pm-claude-skills 46.0.0 → 48.0.0

package/README.md

@@ -13,6 +13,8 @@
 [![Free runs served](https://img.shields.io/endpoint?url=https%3A%2F%2Fpm-skills-mcp.pm-claude-skills.workers.dev%2Ftry%2Fstats&cacheSeconds=300)](https://mohitagw15856.github.io/pm-claude-skills/)
 [![Sponsor](https://img.shields.io/badge/💛_sponsors_fund_the_free_runs-ea4aaa)](https://github.com/sponsors/mohitagw15856)
 
+> 🏛 **This project grew into [The Open Institute for Professional Judgment](https://mohitagw15856.github.io/pm-claude-skills/institute.html)** — the SkillSpec standard, the Operator's Exam, the SkillBench rankings, the ecosystem census, the global Season, and the [State of Professional AI](docs/reports/state-of-professional-ai-2026.md). Every instrument open, free, and verifiable. Also: run it inside your company with the [Org Edition](org/) (`docker compose up`).
+
 > **Big repo?** It's a monorepo on purpose — but you probably need one folder. **[REPO-MAP.md](REPO-MAP.md)** tells you which, and the skills-only clone is 10 seconds: `git clone --filter=blob:none --sparse <url> && git sparse-checkout set skills`
 
 > 💛 **The free runs are sponsor-funded.** Every sponsor dollar visibly raises the daily cap on the counter above — and sponsors get [naming rights, not influence](docs/SPONSORSHIP.md): your name in this README, your logo on the playground, or **a Boardroom bench carrying your company's name**. → [Become a sponsor](https://github.com/sponsors/mohitagw15856)
@@ -84,7 +86,7 @@
 
 A community-built library of professional skills for every field — product management, engineering, customer success, marketing, social media, writers, design, legal, finance, HR, sales, operations, research, and more. Each skill is a structured `SKILL.md` file that teaches an AI assistant how to produce professional-grade outputs for your workflows. Skills run natively in **Claude Code** and **Hermes Agent** (same open `SKILL.md` standard), and ship as ready-to-paste exports for **ChatGPT** and **Gemini** — see [Works With](#-works-with--cross-tool-compatibility).
 
-**🆕 v45.0.0 — the spectacle release:** ⚔️ **Duels** — challenge a friend to the *identical* Gym negotiation or Panel candidate (same hidden state, side-by-side scorecard), 🎓 **[The Charter](https://mohitagw15856.github.io/pm-claude-skills/charter.html)** — the performance-based, cryptographically verifiable certification, and **the library in 3D**: 🌌 [Galaxy 3D](https://mohitagw15856.github.io/pm-claude-skills/galaxy3d.html) (fly a bloom-lit starfield where your used skills burn brighter), 🏗 **[the Tower of Claims](https://mohitagw15856.github.io/pm-claude-skills/tower.html)** (your document as a physics tower — data is steel, assumptions are glass, watch it stand or **collapse**), 🏛 [the Stage](https://mohitagw15856.github.io/pm-claude-skills/stage.html) (Boardroom replays as cinema with a cracking hologram), ✨ holo persona cards, 🏆 [the Trophy Forge](https://mohitagw15856.github.io/pm-claude-skills/trophy.html), 🌃 [Skill City](https://mohitagw15856.github.io/pm-claude-skills/city.html), ☄️ the Reckoning orrery. Plus the record going public: **first official [SkillBench results](skillbench/results.json)** (Haiku 4.5 vs Sonnet 4.6), evolution loop run #1 (all champions held under blind judging), 3 sha256-pinned [registry packs](packs/), and a live **free-runs-served badge**. *Earlier — v44, the legendary release:* Campaign mode, the Professional Work Handbook (2,297-rule Anti-Pattern Almanac), the Reckoning, the ecosystem package manager, zero-key MCP sampling, pm-skills-tools, the SkillSpec badge & the census. *Earlier — v43, the local-first & learning wave:* the 🗂 workspace bridge, Boardroom replay links & bench packs, 🎤 The Panel, 🎓 The Academy, 🎁 Wrapped, the evolution loop & pm-method. *Earlier — v42:* depth (`references/` + `templates/`) on all Production-Ready skills, 🔊 Theatre voices, Firm calibration & the CI smoke suite. *Earlier — v41, the modern skills wave:* two new domains — **🤖 [`pm-agentnative`](plugins/pm-agentnative)** (build for non-human users: [`mcp-server-spec`](skills/mcp-server-spec/SKILL.md), [`agent-readiness-audit`](skills/agent-readiness-audit/SKILL.md), [`agent-era-pricing`](skills/agent-era-pricing/SKILL.md), [`human-in-the-loop-design`](skills/human-in-the-loop-design/SKILL.md), [`voice-agent-design`](skills/voice-agent-design/SKILL.md)) and **🧑‍💼 [`pm-aiwork`](plugins/pm-aiwork)** (the questions every manager has this year: [`ai-roi-audit`](skills/ai-roi-audit/SKILL.md), [`role-redesign-for-ai`](skills/role-redesign-for-ai/SKILL.md), [`ai-usage-policy`](skills/ai-usage-policy/SKILL.md), [`ai-assisted-performance-review`](skills/ai-assisted-performance-review/SKILL.md), [`ai-content-audit`](skills/ai-content-audit/SKILL.md)) — plus 5 singles ([`ai-code-review`](skills/ai-code-review/SKILL.md), [`synthetic-user-research`](skills/synthetic-user-research/SKILL.md), [`async-decision-memo`](skills/async-decision-memo/SKILL.md), [`brand-impersonation-response`](skills/brand-impersonation-response/SKILL.md), [`feature-sunset-plan`](skills/feature-sunset-plan/SKILL.md)). Also: 🌠 Galaxy shooting stars + a 🎲 Warp button, 🎓 frameable [certificates](web/export-doc.js) from the arena pages, and 🔌 [MCP pairings](connectors/mcp-pairings.md) — skills that act through your connected servers. *Earlier — v40: [The Firm](https://mohitagw15856.github.io/pm-claude-skills/firm.html). v39 (three waves):* ⚡ *Superpowers:* [SkillBench](skillbench/) (the professional-work benchmark for models) · the [community registry](community/) (npm-for-skills) · the [Interview Gauntlet](https://mohitagw15856.github.io/pm-claude-skills/gauntlet.html) · [CI recipes](action/examples/) + [ambient hooks](hooks/) · Hugging Face [dataset publishing](dataset/) · [localization to 8 languages](i18n/). 🤯 *Breathtaking:* [living artifacts](https://mohitagw15856.github.io/pm-claude-skills/), [Document X-ray](https://mohitagw15856.github.io/pm-claude-skills/xray.html), [The Gym](https://mohitagw15856.github.io/pm-claude-skills/gym.html), [`pm-vision`](plugins/pm-vision), [`style-fingerprint`](skills/style-fingerprint/SKILL.md), [`evidence-lock`](skills/evidence-lock/SKILL.md). ✨ *Revamped:* the playground command bar + Galaxy 2.0 with a guided Sky tour. **466 skills · 66 bundles · 25 professions.** → [CHANGELOG](CHANGELOG.md) · [all releases](https://github.com/mohitagw15856/pm-claude-skills/releases).
+**🆕 v48.0.0 — the institution release:** 🏛 **[The Open Institute for Professional Judgment](https://mohitagw15856.github.io/pm-claude-skills/institute.html)** — SkillSpec (+ its [foundation trajectory](docs/FOUNDATION.md)), the Operator's Exam, SkillBench rankings, the census, the Season (with the Hall + automated rollover), and **[The State of Professional AI 2026](docs/reports/state-of-professional-ai-2026.md)**; 🏢 the **[Org Edition](org/)** (`docker compose up` = your company's library on your infra), 🎓 the **[6-week Syllabus](docs/syllabus/)** with SCORM export, 🎖 **[Agent Conformance](conformance/)** certification, 💼 the **[creator economy](docs/CREATORS.md)** (0% take). Plus the frontier wave: 🏆 the Season is OPEN, 🌙 the Nightwatch, ⏰ standing skills, 🗺 the Atlas, 📻 the Morning Show, 👥 multiplayer Boardroom, 🧠 the 7b pipeline. *Earlier — v46, the arsenal release:* ⚔️ **[`pm-warroom`](plugins/pm-warroom)** — the adversarial bundle (Premortem Assassin's twelve failure vectors, Devil's Twin writes the opposition's best memo, Metric Gaslighting Detector's eleven distortions, Decision Autopsy, Assumption Bounty), 🧮 **three more skills that do real math** (Erlang-C staffing, schedule Monte Carlo over the task DAG, tornado sensitivity — CI-pinned exact outputs), 🎭 shareable singles (eulogy-writer, wedding-speech, fine-appeal-letter, skill-fusion), 🎨 **generative identities on every skill page and playground card** (five banner families seeded from the name, matching colours + monograms, ⓘ links), 🎯 **466/466 SkillSpec L3 — CI-enforced**, 🧪 the 76-assertion scripts harness, 📱 the **PWA** (no-API core offline), 📈 [public vitals](https://mohitagw15856.github.io/pm-claude-skills/status.html) + self-operating crons, 🗺 [REPO-MAP](REPO-MAP.md). **466 skills · 66 bundles.** *Earlier — v45, the spectacle release:* Duels, the Charter, Galaxy 3D, the collapsing Tower of Claims, the Stage, holo cards & Skill City. *Earlier — v44, the legendary release:* Campaign mode, the Professional Work Handbook (2,297-rule Anti-Pattern Almanac), the Reckoning, the ecosystem package manager, zero-key MCP sampling, pm-skills-tools, the SkillSpec badge & the census. *Earlier — v43, the local-first & learning wave:* the 🗂 workspace bridge, Boardroom replay links & bench packs, 🎤 The Panel, 🎓 The Academy, 🎁 Wrapped, the evolution loop & pm-method. *Earlier — v42:* depth (`references/` + `templates/`) on all Production-Ready skills, 🔊 Theatre voices, Firm calibration & the CI smoke suite. *Earlier — v41, the modern skills wave:* two new domains — **🤖 [`pm-agentnative`](plugins/pm-agentnative)** (build for non-human users: [`mcp-server-spec`](skills/mcp-server-spec/SKILL.md), [`agent-readiness-audit`](skills/agent-readiness-audit/SKILL.md), [`agent-era-pricing`](skills/agent-era-pricing/SKILL.md), [`human-in-the-loop-design`](skills/human-in-the-loop-design/SKILL.md), [`voice-agent-design`](skills/voice-agent-design/SKILL.md)) and **🧑‍💼 [`pm-aiwork`](plugins/pm-aiwork)** (the questions every manager has this year: [`ai-roi-audit`](skills/ai-roi-audit/SKILL.md), [`role-redesign-for-ai`](skills/role-redesign-for-ai/SKILL.md), [`ai-usage-policy`](skills/ai-usage-policy/SKILL.md), [`ai-assisted-performance-review`](skills/ai-assisted-performance-review/SKILL.md), [`ai-content-audit`](skills/ai-content-audit/SKILL.md)) — plus 5 singles ([`ai-code-review`](skills/ai-code-review/SKILL.md), [`synthetic-user-research`](skills/synthetic-user-research/SKILL.md), [`async-decision-memo`](skills/async-decision-memo/SKILL.md), [`brand-impersonation-response`](skills/brand-impersonation-response/SKILL.md), [`feature-sunset-plan`](skills/feature-sunset-plan/SKILL.md)). Also: 🌠 Galaxy shooting stars + a 🎲 Warp button, 🎓 frameable [certificates](web/export-doc.js) from the arena pages, and 🔌 [MCP pairings](connectors/mcp-pairings.md) — skills that act through your connected servers. *Earlier — v40: [The Firm](https://mohitagw15856.github.io/pm-claude-skills/firm.html). v39 (three waves):* ⚡ *Superpowers:* [SkillBench](skillbench/) (the professional-work benchmark for models) · the [community registry](community/) (npm-for-skills) · the [Interview Gauntlet](https://mohitagw15856.github.io/pm-claude-skills/gauntlet.html) · [CI recipes](action/examples/) + [ambient hooks](hooks/) · Hugging Face [dataset publishing](dataset/) · [localization to 8 languages](i18n/). 🤯 *Breathtaking:* [living artifacts](https://mohitagw15856.github.io/pm-claude-skills/), [Document X-ray](https://mohitagw15856.github.io/pm-claude-skills/xray.html), [The Gym](https://mohitagw15856.github.io/pm-claude-skills/gym.html), [`pm-vision`](plugins/pm-vision), [`style-fingerprint`](skills/style-fingerprint/SKILL.md), [`evidence-lock`](skills/evidence-lock/SKILL.md). ✨ *Revamped:* the playground command bar + Galaxy 2.0 with a guided Sky tour. **466 skills · 66 bundles · 25 professions.** → [CHANGELOG](CHANGELOG.md) · [all releases](https://github.com/mohitagw15856/pm-claude-skills/releases).
 
 ### ▶ See it in action — [try the live Skill Playground](https://mohitagw15856.github.io/pm-claude-skills/)
 
@@ -591,6 +593,8 @@ The same 451 skills reach you through every channel — pick whatever fits your
 | 🚀 **Raycast / Alfred** | Search every skill from your launcher, then open, run, or install it — [`integrations/raycast/`](integrations/raycast/) · [`integrations/alfred/`](integrations/alfred/) |
 | 🤖 **Custom GPT / Gemini Gem** | Publish the library as a GPT (live Actions API) or a Gem — copy-paste setup in [`integrations/custom-gpt/`](integrations/custom-gpt/) · [`integrations/gemini-gem/`](integrations/gemini-gem/) |
 | 💬 **Slack / Discord** | A `/pmskill` slash command in your team chat — one signature-verified Worker for both — [`integrations/chatops/`](integrations/chatops/) |
+| 📱 **Text a skill (SMS/WhatsApp)** | Text a task to a Twilio number, get the drafted artifact back — no app, no browser — [`integrations/twilio/`](integrations/twilio/) |
+| 📧 **Email operator** | Forward a thread to a routing address; the drafted artifact replies in-thread — [`integrations/email/`](integrations/email/) |
 | 🖥️ **IDE rules** | Generated exports for **Cursor, Windsurf, Aider, Cline, Continue, Zed, Roo, Kilo Code** — [`exports/`](exports/) |
 | 🤖 **Agents & answer engines** | [`llms.txt`](https://mohitagw15856.github.io/pm-claude-skills/llms.txt) makes the whole library discoverable & citable |
 
@@ -954,7 +958,7 @@ More templates will follow. If you want to contribute one, see the [template con
 <details>
 <summary>Read more ↓</summary>
 
-**Latest: v45.0.0 — the spectacle release: ⚔️ Duels, 🎓 the verifiable Charter, and the library in 3D (Galaxy 3D, the collapsing Tower of Claims, the Stage, holo cards, the Trophy Forge, Skill City, the orrery) — plus the first official SkillBench results and the first evolution-loop run (466 skills, 66 bundles)** · *v44:* Campaign mode, the Handbook, the Reckoning, the ecosystem package manager, zero-key MCP sampling, pm-skills-tools, the badge & the census · *v43:* the workspace bridge, replay links & bench packs, The Panel, The Academy, Wrapped, the evolution loop & pm-method · *v42:* depth on all Production-Ready skills, arena voices, Firm calibration & the web-tests safety net · *v41, modern skills:* [`pm-agentnative`](plugins/pm-agentnative) + [`pm-aiwork`](plugins/pm-aiwork) (15 skills for the agent era), Galaxy cosmic events, 🎓 certificates & [MCP pairings](connectors/mcp-pairings.md) · *v40: [The Firm](https://mohitagw15856.github.io/pm-claude-skills/firm.html) · v39, three waves:* [SkillBench](skillbench/), the [community registry](community/), the [Interview Gauntlet](https://mohitagw15856.github.io/pm-claude-skills/gauntlet.html), [living artifacts](https://mohitagw15856.github.io/pm-claude-skills/), [Document X-ray](https://mohitagw15856.github.io/pm-claude-skills/xray.html), [The Gym](https://mohitagw15856.github.io/pm-claude-skills/gym.html), pm-vision, i18n, HF publishing, CI recipes & the Galaxy Sky tour. 466 skills across 66 bundles, 25 professions. Every tagged release has complete notes on the **[Releases page](https://github.com/mohitagw15856/pm-claude-skills/releases)**.
+**Latest: v47.0.0 — the off-web release: text or call a skill (signature-verified Twilio Worker), the email-native operator, the printable Operator's Deck with QR deep-links, Run the Firm tycoon game, the local-only Watch-me-work coach extension, and the auto morning-show newsletter — plus a 🆕 New nav group + scrollable dropdowns (466 skills, 66 bundles)** · *v46, the arsenal release:* the pm-warroom adversarial bundle, three more computed skills, the shareable singles, generative identities everywhere, 466/466 L3 CI-enforced, the PWA, public vitals & the self-operating crons · *v44:* Campaign mode, the Handbook, the Reckoning, the ecosystem package manager, zero-key MCP sampling, pm-skills-tools, the badge & the census · *v43:* the workspace bridge, replay links & bench packs, The Panel, The Academy, Wrapped, the evolution loop & pm-method · *v42:* depth on all Production-Ready skills, arena voices, Firm calibration & the web-tests safety net · *v41, modern skills:* [`pm-agentnative`](plugins/pm-agentnative) + [`pm-aiwork`](plugins/pm-aiwork) (15 skills for the agent era), Galaxy cosmic events, 🎓 certificates & [MCP pairings](connectors/mcp-pairings.md) · *v40: [The Firm](https://mohitagw15856.github.io/pm-claude-skills/firm.html) · v39, three waves:* [SkillBench](skillbench/), the [community registry](community/), the [Interview Gauntlet](https://mohitagw15856.github.io/pm-claude-skills/gauntlet.html), [living artifacts](https://mohitagw15856.github.io/pm-claude-skills/), [Document X-ray](https://mohitagw15856.github.io/pm-claude-skills/xray.html), [The Gym](https://mohitagw15856.github.io/pm-claude-skills/gym.html), pm-vision, i18n, HF publishing, CI recipes & the Galaxy Sky tour. 466 skills across 66 bundles, 25 professions. Every tagged release has complete notes on the **[Releases page](https://github.com/mohitagw15856/pm-claude-skills/releases)**.
 
 Full [Keep a Changelog](https://keepachangelog.com/)-format history — every release back to the start — is in **[CHANGELOG.md](CHANGELOG.md)**.
 

package/bin/brief.mjs

@@ -0,0 +1,89 @@
+// `pm-claude-skills brief` — the chief-of-staff, on demand. The SessionStart
+// hook's morning brief as a human command: predictions due, the latest arena
+// verdicts, open hypotheses, and (with --stats) the project's public vitals.
+// Pure file reads + two public GETs. No API key, no cost.
+//
+//   pm-claude-skills brief            # this directory's professional state
+//   pm-claude-skills stats            # the public vitals (runs served, stars, bench)
+import { readFileSync, readdirSync, existsSync } from 'node:fs';
+import { join } from 'node:path';
+
+const cwd = process.cwd();
+const today = () => new Date().toISOString().slice(0, 10);
+const dim = (s) => `\x1b[2m${s}\x1b[0m`;
+const bold = (s) => `\x1b[1m${s}\x1b[0m`;
+
+function predictions() {
+  const dir = join(cwd, 'brain', 'predictions');
+  if (!existsSync(dir)) return { due: [], open: 0 };
+  const due = []; let open = 0;
+  for (const f of readdirSync(dir).filter((x) => x.endsWith('.md'))) {
+    const t = readFileSync(join(dir, f), 'utf8');
+    if (!/^status:\s*pending$/m.test(t)) continue;
+    open++;
+    const d = (t.match(/^due:\s*(\S+)/m) || [])[1];
+    if (d && d <= today()) {
+      const line = (t.split(/\n---\n/)[1] || '').trim().split('\n')[0];
+      due.push({ due: d, text: line, file: f });
+    }
+  }
+  return { due, open };
+}
+function latestIn(dir, skipDirs = true) {
+  const p = join(cwd, dir);
+  if (!existsSync(p)) return null;
+  const files = readdirSync(p).filter((f) => !skipDirs || f.includes('.'));
+  if (!files.length) return null;
+  return files.sort().pop();
+}
+function hypotheses() {
+  for (const c of ['brain/hypotheses.md', 'brain/hypotheses']) {
+    const p = join(cwd, c);
+    if (!existsSync(p)) continue;
+    try {
+      const text = c.endsWith('.md') ? readFileSync(p, 'utf8')
+        : readdirSync(p).map((f) => readFileSync(join(p, f), 'utf8')).join('\n');
+      return text.split('\n').filter((l) => l.trim().startsWith('- ')).slice(0, 5);
+    } catch { return []; }
+  }
+  return [];
+}
+
+export async function brief() {
+  console.log(bold(`☀️  Chief of Staff — ${today()}`) + dim(`  (${cwd})`) + '\n');
+  const { due, open } = predictions();
+  if (due.length) {
+    console.log(bold('🔔 Predictions due — settle them:'));
+    for (const d of due) console.log(`   ${d.due}  ${d.text}  ${dim(d.file)}`);
+    console.log(dim('   pm-claude-skills reckoning score <file> hit|miss') + '\n');
+  } else if (open) console.log(`⏳ ${open} prediction(s) open, none due today.\n`);
+  for (const [dir, label] of [['firm-minutes', '🏢 Latest Firm minutes'], ['boardroom', '🏛 Latest Boardroom artifact']]) {
+    const f = latestIn(dir);
+    if (f) console.log(`${label}: ${f}${dim(' — read before revising what it discusses')}`);
+  }
+  const hyp = hypotheses();
+  if (hyp.length) {
+    console.log('\n' + bold('🧪 Open hypotheses') + dim(' ([hunch] stays unsettled until tested):'));
+    hyp.forEach((h) => console.log('   ' + h.trim().slice(0, 100)));
+  }
+  if (!due.length && !open && !latestIn('firm-minutes') && !hyp.length) {
+    console.log(dim('Nothing on file here. Scaffold the workspace:  pm-claude-skills init'));
+  }
+  return 0;
+}
+
+export async function stats() {
+  console.log(bold('📈 PM Skills — public vitals\n'));
+  try {
+    const h = await (await fetch('https://raw.githubusercontent.com/mohitagw15856/pm-claude-skills/vitals-data/history.json')).json();
+    const last = h[h.length - 1] || {}, first = h[0] || {};
+    console.log(`  🔥 Free runs served: ${bold(String(last.runs ?? '—'))}  (${h.length} days on the ledger, +${(last.runs ?? 0) - (first.runs ?? 0)} this period)`);
+    console.log(`  ⭐ Stars: ${bold(String(last.stars ?? '—'))}`);
+  } catch { console.log(dim('  vitals ledger unreachable')); }
+  try {
+    const b = await (await fetch('https://raw.githubusercontent.com/mohitagw15856/pm-claude-skills/main/skillbench/results.json')).json();
+    for (const r of (b.runs || [])) console.log(`  🏆 SkillBench: ${r.model} → ${r.score}  ${dim('(' + (r.date || '').slice(0, 10) + ')')}`);
+  } catch { /* fine */ }
+  console.log(dim('\n  Live dashboard: https://mohitagw15856.github.io/pm-claude-skills/status.html'));
+  return 0;
+}

package/bin/cli.mjs

@@ -252,6 +252,10 @@ Usage:
   npx pm-claude-skills council <skill>        # author -> cross-vendor critique -> arbiter (2+ provider keys)
   npx pm-claude-skills migrate <dir>          # convert a folder of prompts/SOPs into SkillSpec skills
   npx pm-claude-skills init        # scaffold the professional workspace here (brain/, context, arena folders)
+  npx pm-claude-skills nightwatch  # AI staff work this directory while you sleep (install | --once | --dry-run)
+  npx pm-claude-skills subscribe   # standing skills: scheduled runs that report what CHANGED
+  npx pm-claude-skills brief       # the chief-of-staff: predictions due, latest verdicts, open hypotheses
+  npx pm-claude-skills stats       # the project's public vitals (runs served, stars, benchmark)
   npx pm-claude-skills reckoning   # your prediction ledger: due calls, hit rate, calibration curve, Brier score
   npx pm-claude-skills doctor      # checkup: what's installed, what's stale, what to fix (read-only)
   npx pm-claude-skills list
@@ -297,6 +301,21 @@ else if (cmd === 'verify') {
   try { process.exit(await run(process.argv.slice(3))); }
   catch (e) { console.error(`Error: ${e.message}`); process.exit(1); }
 }
+else if (cmd === 'nightwatch') {
+  const { run } = await import('./nightwatch.mjs');
+  try { process.exit(await run(process.argv.slice(3))); }
+  catch (e) { console.error(`Error: ${e.message}`); process.exit(1); }
+}
+else if (cmd === 'subscribe') {
+  const { run } = await import('./subscribe.mjs');
+  try { process.exit(await run(process.argv.slice(3))); }
+  catch (e) { console.error(`Error: ${e.message}`); process.exit(1); }
+}
+else if (cmd === 'brief' || cmd === 'stats') {
+  const m = await import('./brief.mjs');
+  try { process.exit(await (cmd === 'brief' ? m.brief() : m.stats())); }
+  catch (e) { console.error(`Error: ${e.message}`); process.exit(1); }
+}
 else if (cmd === 'reckoning') {
   const { run } = await import('./reckoning.mjs');
   try { process.exit(await run(process.argv.slice(3))); }

package/bin/lib/scheduler.mjs

@@ -0,0 +1,61 @@
+// Local job scheduling for the Nightwatch and standing-skill subscriptions.
+// macOS: launchd plists in ~/Library/LaunchAgents; Linux: user crontab lines.
+// Everything is inspectable, labeled, and uninstallable by name.
+import { writeFileSync, existsSync, unlinkSync, readdirSync } from 'node:fs';
+import { join } from 'node:path';
+import { homedir, platform } from 'node:os';
+import { execSync } from 'node:child_process';
+
+const PREFIX = 'com.pm-skills.';
+
+export function install(name, argvArray, { hour = 5, minute = 30, cron = null } = {}) {
+  if (platform() === 'darwin') {
+    const label = PREFIX + name;
+    const plist = `<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0"><dict>
+  <key>Label</key><string>${label}</string>
+  <key>ProgramArguments</key><array>${argvArray.map((a) => `<string>${a}</string>`).join('')}</array>
+  <key>StartCalendarInterval</key><dict><key>Hour</key><integer>${hour}</integer><key>Minute</key><integer>${minute}</integer></dict>
+  <key>WorkingDirectory</key><string>${process.cwd()}</string>
+  <key>StandardOutPath</key><string>${join(process.cwd(), '.pm-skills', name + '.log')}</string>
+  <key>StandardErrorPath</key><string>${join(process.cwd(), '.pm-skills', name + '.log')}</string>
+</dict></plist>`;
+    const p = join(homedir(), 'Library', 'LaunchAgents', label + '.plist');
+    writeFileSync(p, plist);
+    try { execSync(`launchctl unload ${JSON.stringify(p)} 2>/dev/null`); } catch { /* not loaded */ }
+    execSync(`launchctl load ${JSON.stringify(p)}`);
+    return { kind: 'launchd', path: p, when: `daily ${String(hour).padStart(2, '0')}:${String(minute).padStart(2, '0')}` };
+  }
+  // Linux: append a labeled crontab line.
+  const line = `${cron || `${minute} ${hour} * * *`} cd ${process.cwd()} && ${argvArray.map((a) => JSON.stringify(a)).join(' ')} >> .pm-skills/${name}.log 2>&1 # ${PREFIX}${name}`;
+  const current = (() => { try { return execSync('crontab -l').toString(); } catch { return ''; } })();
+  const cleaned = current.split('\n').filter((l) => !l.includes(`# ${PREFIX}${name}`)).join('\n').trim();
+  execSync('crontab -', { input: cleaned + '\n' + line + '\n' });
+  return { kind: 'cron', path: 'crontab', when: cron || `daily ${hour}:${minute}` };
+}
+
+export function uninstall(name) {
+  if (platform() === 'darwin') {
+    const p = join(homedir(), 'Library', 'LaunchAgents', PREFIX + name + '.plist');
+    if (!existsSync(p)) return false;
+    try { execSync(`launchctl unload ${JSON.stringify(p)}`); } catch { /* fine */ }
+    unlinkSync(p);
+    return true;
+  }
+  const current = (() => { try { return execSync('crontab -l').toString(); } catch { return ''; } })();
+  const cleaned = current.split('\n').filter((l) => !l.includes(`# ${PREFIX}${name}`)).join('\n');
+  if (cleaned === current) return false;
+  execSync('crontab -', { input: cleaned });
+  return true;
+}
+
+export function list() {
+  if (platform() === 'darwin') {
+    const dir = join(homedir(), 'Library', 'LaunchAgents');
+    if (!existsSync(dir)) return [];
+    return readdirSync(dir).filter((f) => f.startsWith(PREFIX)).map((f) => f.slice(PREFIX.length).replace(/\.plist$/, ''));
+  }
+  try { return execSync('crontab -l').toString().split('\n').filter((l) => l.includes('# ' + PREFIX)).map((l) => l.split('# ' + PREFIX)[1]); }
+  catch { return []; }
+}

package/bin/nightwatch.mjs

@@ -0,0 +1,102 @@
+// `pm-claude-skills nightwatch` — your AI staff work while you sleep.
+// A scheduled Agent SDK run (YOUR key, YOUR machine, this directory) where the
+// Firm's discipline meets real files: triage the brain, draft what the open
+// hypotheses and due predictions imply, file memos to firm-minutes/, and leave
+// a morning brief of WORK DONE, not work suggested.
+//
+//   pm-claude-skills nightwatch --once            # run right now, watch it work
+//   pm-claude-skills nightwatch --once --dry-run  # show the shift plan, no API calls
+//   pm-claude-skills nightwatch install [--hour 5 --minute 30]   # schedule nightly
+//   pm-claude-skills nightwatch uninstall | status
+//
+// Requires: ANTHROPIC_API_KEY in the environment (for scheduled runs, launchd/cron
+// must see it — the installer checks and tells you). Spend is bounded by
+// --max-turns (default 30) and the model (default Sonnet). All writes stay in
+// this directory: artifacts/, firm-minutes/, brain/.
+import { readFileSync, readdirSync, existsSync, mkdirSync, writeFileSync } from 'node:fs';
+import { join } from 'node:path';
+import { install, uninstall, list } from './lib/scheduler.mjs';
+
+const getArg = (argv, n, d) => { const i = argv.indexOf('--' + n); return i >= 0 && argv[i + 1] ? argv[i + 1] : d; };
+const today = () => new Date().toISOString().slice(0, 10);
+
+function shiftPlan(cwd) {
+  // The night shift's standing orders, grounded in what's actually on file.
+  const read = (p) => { try { return readFileSync(join(cwd, p), 'utf8'); } catch { return ''; } };
+  const ctx = read('brain/context.md') || read('pm-context.md');
+  const duties = [];
+  const predDir = join(cwd, 'brain', 'predictions');
+  if (existsSync(predDir)) {
+    const due = readdirSync(predDir).filter((f) => {
+      const t = read('brain/predictions/' + f);
+      const d = (t.match(/^due:\s*(\S+)/m) || [])[1];
+      return /^status:\s*pending$/m.test(t) && d && d <= today();
+    });
+    if (due.length) duties.push(`RECKON: ${due.length} prediction(s) are due (${due.join(', ')}). For each: search this directory's files for evidence, then either settle it by editing its status to hit/miss with a one-line justification appended, or write why it cannot be settled from available evidence.`);
+  }
+  const hyp = read('brain/hypotheses.md');
+  const hunches = (hyp.match(/^- \[hunch\].*$/gm) || []).slice(0, 2);
+  if (hunches.length) duties.push(`INVESTIGATE: for each open hunch (${hunches.map((h) => '"' + h.slice(0, 60) + '"').join('; ')}), gather whatever evidence exists in this directory's files and append a dated [data]/[external] line to brain/ if anything upgrades or kills it.`);
+  duties.push('DRAFT: pick the ONE most useful artifact this workspace obviously needs next (an overdue update, the doc a settled prediction implies, the summary firm-minutes/ has been circling) and draft it properly to artifacts/' + today() + '-<slug>.md using the matching installed skill\'s structure — its Quality Checks are your acceptance test.');
+  duties.push('REPORT: write firm-minutes/nightwatch-' + today() + '.md — the morning brief: what was DONE (with file paths), what was settled, what needs a human decision (max 3 items), each with your recommendation.');
+  return { ctx, duties };
+}
+
+export async function run(argv) {
+  const cmd = argv.find((a) => !a.startsWith('--')) || (argv.includes('--once') ? 'once' : 'help');
+  const cwd = process.cwd();
+
+  if (cmd === 'install') {
+    if (!process.env.ANTHROPIC_API_KEY) console.error('⚠ ANTHROPIC_API_KEY is not in this shell — the scheduled job needs it. Add it to the plist/cron environment or a .env this directory loads.');
+    const r = install('nightwatch', [process.execPath, join(new URL('.', import.meta.url).pathname, 'cli.mjs'), 'nightwatch', '--once'],
+      { hour: +getArg(argv, 'hour', 5), minute: +getArg(argv, 'minute', 30) });
+    mkdirSync(join(cwd, '.pm-skills'), { recursive: true });
+    console.log(`🌙 Nightwatch scheduled (${r.kind}, ${r.when}) for ${cwd}\n   Logs: .pm-skills/nightwatch.log · remove: pm-claude-skills nightwatch uninstall`);
+    return 0;
+  }
+  if (cmd === 'uninstall') { console.log(uninstall('nightwatch') ? '🌙 Nightwatch unscheduled.' : 'Nothing scheduled.'); return 0; }
+  if (cmd === 'status') { const l = list(); console.log(l.length ? 'Scheduled: ' + l.join(', ') : 'Nothing scheduled.'); return 0; }
+
+  if (cmd === 'once' || argv.includes('--once')) {
+    const { ctx, duties } = shiftPlan(cwd);
+    if (argv.includes('--dry-run')) {
+      console.log(`🌙 Nightwatch shift plan for ${cwd} (dry run — no API calls):\n`);
+      duties.forEach((d, i) => console.log(`  ${i + 1}. ${d.split(':')[0]}: ${d.split(': ').slice(1).join(': ').slice(0, 140)}…\n`));
+      console.log(`Context loaded: ${ctx ? 'brain/context.md (' + ctx.length + ' chars)' : 'NONE — run pm-claude-skills init'}`);
+      return 0;
+    }
+    if (!process.env.ANTHROPIC_API_KEY) { console.error('ANTHROPIC_API_KEY not set. (--dry-run shows the shift plan for free.)'); return 1; }
+    let query;
+    try { ({ query } = await import('@anthropic-ai/claude-agent-sdk')); }
+    catch { console.error('The Nightwatch needs the Agent SDK:  npm install -g @anthropic-ai/claude-agent-sdk  (or run from a directory that has it)'); return 1; }
+    mkdirSync(join(cwd, 'artifacts'), { recursive: true });
+    console.error(`🌙 Nightwatch shift starting in ${cwd} — ${duties.length} standing orders…`);
+    const prompt = `You are the Nightwatch — the professional staff working this workspace overnight. Complete these standing orders IN ORDER, doing real file work (read, then write), never inventing facts not found in the files:\n\n${duties.map((d, i) => `${i + 1}. ${d}`).join('\n\n')}`;
+    const append = `\nSTANDING CONTEXT:\n${(ctx || '(none)').slice(0, 4000)}\n\nHOUSE RULES: honour brain/ provenance tags; artifacts follow installed skill structures where one matches; every claim in the morning brief cites the file it came from; if evidence is insufficient, say so rather than padding.`;
+    let cost = 0, turns = 0;
+    for await (const message of query({ prompt, options: {
+      systemPrompt: { type: 'preset', preset: 'claude_code', append },
+      allowedTools: ['Read', 'Write', 'Edit', 'Glob', 'Grep'],
+      permissionMode: 'acceptEdits',
+      maxTurns: +getArg(argv, 'max-turns', 30),
+      model: getArg(argv, 'model', undefined),
+    } })) {
+      if (message.type === 'result') { cost = message.total_cost_usd ?? 0; turns = message.num_turns; }
+    }
+    const brief = join(cwd, 'firm-minutes', `nightwatch-${today()}.md`);
+    console.error(`🌙 Shift complete — ${turns} turns, $${cost.toFixed(4)}. Morning brief: ${existsSync(brief) ? brief : '(not filed — check the log)'}`);
+    return 0;
+  }
+
+  console.log(`The Nightwatch — AI staff that work this directory while you sleep.
+
+  pm-claude-skills nightwatch --once              run a shift now
+  pm-claude-skills nightwatch --once --dry-run    see the shift plan, no API calls
+  pm-claude-skills nightwatch install             schedule nightly (5:30am default; --hour/--minute)
+  pm-claude-skills nightwatch uninstall | status
+
+A shift: settle due predictions against file evidence · investigate open hunches ·
+draft the one artifact the workspace needs · file the morning brief of work DONE.
+Writes only inside this directory. Your key, bounded turns.`);
+  return 0;
+}

package/bin/subscribe.mjs

@@ -0,0 +1,76 @@
+// `pm-claude-skills subscribe` — skills as standing subscriptions. A skill that
+// runs on a schedule against a living input (a CSV export, a notes file), files
+// dated artifacts into brain/artifacts, and DIFFS against last time: the run's
+// headline is what CHANGED, not what is.
+//
+//   pm-claude-skills subscribe churn-analysis --input ./exports/latest.csv --weekly monday
+//   pm-claude-skills subscribe run churn-analysis --input ./exports/latest.csv   # run one cycle now
+//   pm-claude-skills subscribe list | unsubscribe <skill>
+//
+// Scheduled runs need ANTHROPIC_API_KEY visible to launchd/cron. Artifacts:
+// brain/subscriptions/<skill>/<date>.md (+ latest.md symlink-copy + CHANGES.md).
+import { readFileSync, writeFileSync, existsSync, mkdirSync, readdirSync, copyFileSync } from 'node:fs';
+import { join, dirname } from 'node:path';
+import { fileURLToPath } from 'node:url';
+import { install, uninstall, list } from './lib/scheduler.mjs';
+import { complete, parseSkill } from './lib/anthropic.mjs';
+
+const PKG_ROOT = dirname(dirname(fileURLToPath(import.meta.url)));
+const getArg = (argv, n, d) => { const i = argv.indexOf('--' + n); return i >= 0 && argv[i + 1] ? argv[i + 1] : d; };
+const DAYS = { sunday: 0, monday: 1, tuesday: 2, wednesday: 3, thursday: 4, friday: 5, saturday: 6 };
+const today = () => new Date().toISOString().slice(0, 10);
+
+async function runCycle(skill, inputPath, model) {
+  const file = join(PKG_ROOT, 'skills', skill, 'SKILL.md');
+  if (!existsSync(file)) { console.error(`Unknown skill "${skill}".`); return 1; }
+  if (!existsSync(inputPath)) { console.error(`Input not found: ${inputPath}`); return 1; }
+  const apiKey = process.env.ANTHROPIC_API_KEY;
+  if (!apiKey) { console.error('ANTHROPIC_API_KEY not set.'); return 1; }
+  const dir = join(process.cwd(), 'brain', 'subscriptions', skill);
+  mkdirSync(dir, { recursive: true });
+  const prev = existsSync(join(dir, 'latest.md')) ? readFileSync(join(dir, 'latest.md'), 'utf8') : null;
+  const { body } = parseSkill(readFileSync(file, 'utf8'));
+  const input = readFileSync(inputPath, 'utf8').slice(0, 60000);
+  console.error(`⏰ ${skill} ← ${inputPath}${prev ? ' (diffing vs last run)' : ' (first run)'}`);
+  const out = await complete({ apiKey, model: model || 'claude-sonnet-4-6', maxTokens: 8192,
+    system: body + '\n\n---\nExecute this skill on the input below. This is a RECURRING run.' +
+      (prev ? ' The previous run\'s output is provided — begin your output with a "## What changed since last run" section (3-6 bullets, most decision-relevant first, honest "nothing material" if true), THEN the full artifact.' : ''),
+    messages: [{ role: 'user', content: 'INPUT:\n' + input + (prev ? '\n\nPREVIOUS RUN OUTPUT:\n' + prev.slice(0, 20000) : '') }] });
+  const dated = join(dir, today() + '.md');
+  writeFileSync(dated, out + '\n');
+  copyFileSync(dated, join(dir, 'latest.md'));
+  const changes = (out.match(/## What changed[\s\S]*?(?=\n## |$)/) || [''])[0];
+  if (changes) writeFileSync(join(dir, 'CHANGES.md'), `# ${skill} — last delta (${today()})\n\n${changes}\n`);
+  console.error(`✅ ${dated}${changes ? ' · delta → CHANGES.md' : ''}`);
+  return 0;
+}
+
+export async function run(argv) {
+  const a0 = argv[0];
+  if (a0 === 'list') { const l = list().filter((n) => n.startsWith('sub-')); console.log(l.length ? l.map((x) => '  ⏰ ' + x.slice(4)).join('\n') : 'No subscriptions.'); return 0; }
+  if (a0 === 'unsubscribe') { console.log(uninstall('sub-' + argv[1]) ? '⏰ Unsubscribed ' + argv[1] : 'No such subscription.'); return 0; }
+  if (a0 === 'run') return runCycle(argv[1], getArg(argv, 'input'), getArg(argv, 'model'));
+
+  const skill = a0 && !a0.startsWith('--') ? a0 : null;
+  const input = getArg(argv, 'input');
+  if (!skill || !input) {
+    console.log(`Standing skills — a skill that runs on a schedule and reports what CHANGED.
+
+  pm-claude-skills subscribe <skill> --input <file> [--weekly monday | --daily] [--hour 6]
+  pm-claude-skills subscribe run <skill> --input <file>     # one cycle now
+  pm-claude-skills subscribe list | unsubscribe <skill>
+
+Artifacts land in brain/subscriptions/<skill>/ — dated runs, latest.md, and
+CHANGES.md (the delta since last run, which is the part worth reading).`);
+    return skill ? 0 : 1;
+  }
+  const weekly = getArg(argv, 'weekly', null);
+  const hour = +getArg(argv, 'hour', 6);
+  const cron = weekly ? `0 ${hour} * * ${DAYS[weekly.toLowerCase()] ?? 1}` : null;
+  const r = install('sub-' + skill,
+    [process.execPath, join(dirname(fileURLToPath(import.meta.url)), 'cli.mjs'), 'subscribe', 'run', skill, '--input', input],
+    { hour, minute: 0, cron });
+  mkdirSync(join(process.cwd(), '.pm-skills'), { recursive: true });
+  console.log(`⏰ Subscribed: ${skill} ← ${input}  (${r.kind}, ${weekly ? 'weekly ' + weekly : r.when})\n   First cycle now:  pm-claude-skills subscribe run ${skill} --input ${input}`);
+  return 0;
+}

package/commands/adopt-ai-properly.md

@@ -1,6 +1,6 @@
 ---
 description: Workflow recipe — the org-side AI adoption arc, policy to proof, by chaining 4 skills.
-argument-hint: [the org: size, industry, what AI tools are in use (officially and not), what's worrying leadership]
+argument-hint: "[the org: size, industry, what AI tools are in use (officially and not), what's worrying leadership]"
 ---
 
 Run the **Adopt AI Properly** workflow recipe for: $ARGUMENTS

package/commands/brain.md

@@ -1,6 +1,6 @@
 ---
 description: Set up or use your Professional Brain — init, ingest, recall, or review.
-argument-hint: [init | ingest <thing> | recall <query> | review]
+argument-hint: "[init | ingest <thing> | recall <query> | review]"
 ---
 
 Apply the **professional-brain** skill to: $ARGUMENTS

package/commands/close-the-quarter.md

@@ -1,6 +1,6 @@
 ---
 description: Workflow recipe — turn the quarter's raw numbers into a leadership story and board deck by chaining 4 skills.
-argument-hint: [the quarter's metrics, wins, and misses]
+argument-hint: "[the quarter's metrics, wins, and misses]"
 ---
 
 Run the **Close the Quarter** workflow recipe for: $ARGUMENTS

package/commands/exec-summary.md

@@ -1,6 +1,6 @@
 ---
 description: Compress a document or update into a crisp executive summary.
-argument-hint: [text, decision, or document to summarise]
+argument-hint: "[text, decision, or document to summarise]"
 ---
 
 Apply the **executive-summary** skill to: $ARGUMENTS

package/commands/firm.md

@@ -1,6 +1,6 @@
 ---
 description: Convene your standing AI staff — memos on every beat, a board session without you, minutes with dissent preserved.
-argument-hint: [optional board agenda — otherwise the staff pick the sharpest open question]
+argument-hint: "[optional board agenda — otherwise the staff pick the sharpest open question]"
 ---
 
 You are the **chief of staff** running a session of the user's standing Firm — a staffed team, not a chatbot. Full concept: the repo's `web/firm.html`; this command is its Claude Code native form, grounded in real files instead of a pasted charter.

package/commands/grow-a-product.md

@@ -1,6 +1,6 @@
 ---
 description: Workflow recipe — turn a growth goal into a funnel diagnosis, experiment backlog, retention loop, and lifecycle journeys by chaining 4 skills.
-argument-hint: [the growth goal — e.g. "lift D30 retention for B2B teams"]
+argument-hint: '[the growth goal — e.g. "lift D30 retention for B2B teams"]'
 ---
 
 Run the **Grow a Product** workflow recipe for: $ARGUMENTS

package/commands/health-scorecard.md

@@ -1,6 +1,6 @@
 ---
 description: Build a weighted customer health scorecard for an account.
-argument-hint: [account name + usage/support/commercial signals]
+argument-hint: "[account name + usage/support/commercial signals]"
 ---
 
 Apply the **cs-health-scorecard** skill to: $ARGUMENTS

package/commands/land-a-job.md

@@ -1,6 +1,6 @@
 ---
 description: Workflow recipe — go after a specific role end to end by chaining 4 skills: decode the JD, research the company, tailor your application, and prep the interview.
-argument-hint: [the role + company, or paste the job description]
+argument-hint: "[the role + company, or paste the job description]"
 ---
 
 Run the **Land a Job** workflow recipe for: $ARGUMENTS

package/commands/launch-a-product.md

@@ -1,6 +1,6 @@
 ---
 description: Workflow recipe — go from competitive landscape to a fully checklisted launch and press release by chaining 5 skills.
-argument-hint: [the product and who it's for]
+argument-hint: "[the product and who it's for]"
 ---
 
 Run the **Launch a Product** workflow recipe for: $ARGUMENTS

package/commands/launch-an-ai-feature.md

@@ -1,6 +1,6 @@
 ---
 description: Workflow recipe — take an AI/LLM feature from a probabilistic-aware PRD to a launch-ready model card by chaining 5 skills.
-argument-hint: [the AI feature idea]
+argument-hint: "[the AI feature idea]"
 ---
 
 Run the **Launch an AI Feature** workflow recipe for: $ARGUMENTS

package/commands/prd.md

@@ -1,6 +1,6 @@
 ---
 description: Draft a product requirements document from a feature idea or brief.
-argument-hint: [feature or problem to spec]
+argument-hint: "[feature or problem to spec]"
 ---
 
 Apply the **prd-template** skill to produce a complete PRD for: $ARGUMENTS

package/commands/red-team.md

@@ -1,6 +1,6 @@
 ---
 description: Stress-test a plan, strategy, PRD, or launch with a room of hostile expert personas before you commit.
-argument-hint: [the plan / doc to pressure-test]
+argument-hint: "[the plan / doc to pressure-test]"
 ---
 
 Apply the **red-team-review** skill to pressure-test: $ARGUMENTS

package/commands/repurpose.md

@@ -1,6 +1,6 @@
 ---
 description: Workflow recipe — turn one blog post, video, or idea into a full platform-native content pack (thread, LinkedIn, newsletter, carousel, short-form script) with sharp hooks and a thumbnail concept.
-argument-hint: [a URL, a transcript/blog paste, or the core idea]
+argument-hint: "[a URL, a transcript/blog paste, or the core idea]"
 ---
 
 Run the **Repurpose Content** workflow recipe for: $ARGUMENTS

package/commands/rescue-an-account.md

@@ -1,6 +1,6 @@
 ---
 description: Workflow recipe — diagnose an at-risk customer and build the full save play through to renewal by chaining 4 skills.
-argument-hint: [the account and what's going wrong]
+argument-hint: "[the account and what's going wrong]"
 ---
 
 Run the **Rescue an Account** workflow recipe for: $ARGUMENTS

package/commands/retro.md

@@ -1,6 +1,6 @@
 ---
 description: Run a structured sprint retrospective from notes.
-argument-hint: [what happened this sprint — wins, misses, blockers]
+argument-hint: "[what happened this sprint — wins, misses, blockers]"
 ---
 
 Apply the **retro-analysis** skill to: $ARGUMENTS

package/commands/rice.md

@@ -1,6 +1,6 @@
 ---
 description: Score and rank initiatives with the RICE framework.
-argument-hint: [list of initiatives, or a file/path of them]
+argument-hint: "[list of initiatives, or a file/path of them]"
 ---
 
 Apply the **rice-prioritisation** skill to: $ARGUMENTS

package/commands/run-discovery.md

@@ -1,6 +1,6 @@
 ---
 description: Workflow recipe — go from a vague opportunity to validated insight and a prioritised next step by chaining 4 skills.
-argument-hint: [the opportunity or fuzzy question]
+argument-hint: "[the opportunity or fuzzy question]"
 ---
 
 Run the **Run Discovery** workflow recipe for: $ARGUMENTS

package/commands/setup-context.md

@@ -1,6 +1,6 @@
 ---
 description: Set up your Skill Memory — a pm-context.md every skill reads so outputs come back tailored to you.
-argument-hint: [optional notes about you/your company to seed it]
+argument-hint: "[optional notes about you/your company to seed it]"
 ---
 
 Set up the user's **Skill Memory** (`pm-context.md`).

package/commands/setup-pm-skills.md

@@ -1,6 +1,6 @@
 ---
 description: Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
-argument-hint: [optional — your role / what you're working on]
+argument-hint: "[optional — your role / what you're working on]"
 ---
 
 You are onboarding someone to the **PM Skills** library (198 professional Agent Skills across 27 bundles). Goal: get them from "installed" to "got real value" in under two minutes. Context they gave: $ARGUMENTS

package/commands/ship-a-feature.md

@@ -1,6 +1,6 @@
 ---
 description: Workflow recipe — take a feature idea from fuzzy brief to launch plan by chaining 5 skills.
-argument-hint: [the feature idea or problem]
+argument-hint: "[the feature idea or problem]"
 ---
 
 Run the **Ship a Feature** workflow recipe for: $ARGUMENTS