pm-claude-skills 36.0.0 → 37.0.0

package/README.md

@@ -1,4 +1,4 @@
-# 🧠 PM Skills — 411 Professional Agent Skills for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes
+# 🧠 PM Skills — 420 Professional Agent Skills for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes
 
 [![In the official Anthropic plugin directory](https://img.shields.io/badge/Anthropic%20Plugin%20Directory-Published-D97757?logo=anthropic&logoColor=white)](#-quick-install-2-minutes)
 [![Stars](https://img.shields.io/github/stars/mohitagw15856/pm-claude-skills?style=social)](https://github.com/mohitagw15856/pm-claude-skills/stargazers)
@@ -9,7 +9,7 @@
 [![MCP](https://img.shields.io/badge/MCP-registry-0098FF?logo=modelcontextprotocol&logoColor=white)](https://github.com/mohitagw15856/pm-claude-skills#-use-it-anywhere--the-ai-ecosystem)
 [![Remote MCP](https://img.shields.io/badge/ChatGPT%20%C2%B7%20Claude.ai-connector-10A37F)](mcp-remote/)
 [![Smithery](https://smithery.ai/badge/mohit15856/pm-skills)](https://smithery.ai/servers/mohit15856/pm-skills)
-[![Skills](https://img.shields.io/badge/skills-411-blue)](https://github.com/mohitagw15856/pm-claude-skills)
+[![Skills](https://img.shields.io/badge/skills-420-blue)](https://github.com/mohitagw15856/pm-claude-skills)
 [![eval](https://img.shields.io/badge/eval--scored-208%20%C2%B7%20avg%204.8%2F5-brightgreen)](https://mohitagw15856.github.io/pm-claude-skills/leaderboard.html)
 [![Subagents](https://img.shields.io/badge/subagents-4-blueviolet)](agents/)
 [![Commands](https://img.shields.io/badge/slash%20commands-19-blueviolet)](commands/)
@@ -25,7 +25,7 @@
 
 <p align="center">
   <a href="https://mohitagw15856.github.io/pm-claude-skills/">
-    <img src="https://readme-typing-svg.demolab.com?font=Inter&weight=600&size=24&pause=900&color=D97757&center=true&vCenter=true&width=720&lines=411+pro+AI+skills;PRDs%2C+roadmaps%2C+launches+%E2%80%94+done+right;Run+any+one+free+in+your+browser" alt="PM Skills" />
+    <img src="https://readme-typing-svg.demolab.com?font=Inter&weight=600&size=24&pause=900&color=D97757&center=true&vCenter=true&width=720&lines=420+pro+AI+skills;PRDs%2C+roadmaps%2C+launches+%E2%80%94+done+right;Run+any+one+free+in+your+browser" alt="PM Skills" />
   </a>
 </p>
 
@@ -56,11 +56,11 @@
 *Not sure? Start with the Playground.* This is a **CLI, not a library** — you don't need `npm install`; `npx pm-claude-skills …` always runs the latest. Browse everything first with `npx pm-claude-skills list`.
 
 > **PM stands for Professional, not just Product Management.**
-> 411 professional skills + 4 agent templates across 59 bundles covering 25 professions. Built for Claude Code — and now portable to ChatGPT, Gemini, and Hermes Agent. Built by a PM, used by everyone.
+> 420 professional skills + 4 agent templates across 61 bundles covering 25 professions. Built for Claude Code — and now portable to ChatGPT, Gemini, and Hermes Agent. Built by a PM, used by everyone.
 
 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).
 
-**🆕 Latest — v36.0.0 (Security & Government bundles, Fable 5 & an always-current catalog):** two new professional domains — **🔒 `pm-security`** (hands-on appsec: `threat-model` STRIDE, `security-review`, `vuln-triage` CVSS, `security-incident-response`, `pentest-report` — defensive & authorized-testing framing) and **🏛️ `pm-gov`** (`rfp-response`, `policy-memo`, `public-comment`, `briefing-note`, `foia-request`, `regulatory-impact-analysis`). The playground now offers **Fable 5 ✨**, the newest model, as the default. And **`SKILLS.md` is auto-generated** from the catalog (grouped by domain), so the full listing can never go stale again. *Earlier (v35.0):* the `pm-pmm` Product Marketing bundle, Custom GPT / Gemini Gem, and Raycast/Alfred launchers. **411 skills across 59 bundles.** → **[Full release history & notes](https://github.com/mohitagw15856/pm-claude-skills/releases)**.
+**🆕 Latest — v37.0.0 (The Boardroom, AgentOps, Autopilot & a skill router):** **🏛️ [The Boardroom](https://mohitagw15856.github.io/pm-claude-skills/boardroom.html)** — paste a PRD or pitch and five AI executives debate it live (openings → cross-examination → verdict memo with the changes that would survive the room). Plus two new domains — **🤖 `pm-agentops`** (operate AI agents in production: `prompt-regression-suite`, `model-migration-plan`, `context-engineering-review`, `agent-incident-postmortem`, `agent-observability-spec`) and **⏰ `pm-autopilot`** (put recurring rituals on a schedule: `autopilot-charter`, `schedule-recipe`, `delta-briefing` + the recurring skills worth scheduling). New **`which-skill`** router: describe your task, get routed to the right skill — with a disambiguation table for the library's look-alike clusters. And the depth push has begun: 6 Production-Ready skills now ship `references/` + `templates/` (PRD, RICE, OKRs, teardown, postmortem, stakeholder update). *Earlier (v36.0):* `pm-security` + `pm-gov` bundles, Fable 5 in the playground, auto-generated `SKILLS.md`. **420 skills across 61 bundles.** → **[Full release history & notes](https://github.com/mohitagw15856/pm-claude-skills/releases)**.
 
 ### ▶ See it in action — [try the live Skill Playground](https://mohitagw15856.github.io/pm-claude-skills/)
 
@@ -89,7 +89,7 @@ A community-built library of professional skills for every field — product man
 | 🔭 [Competitor Teardown](skills/competitor-teardown) | "what are rivals up to?" | a positioning map, feature gaps & strategy |
 | 📝 [Meeting Notes](skills/meeting-notes) | a raw transcript | decisions, owners & next steps |
 
-→ Want proof first? See [**real sample outputs**](https://mohitagw15856.github.io/pm-claude-skills/examples.html) from each skill. Like what you see? [**Install in 2 minutes**](#-quick-install-2-minutes) · [browse all 411 skills](#️-all-411-skills) · [**⭐ star the repo**](https://github.com/mohitagw15856/pm-claude-skills/stargazers) so others find it.
+→ Want proof first? See [**real sample outputs**](https://mohitagw15856.github.io/pm-claude-skills/examples.html) from each skill. Like what you see? [**Install in 2 minutes**](#-quick-install-2-minutes) · [browse all 420 skills](#️-all-420-skills) · [**⭐ star the repo**](https://github.com/mohitagw15856/pm-claude-skills/stargazers) so others find it.
 
 ---
 
@@ -112,7 +112,7 @@ It's not just text — the playground exports every result as a **professionally
   </tr>
 </table>
 
-> Generate yours: run a skill in the [Playground](https://mohitagw15856.github.io/pm-claude-skills/), then **Download → PDF · Paper / Modern / Technical**. Add a `Brand color: #hex` line to your context and it tints to match (last tile). Personal documents live in the [`pm-personal`](#️-all-411-skills) bundle (résumé, cover letter, bio, LinkedIn, portfolio, one-pager).
+> Generate yours: run a skill in the [Playground](https://mohitagw15856.github.io/pm-claude-skills/), then **Download → PDF · Paper / Modern / Technical**. Add a `Brand color: #hex` line to your context and it tints to match (last tile). Personal documents live in the [`pm-personal`](#️-all-420-skills) bundle (résumé, cover letter, bio, LinkedIn, portfolio, one-pager).
 
 ---
 
@@ -121,11 +121,11 @@ It's not just text — the playground exports every result as a **professionally
 <details>
 <summary>Read more ↓</summary>
 
-The whole library on one page — install, all 411 skills by profession, the Professional Brain, the REST API, integrations, and quality tooling. Great to **print, share, or drop into a slide**.
+The whole library on one page — install, all 420 skills by profession, the Professional Brain, the REST API, integrations, and quality tooling. Great to **print, share, or drop into a slide**.
 
 <p align="center">
   <a href="CHEATSHEET.md">
-    <img src="web/docs-assets/cheatsheet.png" width="80%" alt="PM Skills one-page cheatsheet — 411 skills, the Professional Brain, REST API, integrations, and tooling at a glance." />
+    <img src="web/docs-assets/cheatsheet.png" width="80%" alt="PM Skills one-page cheatsheet — 420 skills, the Professional Brain, REST API, integrations, and tooling at a glance." />
   </a>
 </p>
 
@@ -156,7 +156,7 @@ Generic AI forgets everything between sessions, so you re-paste context forever
 <details>
 <summary>Read more ↓</summary>
 
-These 411 skills aren't a random catalog — they cover the **full arc of professional work**, end to end. Wherever you are in the loop, there's a skill for it:
+These 420 skills aren't a random catalog — they cover the **full arc of professional work**, end to end. Wherever you are in the loop, there's a skill for it:
 
 ```mermaid
 flowchart LR
@@ -175,7 +175,7 @@ flowchart LR
 | **📊 Measure** | Track outcomes & analyse | `metrics-framework` · `cohort-analysis` · `ab-test-planner` · `churn-analysis` |
 | **📣 Communicate** | Report up and out | `executive-update` · `board-deck-narrative` · `stakeholder-update` · `qbr-deck` |
 
-> New here? Start with the [**top-tier skills**](#️-skill-tiers--start-with-the-strongest), or jump straight to [**all 411 skills**](#️-all-411-skills) grouped by profession.
+> New here? Start with the [**top-tier skills**](#️-skill-tiers--start-with-the-strongest), or jump straight to [**all 420 skills**](#️-all-420-skills) grouped by profession.
 
 </details>
 
@@ -216,6 +216,18 @@ Individual skills are great. **Chaining** them is the superpower. A *recipe* run
 
 </details>
 
+## 🏛️ The Boardroom — your document vs. five AI executives
+
+Every tool above helps you **write** the document. [**The Boardroom**](https://mohitagw15856.github.io/pm-claude-skills/boardroom.html) is where you find out if it **survives a leadership team** — before the real one sees it.
+
+Paste a PRD, launch plan, investor pitch, or strategy memo. A bench of five AI executives — **💰 a CFO** who kills anything that can't show its maths, **🛠️ a CTO** who asks what breaks at 10×, **❤️ a Chief Customer Officer** channelling your angriest user, **⚖️ a General Counsel** who reads every superlative as a future lawsuit, and **🦈 a sceptical VC** who's seen 400 decks this year — debate it live in structured rounds:
+
+1. **Opening statements** — each executive's three sharpest points, severity-tagged `BLOCKER` / `RISK` / `QUESTION`
+2. **Cross-examination** — they argue with *each other*, concede points, and update positions
+3. **The verdict** — a neutral Chair weighs the arguments and issues a decision memo: ✅ approve / 🟡 conditions / 🔴 rework / ⛔ reject, risks ranked with owners, and **the 3–5 changes that would survive the room**
+
+Seat or excuse executives, set the grill level (🤝 constructive → 🔥 brutal), and download the decision memo. Runs entirely in your browser with your own key — same as the playground. **[Convene the board →](https://mohitagw15856.github.io/pm-claude-skills/boardroom.html)**
+
 ---
 
 ## 🧠 Skill Memory — set your context once, every skill uses it
@@ -298,7 +310,7 @@ Most skill repos are a folder of prompts. This one is a **system** — measured,
 
 | | **PM Skills** | Typical skill repo |
 |---|:---:|:---:|
-| Skills | **411**, across 25 professions | a handful → dozens, usually one domain |
+| Skills | **420**, across 25 professions | a handful → dozens, usually one domain |
 | Quality | **eval-scored** on a rubric + a public [benchmark](https://mohitagw15856.github.io/pm-claude-skills/benchmark.html) | trust the README |
 | Improves itself | ✅ eval → critique → rewrite (kept only if it scores higher) | ✗ |
 | Grounded in frameworks | ✅ each cites its source (RICE, JTBD, Pyramid Principle…) | rarely |
@@ -323,13 +335,13 @@ Most skill repos are a folder of prompts. This one is a **system** — measured,
 >
 > ⚠️ **You don't need `npm install pm-claude-skills`** — it's a CLI, not a library, so there's nothing to import. Use `npx pm-claude-skills …` (it always runs the latest). `npm install` just downloads it and does nothing on its own.
 
-**With the [`skills`](https://github.com/vercel-labs/skills) CLI** (the open agent-skills installer that works across Claude Code, Cursor, Codex, OpenCode & 60+ agents) — pick from all 411 interactively:
+**With the [`skills`](https://github.com/vercel-labs/skills) CLI** (the open agent-skills installer that works across Claude Code, Cursor, Codex, OpenCode & 60+ agents) — pick from all 420 interactively:
 
 ```bash
 npx skills add mohitagw15856/pm-claude-skills            # browse & pick (auto-detects your agent)
 npx skills add mohitagw15856/pm-claude-skills --list     # just preview the catalog
 npx skills add mohitagw15856/pm-claude-skills --skill prd-template   # grab one
-npx skills add mohitagw15856/pm-claude-skills --skill '*'            # install all 411
+npx skills add mohitagw15856/pm-claude-skills --skill '*'            # install all 420
 ```
 
 **Or our own installer** — via the [`pm-claude-skills`](https://www.npmjs.com/package/pm-claude-skills) npm package (Windows/macOS/Linux, needs Node), which also installs subagents, slash commands & cross-tool exports:
@@ -338,7 +350,7 @@ npx skills add mohitagw15856/pm-claude-skills --skill '*'            # install a
 npx pm-claude-skills add --agent claude     # or: codex · cursor · hermes · openclaw
 ```
 
-**Or one-line MCP** — make all 411 skills + 5 workflow recipes available in *every* session of any MCP client (Claude Code, Claude Desktop, Cursor, Windsurf), no per-file install:
+**Or one-line MCP** — make all 420 skills + 5 workflow recipes available in *every* session of any MCP client (Claude Code, Claude Desktop, Cursor, Windsurf), no per-file install:
 
 ```bash
 claude mcp add pm-skills -- npx -y pm-claude-skills-mcp
@@ -399,7 +411,7 @@ ln -s ~/pm-claude-skills/skills/* ~/.claude/skills/
 <details>
 <summary>Read more ↓</summary>
 
-The same 411 skills reach you through every channel — pick whatever fits your stack:
+The same 420 skills reach you through every channel — pick whatever fits your stack:
 
 | Channel | Get it |
 |---|---|
@@ -416,7 +428,7 @@ The same 411 skills reach you through every channel — pick whatever fits your
 | 🖥️ **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 |
 
-> **208 of 411 skills are eval-scored, averaging 4.8/5** — see the [leaderboard](https://mohitagw15856.github.io/pm-claude-skills/leaderboard.html).
+> **208 of 420 skills are eval-scored, averaging 4.8/5** — see the [leaderboard](https://mohitagw15856.github.io/pm-claude-skills/leaderboard.html).
 
 > 🧠 **Give your skills memory:** the [Professional Brain](BRAIN.md) is a local markdown folder skills read, write back to, and act on. It's a folder + one file to start — **[5-minute Quickstart](BRAIN_QUICKSTART.md)**.
 
@@ -438,7 +450,7 @@ There are two kinds of support. **Native `SKILL.md` agents** read the file as-is
 auto-discover skills from the `description` frontmatter. **Other tools** take the markdown
 body as a system prompt — for those we ship ready-made [exports](#ready-to-use-exports).
 
-**In your editor (VS Code / Cursor):** the [**`vscode-extension/`**](vscode-extension/) brings all 411 skills into the Command Palette — search and *insert a skill as context* for Copilot/Cursor chat, copy it, or open it in the Playground.
+**In your editor (VS Code / Cursor):** the [**`vscode-extension/`**](vscode-extension/) brings all 420 skills into the Command Palette — search and *insert a skill as context* for Copilot/Cursor chat, copy it, or open it in the Playground.
 
 | Platform | How it works | Auto-trigger? |
 |---|---|---|
@@ -600,7 +612,7 @@ ANTHROPIC_API_KEY=sk-ant-… npx pm-claude-skills generate --from ./team-process
 
 **🏆 Skill Leaderboard — [evals](evals/).** An LLM-as-judge harness scores each skill across Claude models on structure, completeness, usefulness, and grounding. **[View the leaderboard →](https://mohitagw15856.github.io/pm-claude-skills/leaderboard.html)**
 
-> **Score the *whole* library, cheaply.** `npm run eval:gen-cases` writes a representative input for **all 411 skills** (curated cases kept verbatim; the rest auto-generated), then `npm run eval:all` runs the full pass on Haiku for **~$2** total. The weakest scorers can then be auto-rewritten with **`npm run improve -- <skill>`** (`/improve`), which keeps a change only if the score goes up.
+> **Score the *whole* library, cheaply.** `npm run eval:gen-cases` writes a representative input for **all 420 skills** (curated cases kept verbatim; the rest auto-generated), then `npm run eval:all` runs the full pass on Haiku for **~$2** total. The weakest scorers can then be auto-rewritten with **`npm run improve -- <skill>`** (`/improve`), which keeps a change only if the score goes up.
 
 </details>
 
@@ -696,7 +708,7 @@ Not sure which plugin to install? Here's what each one covers:
 
 On May 5, 2026, Anthropic [released their first agent templates](https://www.anthropic.com/news/finance-agents) — pre-packaged Claude agents that combine **skills, connectors, and subagents** into ready-to-run workflows for financial services.
 
-This library is the largest open-source collection of professional skills available — covering 20 professions beyond financial services. **The 411 skills here are the building blocks for agent templates outside of finance.**
+This library is the largest open-source collection of professional skills available — covering 20 professions beyond financial services. **The 420 skills here are the building blocks for agent templates outside of finance.**
 
 ### What is an agent template?
 
@@ -776,7 +788,7 @@ More templates will follow. If you want to contribute one, see the [template con
 <details>
 <summary>Read more ↓</summary>
 
-**Latest: v32.0.0 — 4 new bundles, 24 skills (E-commerce, UX Writing, Recruiting, Accounting).** 411 skills across 59 bundles, 25 professions. Every tagged release has complete notes on the **[Releases page](https://github.com/mohitagw15856/pm-claude-skills/releases)**.
+**Latest: v37.0.0 — The Boardroom, AgentOps & Autopilot bundles + the `which-skill` router.** 420 skills across 61 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)**.
 
@@ -824,7 +836,7 @@ This repo was built alongside a published 16-part article series on Medium.
 <details>
 <summary>Read more ↓</summary>
 
-A 411-skill library doesn't have 411 equally-mature skills, and pretending otherwise
+A 420-skill library doesn't have 420 equally-mature skills, and pretending otherwise
 wastes your time. Skills are tiered honestly so you can start with the best work:
 
 - 🟢 **Production-Ready (50)** — battle-tested, stable output, used in real work. Includes the three skills with computed Python helpers (sprint planning, RICE, customer health). **Start here.**
@@ -839,7 +851,7 @@ If you're new, install `pm-essentials` and try a couple of Production-Ready skil
 
 ---
 
-## 🗂️ All 411 Skills
+## 🗂️ All 420 Skills
 
 <details>
 <summary>Read more ↓</summary>
@@ -887,7 +899,7 @@ Every skill, grouped by profession. **[Browse the full per-skill catalog → SKI
 <details>
 <summary>Read more ↓</summary>
 
-Building and maintaining 411 skills across 59 bundles takes real time — testing skills against new model releases, building new ones from community requests, writing the article series, and keeping documentation current.
+Building and maintaining 420 skills across 61 bundles takes real time — testing skills against new model releases, building new ones from community requests, writing the article series, and keeping documentation current.
 
 If these skills save you time at work — or you're a company that wants your logo in front of the PMs, engineers, and operators who use them daily — **[become a sponsor →](https://github.com/sponsors/mohitagw15856)** (or [☕ buy me a coffee](https://www.buymeacoffee.com/mohit15856)).
 
@@ -919,7 +931,7 @@ pull request**, and once it's merged you earn a badge to show off in your own re
 ```
 
 Community listings live in their authors' own repos and are **community-maintained — not
-eval-scored or security-audited** (that's the [curated library](#️-all-411-skills) above). Want
+eval-scored or security-audited** (that's the [curated library](#️-all-420-skills) above). Want
 your skill *in* the curated library instead? See **Contributing** below.
 
 ---
@@ -1149,7 +1161,7 @@ Stars unlock the next wave of skills and features. We've hit every milestone so
 | 1,000 ⭐ | Startup Founder kit — *delivered, and then some: the Founders **and** Educators bundles + a browser extension for ChatGPT/Claude.ai/Gemini* | ✅ Shipped (v24.0.0) |
 | **2,000 ⭐** | 2 community-voted profession bundles + the browser & VS Code extensions published to their stores | 🔓 **Current goal** |
 | 3,500 ⭐ | Community **skill packs** (curated role/industry bundles) + internationalised skill descriptions | 🔒 Locked |
-| 5,000 ⭐ | Public **contributor leaderboard** + the push to 411 skills | 🔒 Locked |
+| 5,000 ⭐ | Public **contributor leaderboard** + the push to 420 skills | 🔒 Locked |
 
 **[⭐ Star this repo to unlock the next milestone →](https://github.com/mohitagw15856/pm-claude-skills)** — we're at **2,000⭐** next.
 

package/exports/README.md

@@ -8,7 +8,7 @@ by hand; edit the source skill and run:
 node scripts/build-exports.mjs
 ```
 
-Currently exporting **411 skills** to:
+Currently exporting **420 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.
 
-411 skills exported. Copy a `.mdc rule` into the tool to use it.
+420 skills exported. Copy a `.mdc rule` into the tool to use it.
 
 | Skill | Bundle | Path |
 |---|---|---|
@@ -16,6 +16,8 @@
 | Ad Copy | `pm-copy` | `pm-copy/ad-copy/ad-copy.md` |
 | AEO Optimizer | `pm-writers` | `pm-writers/aeo-optimizer/aeo-optimizer.md` |
 | Agent Design Review | `pm-ai` | `pm-ai/agent-design-review/agent-design-review.md` |
+| Agent Incident Postmortem | `pm-agentops` | `pm-agentops/agent-incident-postmortem/agent-incident-postmortem.md` |
+| Agent Observability Spec | `pm-agentops` | `pm-agentops/agent-observability-spec/agent-observability-spec.md` |
 | Agent Spec | `pm-ai` | `pm-ai/agent-spec/agent-spec.md` |
 | AI Ethics Review | `pm-advanced` | `pm-advanced/ai-ethics-review/ai-ethics-review.md` |
 | AI Eval Plan | `pm-ai` | `pm-ai/ai-eval-plan/ai-eval-plan.md` |
@@ -31,6 +33,7 @@
 | Architecture Decision Record (ADR) | `pm-engineering` | `pm-engineering/architecture-decision-record/architecture-decision-record.md` |
 | Architecture Diagram | `pm-visuals` | `pm-visuals/architecture-diagram/architecture-diagram.md` |
 | Assumption Mapper | `pm-discovery` | `pm-discovery/assumption-mapper/assumption-mapper.md` |
+| Autopilot Charter | `pm-autopilot` | `pm-autopilot/autopilot-charter/autopilot-charter.md` |
 | Board Deck Narrative | `pm-business` | `pm-business/board-deck-narrative/board-deck-narrative.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` |
@@ -85,6 +88,7 @@
 | Content Calendar | `pm-gtm` | `pm-gtm/content-calendar/content-calendar.md` |
 | Content Repurposer | `pm-creator` | `pm-creator/content-repurposer/content-repurposer.md` |
 | Content Style Guide | `pm-uxwriting` | `pm-uxwriting/content-style-guide/content-style-guide.md` |
+| Context Engineering Review | `pm-agentops` | `pm-agentops/context-engineering-review/context-engineering-review.md` |
 | Context Mode | `pm-engineering` | `pm-engineering/context-mode/context-mode.md` |
 | Contract Review | `pm-legal` | `pm-legal/contract-review/contract-review.md` |
 | Contributor Guide | `pm-devrel` | `pm-devrel/contributor-guide/contributor-guide.md` |
@@ -113,6 +117,7 @@
 | Debt Payoff Plan | `pm-money` | `pm-money/debt-payoff-plan/debt-payoff-plan.md` |
 | Debugging Log Analyser | `pm-engineering` | `pm-engineering/debugging-log-analyser/debugging-log-analyser.md` |
 | Decision Memo | `pm-business` | `pm-business/decision-memo/decision-memo.md` |
+| Delta Briefing | `pm-autopilot` | `pm-autopilot/delta-briefing/delta-briefing.md` |
 | Demand Letter | `pm-legal` | `pm-legal/demand-letter/demand-letter.md` |
 | Dependency Audit | `pm-engineering` | `pm-engineering/dependency-audit/dependency-audit.md` |
 | Dependency Conflict Resolver | `pm-engineering` | `pm-engineering/dependency-conflict-resolver/dependency-conflict-resolver.md` |
@@ -237,6 +242,7 @@
 | Microservices Decomposition | `pm-engineering` | `pm-engineering/microservices-decomposition/microservices-decomposition.md` |
 | Mind Map | `pm-visuals` | `pm-visuals/mind-map/mind-map.md` |
 | Model Card | `pm-ai` | `pm-ai/model-card/model-card.md` |
+| Model Migration Plan | `pm-agentops` | `pm-agentops/model-migration-plan/model-migration-plan.md` |
 | Model Selection Advisor | `pm-ai` | `pm-ai/model-selection-advisor/model-selection-advisor.md` |
 | Monitoring Setup Guide | `pm-engineering` | `pm-engineering/monitoring-setup-guide/monitoring-setup-guide.md` |
 | Morning Intelligence | `pm-operations` | `pm-operations/morning-intelligence/morning-intelligence.md` |
@@ -293,6 +299,7 @@
 | Promotion Packet | `pm-career` | `pm-career/promotion-packet/promotion-packet.md` |
 | Promotion Plan | `pm-ecommerce` | `pm-ecommerce/promotion-plan/promotion-plan.md` |
 | Prompt Optimizer | `pm-ai` | `pm-ai/prompt-optimizer/prompt-optimizer.md` |
+| Prompt Regression Suite | `pm-agentops` | `pm-agentops/prompt-regression-suite/prompt-regression-suite.md` |
 | Property Investment Analysis | `pm-realestate` | `pm-realestate/property-investment-analysis/property-investment-analysis.md` |
 | Property Listing | `pm-realestate` | `pm-realestate/property-listing/property-listing.md` |
 | Property Offer Letter | `pm-realestate` | `pm-realestate/property-offer-letter/property-offer-letter.md` |
@@ -348,6 +355,7 @@
 | Sales Page | `pm-copy` | `pm-copy/sales-page/sales-page.md` |
 | Savings Goal Plan | `pm-money` | `pm-money/savings-goal-plan/savings-goal-plan.md` |
 | Saying No | `pm-comms` | `pm-comms/saying-no/saying-no.md` |
+| Schedule Recipe | `pm-autopilot` | `pm-autopilot/schedule-recipe/schedule-recipe.md` |
 | Schema Markup | `pm-growth` | `pm-growth/schema-markup/schema-markup.md` |
 | Security Incident Response | `pm-security` | `pm-security/security-incident-response/security-incident-response.md` |
 | Security Review | `pm-security` | `pm-security/security-review/security-review.md` |
@@ -413,6 +421,7 @@
 | Viral Content Framework | `pm-social` | `pm-social/viral-content-framework/viral-content-framework.md` |
 | Voice of Customer Program | `pm-pmm` | `pm-pmm/voice-of-customer-program/voice-of-customer-program.md` |
 | Vulnerability Triage | `pm-security` | `pm-security/vuln-triage/vuln-triage.md` |
+| Which Skill Router | `pm-essentials` | `pm-essentials/which-skill/which-skill.md` |
 | Win/Loss Analysis | `pm-pmm` | `pm-pmm/win-loss-analysis/win-loss-analysis.md` |
 | Word Document | `pm-documents` | `pm-documents/word-document/word-document.md` |
 | Workshop Facilitation Guide | `pm-operations` | `pm-operations/workshop-facilitation-guide/workshop-facilitation-guide.md` |

package/exports/aider/pm-agentops/agent-incident-postmortem/agent-incident-postmortem.md

@@ -0,0 +1,85 @@
+# Agent Incident Postmortem Skill
+
+AI incidents differ from outages: the system didn't go down — it did something wrong, confidently, and maybe only once. This skill adapts blameless postmortem practice to nondeterministic systems, where "can we reproduce it?" needs traces, not just steps.
+
+## What This Skill Produces
+
+- A **blameless postmortem document** with timeline and user/business impact
+- A **trace reconstruction** of what the agent saw, decided, and did
+- A **root-cause analysis across the AI failure layers** (not "the model hallucinated" as a conclusion)
+- **Corrective actions** — always including a new permanent case in the regression suite
+
+## Required Inputs
+
+Ask for (if not already provided):
+- **What the agent did** and what it should have done
+- **The trace** — the full request: system prompt, context, tool calls and results, output. If no trace exists, that absence is itself a finding
+- **Blast radius** — how many users/requests, over what window, and whether it's ongoing
+- **Detection** — how it was noticed (user report? monitor? luck?) and how long after it started
+
+## Root-Cause Layers
+
+Walk the layers in order; the root cause is usually the *earliest* layer that could have prevented the outcome. "The model was wrong" is a starting point, never the conclusion — models are known to be fallible, so the question is what let a fallible output become an incident.
+
+| Layer | Ask |
+|---|---|
+| **Input / context** | Was the context wrong, stale, contradictory, or poisoned (injection)? Did retrieval feed it bad ground truth? |
+| **Model behaviour** | Given that context, was the output a foreseeable failure mode (fabrication under missing data, over-compliance with injected text)? |
+| **Guardrails** | What check should have caught this output and didn't exist / didn't fire? (schema validation, groundedness check, action allow-list) |
+| **Action layer** | Why could the wrong output become a real action or reach a user without the appropriate gate for its risk level? |
+| **Detection** | Why did we learn about it this way, this late? What signal would have caught it in minutes? |
+
+## Nondeterminism Discipline
+
+- **Reproduce with the trace, not the anecdote:** replay the exact context; then re-run N times to measure frequency — a 1-in-20 failure at 10k requests/day is 500 incidents/day.
+- **Pin everything when replaying:** model version, prompt version, temperature, tool results.
+- **If it can't be reproduced:** say so, keep the trace as the evidence, and treat frequency as unknown — not as "rare".
+
+## Output Format
+
+### AI Incident Postmortem: [title] — [date]
+
+**Severity:** [level] · **Status:** [resolved/monitoring] · **Owner:** [name]
+
+**Summary:** [3 sentences: what the agent did, impact, root cause layer]
+
+**Impact:** [users/requests affected, window, cost, trust/regulatory dimension]
+
+**Timeline:** [first bad output → detection → mitigation → resolution, with the detection gap called out]
+
+**Trace reconstruction:** [what was in the window; which tool calls ran; where the path diverged from intended behaviour]
+
+**Root cause by layer:**
+| Layer | Finding |
+|---|---|
+| Input/context | |
+| Model behaviour | |
+| Guardrails | |
+| Action layer | |
+| Detection | |
+
+**Reproduction:** [replayed? failure frequency over N runs / not reproducible — evidence is the trace]
+
+**Corrective actions:**
+| Action | Layer | Owner | Due |
+|---|---|---|---|
+| Add this trace as a permanent regression case | eval | | |
+| [guardrail/monitor/context fix] | | | |
+
+**What went well / what got lucky:** [both, honestly]
+
+## Quality Checks
+
+- [ ] The postmortem is blameless toward humans *and* useful about the system — "prompt engineer error" and "model hallucinated" are both banned conclusions
+- [ ] Root cause identifies the earliest layer that could have prevented impact, not just the layer that misbehaved
+- [ ] The trace (or its absence) is in the document; findings cite it
+- [ ] Failure frequency was measured or explicitly marked unknown
+- [ ] Corrective actions include the permanent regression case and at least one detection improvement
+
+## Anti-Patterns
+
+- [ ] Do not close with "improved the prompt" as the only action — the same class of output must also be caught by a guardrail or gate next time
+- [ ] Do not assess frequency from one replay — nondeterministic failures hide at low temperatures and reappear at scale
+- [ ] Do not skip the injection question when any untrusted text (web, user docs, tickets) was in the window
+- [ ] Do not let "the model will be better next version" close an action item — upgrades are migrations (see model-migration-plan), not fixes
+- [ ] Do not write it as an outage report — the system was up; the failure was behavioural, and the doc must analyse behaviour

package/exports/aider/pm-agentops/agent-observability-spec/agent-observability-spec.md

@@ -0,0 +1,85 @@
+# Agent Observability Spec Skill
+
+You can't fix what you didn't record. For LLM systems the unit of observability is the *trace* — everything the model saw and did — because behaviour, not uptime, is what fails. This skill specifies what to capture, what to compute from it, and when to page someone.
+
+## What This Skill Produces
+
+- A **trace schema**: per-request spans and the fields each must carry
+- **Metric definitions** across health, quality, cost, and behaviour — each with a threshold and owner
+- A **sampling and retention policy** that keeps cost sane and debugging possible
+- A **privacy note**: what logged content contains, who can see it, and how long it lives
+
+## Required Inputs
+
+Ask for (if not already provided):
+- **The system's shape** — single LLM call, RAG pipeline, or multi-step tool-using agent
+- **Traffic volume and cost sensitivity** — full tracing at 10M req/day is a budget decision
+- **What "misbehaving" means here** — the two or three failure modes that matter most (wrong facts? wrong actions? cost? refusals?)
+- **Existing observability stack** (Datadog, Langfuse, OTel, homegrown) — spec into it, not around it
+
+## Trace Schema
+
+Every request produces one trace; every model call, retrieval, guardrail check, and tool execution is a span. Minimum fields:
+
+| Span | Must capture |
+|---|---|
+| **Request root** | request id, user/session (pseudonymous), feature + prompt version, model id, total tokens, total cost, latency, terminal status |
+| **Model call** | full input context (or content-addressed ref), output, finish reason, tokens in/out, cached-token share, temperature |
+| **Retrieval** | query, top-k ids + scores, which chunks entered the context |
+| **Tool call** | tool name, arguments, result (or ref), duration, error |
+| **Guardrail** | check name, verdict, and *what it did* (blocked / rewrote / flagged) |
+| **User signal** | edits, regenerates, thumbs, abandonment — joined to the trace id |
+
+The test of the schema: **an engineer can replay any incident from its trace alone** (see `agent-incident-postmortem`).
+
+## Metrics and Alerts
+
+Define four families; every metric gets a threshold, a window, and an owner.
+
+- **Health** — error rate, p50/p95 latency, timeout rate, provider 429/5xx rate. *Page* on these.
+- **Cost** — cost per request (p50, p99), tokens per request, cache hit rate, daily spend vs. budget (pair with `llm-cost-latency-budget`). *Alert* on p99 and daily-budget burn — cost incidents are caused by the tail, not the mean.
+- **Quality proxies** — format/schema violation rate, refusal rate, groundedness-check failure rate, judge score on a sampled slice, regenerate/edit rate. *Alert on drift* vs. a rolling baseline: absolute thresholds go stale, deltas don't.
+- **Behaviour (agents)** — steps per task, tool-error rate, loop detection (same tool + same args N times), unauthorised-action attempts caught by guardrails. *Page* on the last one.
+
+## Sampling & Retention
+
+- **Metadata for 100%** of requests (ids, versions, tokens, cost, status) — this is cheap and non-negotiable.
+- **Full content traces:** 100% for errors, guardrail hits, and negative user signals; [1-10]% random sample for the rest, adjusted to volume.
+- **Retention:** full content [30-90] days, metadata [12+] months for trend baselines; incident traces pinned indefinitely.
+- **Privacy:** logged context contains user data — state where it lives, who has access, how deletion requests reach it, and that traces are scrubbed or access-gated before wide sharing.
+
+## Output Format
+
+### Observability Spec: [feature/agent]
+
+**System shape:** [calls/pipeline/agent] · **Volume:** [req/day] · **Stack:** [tooling]
+
+**Trace schema:** [the span table, tailored]
+
+**Metrics:**
+| Metric | Family | Threshold / baseline | Window | Alert → owner |
+|---|---|---|---|---|
+
+**Sampling & retention:** [the policy]
+
+**Privacy:** [content classification, access, deletion path]
+
+**Dashboards:** [the 2-3 views: live health, quality drift, cost]
+
+**First incident drill:** pick yesterday's worst trace and confirm it can be replayed end-to-end from the stored data.
+
+## Quality Checks
+
+- [ ] Any incident is replayable from its trace alone — the schema was tested against that bar
+- [ ] Every metric has a number, a window, and a named owner — no orphan dashboards
+- [ ] Quality alerts are drift-based against a rolling baseline, not absolute guesses
+- [ ] Sampling keeps 100% of error/guardrail/negative-signal traces
+- [ ] The privacy note exists and names retention and access — logged prompts are user data
+
+## Anti-Patterns
+
+- [ ] Do not log only inputs and outputs — without retrieval and tool spans, root cause analysis is guesswork
+- [ ] Do not alert on mean cost or mean latency — the tail is where both incidents live
+- [ ] Do not run judge-based quality scoring on 100% of traffic — sample; spend the budget on better baselines
+- [ ] Do not treat observability as launch-week scaffolding — drift metrics only work with months of baseline
+- [ ] Do not ship an agent that can take actions without logging the guardrail verdicts alongside the actions

package/exports/aider/pm-agentops/context-engineering-review/context-engineering-review.md

@@ -0,0 +1,72 @@
+# Context Engineering Review Skill
+
+Most agent failures aren't model failures — they're context failures: instructions buried under retrieval dumps, stale history contradicting fresh facts, twelve tool definitions the task never needed. This skill audits the *assembled window*, not just the prompt text.
+
+## What This Skill Produces
+
+- A **context inventory**: every component in the window, its size, and who put it there
+- A **keep / cut / restructure verdict** per component, with the reasoning
+- **Ordering and cache-alignment fixes** (stable prefix first, volatile content last)
+- A **token budget** per component with an enforcement point
+
+## Required Inputs
+
+Ask for (if not already provided):
+- **A real assembled context** — an actual logged request (system prompt + messages + tools), not the template. If only the template exists, review that but flag that dynamic bloat is invisible
+- **The failure or goal** — ignoring instructions? too expensive? inconsistent? slow?
+- **What varies per request** (retrieval, history, user data) vs. what is static
+- **The model and its context limit**, and current typical request size
+
+## Review Method
+
+**1. Inventory.** List every component in window order: system prompt sections, tool definitions, retrieved documents, conversation history, few-shot examples, injected state. For each: token count (estimate if unlogged), static vs. dynamic, and owner.
+
+**2. Interrogate each component:**
+- **Earning its tokens?** Would removing it change outputs on real traffic? The honest test is ablation, not intuition.
+- **Right form?** Raw dumps (full HTML, whole files, unabridged history) almost always beat down to summaries, excerpts, or references the agent can expand via a tool.
+- **Right position?** Instructions that must win go in the system prompt; volatile data goes late; nothing critical hides in the middle of a long window.
+- **Fighting anything?** Contradictions between sections (persona says terse, examples are verbose; old history asserts what retrieval now refutes) are the classic "ignores instructions" root cause.
+
+**3. Check the structural patterns:**
+- **Cache alignment** — a byte-stable prefix (system prompt, tools) with per-request content after it; anything dynamic *inside* the prefix (timestamps, user names) breaks caching every request.
+- **Tool sprawl** — tools the task can't need this turn dilute selection accuracy; load narrow toolsets per task or defer rarely-used schemas.
+- **History policy** — unbounded transcripts are the top silent cost driver; define truncation/summarisation and what must survive it.
+- **Retrieval discipline** — cap chunks by relevance score, not by k; label each chunk's source so the model can weigh it.
+
+**4. Budget.** Assign each component a token ceiling that sums comfortably under the limit at p95, and name where it's enforced (the assembly code, not hope).
+
+## Output Format
+
+### Context Engineering Review: [feature/agent]
+
+**Reviewed:** [a real request from date / the template]. **Current size:** [n] tokens typical, [n] p95, limit [n].
+
+| # | Component | Tokens | Static? | Verdict | Fix |
+|---|---|---|---|---|---|
+| 1 | [system: persona] | | ✓ | Keep | — |
+| 2 | [12 tool defs] | | ✓ | Restructure | [narrow per task] |
+| 3 | [retrieval, k=20] | | dyn | Cut to k≤8 by score | |
+
+**Conflicts found:** [each contradiction and which side should win]
+
+**Ordering / caching:** [the reordered layout; what moves out of the stable prefix]
+
+**Token budget:** [component → ceiling; enforcement point]. Projected size: [n] (−[x]%).
+
+**Verify:** re-run [the eval suite / golden cases] after changes — cuts must be validated, not assumed safe (see `prompt-regression-suite`).
+
+## Quality Checks
+
+- [ ] The review used at least one real assembled request, or explicitly flags it could not
+- [ ] Every verdict has a reason tied to the stated failure/goal, not generic advice
+- [ ] Cache-breaking dynamic content in the stable prefix is called out with its cost
+- [ ] The token budget sums under the model limit at p95 including output headroom
+- [ ] Recommended cuts come with a validation step before they ship
+
+## Anti-Patterns
+
+- [ ] Do not review the prompt template and call it a context review — the bloat lives in the dynamic parts
+- [ ] Do not recommend "shorten everything" — cutting the wrong 200 tokens costs more than keeping 2,000 idle ones
+- [ ] Do not leave contradictions in place because each section "is fine alone" — the window is read as one document
+- [ ] Do not treat more retrieval as more grounding — irrelevant chunks actively mislead
+- [ ] Do not propose structure the assembly code can't enforce — a budget without an enforcement point is a wish