pm-claude-skills 63.0.0 → 64.0.0

package/README.md

@@ -1,8 +1,8 @@
-# 🧠 PM Skills — 776 Professional Agent Skills for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes
+# 🧠 PM Skills — 782 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 — 776 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 — 782 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 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.
+PM Skills is an open-source library of 782 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 776 asks live in **[the catalog](SKILLS.md)**.
+…all 782 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 776 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 782 pass the [SkillSpec](SKILLSPEC.md) L3 gate and a security audit in CI.
 
 <table align="center">
   <tr align="center">
@@ -122,6 +122,7 @@ Every skill follows the same discipline: what it produces, the inputs it needs,
 | 🏠 **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) |
+| 🎲 **Tabletop** (5) 🆕 | Game night, upgraded — teach, judge, plan, design, and practice the trades | [teach-the-game](skills/teach-the-game/SKILL.md) · [rules-lawyer](skills/rules-lawyer/SKILL.md) · [game-night-planner](skills/game-night-planner/SKILL.md) · [board-game-designer](skills/board-game-designer/SKILL.md) · [tabletop-negotiator](skills/tabletop-negotiator/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) |
@@ -135,7 +136,7 @@ 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/) (95 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/) (96 bundles). Install any bundle: `/plugin install pm-decoders@pm-skills`.
 
 ### Meta
 
@@ -239,13 +240,13 @@ The whole library on one poster — start path, standout features, and install o
 
 ## 🆕 Latest
 
-**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)
+**v64.0.0 — game night:** [pm-tabletop](plugins/pm-tabletop) — teach any board game in 5 minutes, settle rules arguments fairly, plan the lineup, design your own game, and [spar the Catan trade](skills/tabletop-negotiator/SKILL.md) against a hidden agenda with a scored debrief; 782 skills, 96 bundles. *v63.1 — pixel confetti:* [pixel-gif-maker](skills/pixel-gif-maker/SKILL.md) — custom retro Slack GIFs (scroll, pulse, party, sparkle) from a pure-stdlib deterministic encoder; 782 skills. *And 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 776 skills, forever. The skills are markdown; there is nothing to gate. Sponsors fund the playground's free model runs, not access.
+Yes — MIT, all 782 skills, forever. The skills are markdown; there is nothing to gate. Sponsors fund the playground's free model runs, not access.
 </details>
 
 <details>
@@ -288,4 +289,4 @@ MIT — use them, fork them, ship them at work. Skills are judgment, and judgmen
 
 ---
 
-*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)**.*
+*Built by [Mohit](https://github.com/mohitagw15856) with Claude. 782 skills · 96 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 **776 skills** to:
+Currently exporting **782 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.
 
-776 skills exported. Copy a `.md rule` into the tool to use it.
+782 skills exported. Copy a `.md rule` into the tool to use it.
 
 | Skill | Bundle | Path |
 |---|---|---|
@@ -61,6 +61,7 @@
 | 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` |
+| Board Game Designer | `pm-tabletop` | `pm-tabletop/board-game-designer/board-game-designer.md` |
 | Board Minutes | `pm-business` | `pm-business/board-minutes/board-minutes.md` |
 | Board Pre-Read | `pm-business` | `pm-business/board-pre-read/board-pre-read.md` |
 | BOM Cost Review | `pm-hardware` | `pm-hardware/bom-cost-review/bom-cost-review.md` |
@@ -321,6 +322,7 @@
 | 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` |
+| Game Night Planner | `pm-tabletop` | `pm-tabletop/game-night-planner/game-night-planner.md` |
 | Gantt / Roadmap | `pm-visuals` | `pm-visuals/gantt-roadmap/gantt-roadmap.md` |
 | GDPR Compliance | `pm-compliance` | `pm-compliance/gdpr-compliance/gdpr-compliance.md` |
 | Git Troubleshooter | `pm-engineering` | `pm-engineering/git-troubleshooter/git-troubleshooter.md` |
@@ -493,6 +495,7 @@
 | PIP Responder | `pm-career` | `pm-career/pip-responder/pip-responder.md` |
 | Pitch Vs Teach | `pm-cowork` | `pm-cowork/pitch-vs-teach/pitch-vs-teach.md` |
 | Pivot Analysis Planner | `pm-cowork` | `pm-cowork/pivot-analysis-planner/pivot-analysis-planner.md` |
+| Pixel GIF Maker | `other` | `other/pixel-gif-maker/pixel-gif-maker.md` |
 | Plain Language Rewrite | `pm-cowork` | `pm-cowork/plain-language-rewrite/plain-language-rewrite.md` |
 | PM Weekly Review | `pm-rituals` | `pm-rituals/pm-weekly-review/pm-weekly-review.md` |
 | Policy Drafter | `pm-cowork` | `pm-cowork/policy-drafter/policy-drafter.md` |
@@ -599,6 +602,7 @@
 | Rollback Plan | `pm-engineering` | `pm-engineering/rollback-plan/rollback-plan.md` |
 | RSS Digest | `pm-live` | `pm-live/rss-digest/rss-digest.md` |
 | Rubric Builder | `pm-education` | `pm-education/rubric-builder/rubric-builder.md` |
+| Rules Lawyer | `pm-tabletop` | `pm-tabletop/rules-lawyer/rules-lawyer.md` |
 | Runbook Writer | `pm-engineering` | `pm-engineering/runbook-writer/runbook-writer.md` |
 | Runway Calculator | `pm-calculators` | `pm-calculators/runway-calculator/runway-calculator.md` |
 | Runway Monte Carlo | `pm-calculators` | `pm-calculators/runway-monte-carlo/runway-monte-carlo.md` |
@@ -698,9 +702,11 @@
 | Sycophancy Challenger | `pm-cross` | `pm-cross/sycophancy-challenger/sycophancy-challenger.md` |
 | Synthetic User Research | `pm-research` | `pm-research/synthetic-user-research/synthetic-user-research.md` |
 | System Design Interview | `pm-engineering` | `pm-engineering/system-design-interview/system-design-interview.md` |
+| Tabletop Negotiator | `pm-tabletop` | `pm-tabletop/tabletop-negotiator/tabletop-negotiator.md` |
 | Task Triage Matrix | `pm-cowork` | `pm-cowork/task-triage-matrix/task-triage-matrix.md` |
 | Tax Planning Checklist | `pm-finance` | `pm-finance/tax-planning-checklist/tax-planning-checklist.md` |
 | TDD Workflow | `pm-craft` | `pm-craft/tdd-workflow/tdd-workflow.md` |
+| Teach The Game | `pm-tabletop` | `pm-tabletop/teach-the-game/teach-the-game.md` |
 | Teaching Lesson Plan | `pm-cross` | `pm-cross/teaching-lesson-plan/teaching-lesson-plan.md` |
 | Team Budget Tracker | `pm-cowork` | `pm-cowork/team-budget-tracker/team-budget-tracker.md` |
 | Team Health Check | `pm-people` | `pm-people/team-health-check/team-health-check.md` |

package/exports/aider/other/pixel-gif-maker/pixel-gif-maker.md

@@ -0,0 +1,68 @@
+# Pixel GIF Maker Skill
+
+The most-reacted message in any Slack channel is never the status update — it's the
+GIF. This skill makes custom ones in a retro pixel style: your words, four
+animations, eight colors, and a file small enough to drag anywhere. The whole
+encoder is a bundled pure-stdlib Python script — this library's calculators are
+dependency-free and deterministic, and so is its confetti.
+
+## What This Skill Produces
+
+- A `.gif` file (GIF89a, looping) with the user's text in chunky 5×7 pixel type
+- One of four animations: **scroll** (marquee), **pulse** (heartbeat zoom),
+  **party** (hue-cycling text + confetti), **sparkle** (twinkling stars)
+- Sized for chat: typically 10–60KB, well under any upload limit
+
+## Required Inputs
+
+Ask for (if not already provided):
+- The text — **under 24 characters**; pixel fonts are for punchlines
+  ("SHIP IT", "1000 STARS", "GG TEAM", "V63 IS LIVE"). Type `*` for a ♥.
+- The mood → mode: victory lap = `party` · announcement = `scroll` ·
+  emphasis = `pulse` · appreciation = `sparkle`
+- Optional: colors (`night, plum, teal, mint, gold, coral, white, ink, violet`)
+  and `--scale 1-4` (default 3)
+
+## Process
+
+1. Run the bundled script — no installs, Python 3 stdlib only:
+   ```bash
+   python3 scripts/pixel_gif.py --text "SHIP IT" --mode party --out shipit.gif
+   python3 scripts/pixel_gif.py --text "GG TEAM *" --mode sparkle --fg gold --bg night --out gg.gif
+   python3 scripts/pixel_gif.py --self-test    # verify all four modes, print hashes
+   ```
+2. Uppercase renders best (the font is A–Z, 0–9, and common punctuation; unknown
+   characters become `?` — warn the user rather than surprise them).
+3. Same arguments + same `--seed` → byte-identical file; change `--seed` to
+   reshuffle confetti/star positions.
+4. Hand back the file path and one line on which mode was chosen and why.
+
+## Output Format
+
+The `.gif` itself, plus:
+
+```
+🎉 shipit.gif — 159×57, 10 frames, party mode (confetti for a launch).
+Drag it into Slack. Want it calmer (sparkle) or bigger (--scale 4)?
+```
+
+## Quality Checks
+
+- [ ] Text length checked BEFORE generating — over 24 characters, ask them to cut
+      (offer the punchline edit: "SHIPPED THE MIGRATION" → "SHIPPED IT")
+- [ ] Mode matches the moment — a layoff-week channel does not get confetti;
+      when in doubt, sparkle
+- [ ] Script ran without error and the reported file size is under ~200KB
+- [ ] Any character outside the font set was flagged to the user, not silently
+      turned into `?`
+
+## Anti-Patterns
+
+- [ ] Do not reach for image libraries or external services — the point of the
+      bundled encoder is zero dependencies and deterministic output
+- [ ] Do not generate GIFs containing colleagues' names in mocking contexts —
+      celebration tool, not a roast tool; decline and suggest the kind version
+- [ ] Do not cram sentences in — if the user insists past 24 characters, use
+      scroll mode and say why
+- [ ] Do not promise Slack emoji-size rendering — this makes message GIFs;
+      custom emoji have their own size rules the user handles in Slack settings

package/exports/aider/pm-tabletop/board-game-designer/board-game-designer.md

@@ -0,0 +1,94 @@
+# Board Game Designer Skill
+
+Everyone has a board game idea; almost nobody has a *prototype*, because the gap
+between theme ("it's about deep-sea heists!") and game (what do I DO on my
+turn?) is where ideas stall. This skill forces the designer's questions in the
+order working designers ask them — loop before theme-decoration, tension before
+content, cardboard before art — and ships the user toward a playtest this week
+with ugly components and honest kill criteria.
+
+## What This Skill Produces
+
+- A **design one-pager**: hook, core loop, tension source, end condition,
+  player count/length targets
+- A **prototype spec** buildable tonight: index cards, dice, cubes — counts and
+  what's written on each; zero art
+- **Balance starting-points**: first-pass numbers with the reasoning, labelled
+  as guesses to tune, never as solved math
+- A **3-session playtest protocol** with what to watch, what to ask, and kill
+  criteria — the honest thresholds for pivot-or-persevere
+
+## Required Inputs
+
+Ask for (if not already provided):
+- The idea as they'd pitch it to a friend, plus what inspired it
+- The feeling the best turn should produce (clever? tense? gleeful betrayal?)
+- Target: players, minutes, audience (family? hobbyists? their own group?)
+- If mid-design: what's working, and where it drags
+
+## Process
+
+1. **Find the loop.** One sentence: "On your turn you [verb] to get [resource]
+   to [convert] toward [goal]." No loop sentence, no game yet — iterate here
+   before anything else.
+2. **Name the tension.** Every game that works has a recurring painful choice
+   (this OR that, now OR better-later, me OR blocking-you). Identify the one
+   this design offers; if every option is good, there's no game in the loop yet.
+3. **Steal structure honestly.** Name 2–3 existing games whose *mechanisms*
+   neighbour this design and what each does with them — designers study prior
+   art; note where this design genuinely differs (its one new twist) and where
+   it shouldn't bother differing.
+4. **Spec the ugliest playable version.** Index cards and cubes, tonight. Every
+   component count written down. The rule: nothing gets art until it survives
+   five plays.
+5. **First-pass the numbers.** Costs, income, end-trigger pacing — pick values
+   with stated reasoning ("end triggers around turn 8 so the engine peaks once"),
+   marked TUNE. Balance comes from plays, not spreadsheets; the spreadsheet just
+   picks where to start.
+6. **Protocol the playtests.** Session 1 (solo, all seats): does the loop
+   function? Session 2 (friendly table): where does attention die? Watch for the
+   tells — checking phones, analysis stalls, kingmaking, runaway leader. Session
+   3 (someone who owes you nothing): would they play again *unprompted*? Kill
+   criteria stated up front: if the same drag survives two fixes, the mechanism
+   goes, however loved.
+
+## Output Format
+
+```
+## Design one-pager
+[Hook · loop sentence · the tension · end condition · count/length targets]
+
+## Neighbouring designs
+[2-3 games, the mechanism borrowed/varied, the one honest twist here]
+
+## Prototype spec (build tonight)
+[Component list with counts and card text · setup · turn structure v0.1]
+
+## Numbers v0.1 (all marked TUNE)
+[Table of starting values + one line of reasoning each]
+
+## Playtest protocol
+[3 sessions: goal, what to watch, questions to ask AFTER not during]
+Kill criteria: [the honest thresholds]
+```
+
+## Quality Checks
+
+- [ ] The loop fits in one sentence and contains a decision, not just an action
+- [ ] The tension is a *recurring* choice, named concretely
+- [ ] Prototype is buildable from household stationery in an evening — if it
+      needs printing services, it's overdesigned for v0.1
+- [ ] Every number carries reasoning and a TUNE flag — no false precision
+- [ ] Kill criteria exist and are specific enough to actually trigger
+
+## Anti-Patterns
+
+- [ ] Do not start with theme, art, or a Kickstarter plan — loop, tension,
+      cardboard, in that order
+- [ ] Do not claim the idea is original without the prior-art pass, and do not
+      copy a game wholesale with the theme swapped — name the twist
+- [ ] Do not present first-pass numbers as balanced — playtesting owns balance
+- [ ] Do not let the designer explain rules during playtests — confusion IS the
+      data
+- [ ] Do not promise market outcomes ("this would sell!") — the promise is a
+      playtest by Friday

package/exports/aider/pm-tabletop/game-night-planner/game-night-planner.md

@@ -0,0 +1,89 @@
+# Game Night Planner Skill
+
+Game nights don't fail because the games are bad — they fail because someone
+brought a 3-hour economic engine to a table that wanted snacks and laughing, or
+because choosing took 40 minutes, or because seven people showed up for a
+4-player game. This skill plans like a good host thinks: who is actually coming,
+what's their tolerance, sequence light-to-heavy, and always know what happens
+when the count changes at 7pm.
+
+## What This Skill Produces
+
+- A **sequenced lineup** (opener → main event → optional nightcap) with
+  per-game: player count fit, realistic time *including the teach*, and why it
+  suits this table
+- **Plan B branches**: someone bails / someone brings a friend / running late
+- A **from-their-shelf first** selection when the user lists what they own, with
+  1–3 to-buy/borrow suggestions only if the shelf can't cover the night
+- The **house logistics**: teach order, who teaches (pair with teach-the-game),
+  when to call the last game
+
+## Required Inputs
+
+Ask for (if not already provided):
+- Headcount (and how firm it is), plus ages and the experience mix
+- The vibe wanted: competitive, cooperative, social/party, "just talking with
+  something to do"
+- Hard limits: total hours, any player's complexity ceiling, themes to avoid
+- What they own or can borrow — plan from the shelf before the shop
+
+## Process
+
+1. **Plan for the people, not the games.** The least-enthusiastic guest sets the
+   weight ceiling for the main event; the most-enthusiastic one gets the
+   nightcap. Say who each pick serves.
+2. **Sequence by energy.** Opener: ≤20 minutes, teachable in one, works while
+   people arrive. Main event: the night's centrepiece, started while energy is
+   high — never after 9pm for a heavy game. Nightcap: low-rules, high-laughs,
+   quittable anytime.
+3. **Budget honest time.** A "45-minute" game with a teach and a first play is
+   90; say the real number per slot and total. If the lineup exceeds the stated
+   window, cut a game, don't compress the estimates.
+4. **Branch the plan.** Player counts are fiction until the doorbell stops: for
+   each lineup slot, name the swap when N±1 shows up (many great games break at
+   exactly one count — flag those).
+5. **Recommend honestly.** Suggest well-known games by name where they genuinely
+   fit, note "check availability/price" rather than asserting either, and if
+   the user's shelf covers the night, say so — the best recommendation is often
+   already owned.
+
+## Output Format
+
+```
+## The night at a glance
+[Who's coming, the vibe, total window · one-line theme of the plan]
+
+## Lineup
+1. OPENER — [game] ([count] players, ~[real minutes] incl. teach)
+   Why for this table: … · Who it serves: …
+2. MAIN EVENT — [game] …
+3. NIGHTCAP (optional) — [game] …
+Total honest time: [X]h[Y]m of your [window]
+
+## When reality edits the guest list
+- One fewer: … · One extra: … · Running an hour late: cut […], start at […]
+
+## Logistics
+[Who teaches what · setup while people arrive · the "last game" call time]
+```
+
+## Quality Checks
+
+- [ ] Every pick names who at the table it serves — a lineup with no named
+      beneficiary is a list, not a plan
+- [ ] Times include teach + setup, and the total fits the stated window without
+      wishful compression
+- [ ] Player-count edge cases flagged (games that break at exactly this N±1)
+- [ ] Shelf games considered before purchases; buys capped at three and marked
+      "check availability"
+- [ ] The weight ceiling respects the least-enthusiastic guest, not the host
+
+## Anti-Patterns
+
+- [ ] Do not build the host's dream lineup — the guest who came reluctantly
+      decides whether there's a next game night
+- [ ] Do not schedule a heavy teach late in the evening
+- [ ] Do not recommend obscure games as if universally available, and never
+      state prices as fact
+- [ ] Do not plan zero slack — the gap between games is where game night
+      actually happens

package/exports/aider/pm-tabletop/rules-lawyer/rules-lawyer.md

@@ -0,0 +1,89 @@
+# Rules Lawyer Skill
+
+Every game group has The Argument: two players, two readings of one sentence, and
+a fun evening curdling while someone scrolls a forum from 2011. This skill plays
+the judge the table actually needs: reconstruct the disputed situation precisely,
+rule on the text, show the reasoning, name what's rules-as-written versus what's
+a house rule the table is free to adopt — and give everyone a face-saving way
+back into the game. The ruling matters less than the game night surviving it.
+
+## What This Skill Produces
+
+- A **table ruling**: the answer, with the rule text or principle it rests on
+- A **RAW vs house rule** split: what the rules actually say vs what this table
+  may prefer — both legitimate, never confused
+- A **confidence label**: ruled from text (paste provided) · ruled from general
+  knowledge of the game (verify if it's for money/tournament) · genuinely
+  ambiguous (here's the fairest tiebreak)
+- A **keep-the-peace line** to read aloud, and a suggestion for logging it as a
+  standing house rule so the argument never repeats
+
+## Required Inputs
+
+Ask for (if not already provided):
+- The game (edition matters — rules change between printings)
+- The exact situation: who did what, in what order, and what's contested
+- The rulebook passage in dispute, pasted, if anyone has it to hand — text beats
+  memory, including this skill's
+- What each side claims (steelman both)
+
+## Process
+
+1. **Reconstruct before ruling.** Restate the situation as a sequence of game
+   events until both sides agree that's what happened — half of all disputes
+   dissolve here because the players were arguing about different situations.
+2. **Rule on the text.** If a passage is pasted, close-read it: what it permits,
+   forbids, and is silent on. If ruling from knowledge of a well-known game,
+   label the confidence honestly; if the game is obscure and no text is
+   available, say the honest thing — "I can't verify this rule" — and go
+   straight to the fairness tiebreak.
+3. **Silence is a decision.** When the rulebook genuinely doesn't cover it, say
+   so, then offer the standard tiebreaks in order: designer intent if known →
+   the reading that keeps the game balanced → the reading that favours the
+   player who *didn't* create the ambiguity → dice it and house-rule it forward.
+4. **Separate law from custom.** Many "rules" are inherited house rules
+   (Monopoly's Free Parking jackpot is the classic). Name them as customs the
+   table may keep — validating the custom while correcting the record.
+5. **End the argument, not just the question.** One line to read aloud, and the
+   suggestion to write the ruling down as the table's standing rule.
+
+## Output Format
+
+```
+## What actually happened
+[The agreed sequence of events]
+
+## The ruling
+[Answer + the text/principle it rests on] — Confidence: [from text / from
+knowledge — verify for stakes / ambiguous]
+
+## Rules-as-written vs your table
+[What the rules say · what would also be a perfectly good house rule]
+
+## Read this aloud
+"[One sentence that settles it and restarts the game]"
+
+## So it never comes back
+[The one-line house rule to write inside the box lid]
+```
+
+## Quality Checks
+
+- [ ] Both sides' readings were steelmanned before the ruling
+- [ ] Confidence is labelled on every ruling — text, knowledge, or ambiguous
+- [ ] No rule was invented: unverifiable claims are marked unverifiable, and the
+      fairness tiebreak carries the ruling instead
+- [ ] The ruling explains *why*, in two sentences a 10-year-old at the table
+      could follow
+- [ ] The output ends with the game restarting, not with the loser relitigating
+
+## Anti-Patterns
+
+- [ ] Do not bluff rules for games you can't verify — a wrong confident ruling
+      is the one unforgivable move for a rules lawyer
+- [ ] Do not declare a winner of the *argument* — rule on the situation, give
+      both sides a way back in
+- [ ] Do not dismiss house rules as "playing wrong"; name them, honour them,
+      distinguish them
+- [ ] Do not import tournament strictness into a family kitchen — stakes set
+      the standard, and the skill should ask about stakes if unclear

package/exports/aider/pm-tabletop/tabletop-negotiator/tabletop-negotiator.md

@@ -0,0 +1,91 @@
+# Tabletop Negotiator Skill
+
+In negotiation games, the board is only half the game — the other half is
+table-talk, and nobody practices it. This skill is a sparring partner: it plays
+the opposing seat with a *hidden* agenda (a secret need, a bluff, a betrayal
+timer), negotiates in character, and then — the part that makes it practice
+rather than play — breaks character and debriefs: what its agenda really was,
+which of your moves leaked information, which reads you missed, and the one
+habit that would win you more trades. Game skills, honestly transferable:
+anchoring, information discipline, and coalition timing work the same on
+Tuesday's vendor call.
+
+## What This Skill Produces
+
+- A **played negotiation** (5–10 exchanges) in a scenario matching the named
+  game's deal-structure: resource trade, alliance pact, package deal
+- A **hidden agenda**, committed before play begins and revealed only in the
+  debrief
+- An **out-of-character debrief**: the agenda revealed, your leaks and misses,
+  what was actually achievable, scored /10 against it
+- **One habit to change**, phrased as a rule for the next real game
+
+## Required Inputs
+
+Ask for (if not already provided):
+- The game (or "generic trading game") and the situation: what the user holds,
+  what they need, roughly what's visible about the opponent
+- Stakes and mood: friendly kitchen table or cutthroat club?
+- What tends to go wrong for them ("I accept first offers", "everyone sees my
+  bluffs", "I get frozen out of alliances")
+
+## Process
+
+1. **Set the seat.** Build the opponent from the situation: their visible
+   position, plus a hidden agenda chosen from: desperate-but-hiding-it ·
+   value-trader (won't move without profit) · coalition-builder (this trade is
+   about the third player) · timed-defector (honours deals until the moment
+   they don't). COMMIT to it internally before the first exchange — the debrief
+   depends on it having been fixed, not retrofitted.
+2. **Play it straight.** Negotiate in character, at the table's declared mood.
+   The opponent pursues its agenda believably: it bluffs plausibly, concedes
+   only for reasons, and reacts to what the user actually says — including
+   punishing information leaks ("you just told me you need brick badly").
+3. **Let them lose if they lose.** No mercy-balancing mid-game; bad trades
+   stand. The debrief is where kindness lives.
+4. **Break character cleanly.** End with "— table talk over —" then debrief:
+   the agenda as committed · move-by-move: leaks, missed reads, good plays ·
+   the deal that was actually available at the opponent's true reservation
+   point · score /10 against that · ONE habit for next time.
+5. **Bridge, lightly.** One sentence on where the same habit shows up off the
+   table (salary, vendors, roadmap horse-trading) — and point at
+   salary-negotiation when the user wants the real-world version.
+
+## Output Format
+
+```
+[The negotiation, in character, exchange by exchange]
+
+— table talk over —
+
+## Debrief
+My hidden agenda was: [as committed at the start]
+What you leaked: … · What you missed: … · What you played well: …
+The deal actually available: [opponent's true walk-away point]
+Score: X/10 · One habit to change: [rule for the next game]
+Same habit off the table: [one sentence]
+```
+
+## Quality Checks
+
+- [ ] The agenda was committed before exchange one and the revealed agenda
+      matches the opponent's actual behaviour throughout
+- [ ] The opponent conceded only for in-character reasons — no drift toward
+      letting the user win
+- [ ] The debrief cites specific lines the user said, not generalities
+- [ ] Exactly one habit prescribed — a list of five fixes fixes nothing
+- [ ] Game-rule specifics for named games stay light and non-authoritative —
+      this practices the talking, not the rules (rules-lawyer owns rules)
+
+## Anti-Patterns
+
+- [ ] Do not go easy — flattering practice is worse than none; the debrief is
+      where support lives
+- [ ] Do not reveal or hint at the hidden agenda mid-game, even when asked
+- [ ] Do not coach mid-negotiation; interruptions destroy the read-the-table
+      practice (unless the user calls "pause")
+- [ ] Do not teach real-deception skills for real-world harm — the bluffing
+      stays inside game frames; off-table bridges are about discipline and
+      reads, not deceit
+- [ ] Do not moralise about betrayal mechanics — in Diplomacy, the knife is
+      the game; debrief the timing, not the ethics