) — "supreme excellence consists in breaking the
+enemy's resistance without fighting" (Giles). Before planning the head-to-head, list
+at least three no-battle outcomes: reframe the buying criteria, partner instead of
+compete, concede this deal to own the next segment, change what is being compared.
+
+**4. Invincibility first** (Ch. IV) — secure what cannot be lost before reaching for
+what can be won: which existing customers, allies, or territory must be defended
+*while* you fight this? An offense that exposes the base is how challengers die.
+
+## Output Format
+
+```
+## The contest
+[One paragraph: who, over what, decided by whom, when]
+
+## Five factors
+| Factor | Us | Them | Edge | Known/assumed? |
+
+## Unknowns that could flip the verdict
+[The assumed/unknown cells, and the cheapest way to convert each to known]
+
+## Three ways to win without fighting
+1. … 2. … 3. …
+
+## Verdict: FIGHT / RESHAPE / DECLINE
+[Fight: the two factors that decide it and how to press them.
+ Reshape: which factor you change before engaging, and how.
+ Decline: what you protect instead, and what declining costs.]
+
+## Defend while attacking
+[What must not be lost during this, and its guard]
+```
+
+## Quality Checks
+
+- [ ] Both columns scored — a brief that only assesses the opponent is scouting,
+      not strategy
+- [ ] Every factor cell marked known/assumed/unknown, and the unknown count stated
+      plainly next to the verdict
+- [ ] At least three genuine no-battle options, not one padded to three
+- [ ] The verdict is one of the three words, committed to — "it depends" is the
+      exact failure this skill exists to prevent
+- [ ] Quotes only where exact (Giles translation); otherwise paraphrase with a
+      chapter reference
+
+## Anti-Patterns
+
+- [ ] Do not produce war-metaphor decoration on top of an ordinary SWOT — every
+      section should do analytical work the five factors made possible
+- [ ] Do not let the user's fighting spirit set the verdict; the book's most-repeated
+      advice is to not fight battles you haven't already won on paper
+- [ ] Do not treat colleagues as the "enemy" — this skill is for external contests;
+      internal politics belongs to machiavelli-counsel, and the difference matters
+- [ ] Do not skip the defend-while-attacking section because the user is excited