pm-claude-skills 40.0.0 → 41.0.0

package/README.md

@@ -1,4 +1,4 @@
-# 🧠 PM Skills — 426 Professional Agent Skills for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes
+# 🧠 PM Skills — 441 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-426-blue)](https://github.com/mohitagw15856/pm-claude-skills)
+[![Skills](https://img.shields.io/badge/skills-441-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-21-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=426+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=441+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.**
-> 426 professional skills + 4 agent templates across 62 bundles covering 25 professions. Built for Claude Code — and now portable to ChatGPT, Gemini, and Hermes Agent. Built by a PM, used by everyone.
+> 441 professional skills + 4 agent templates across 64 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).
 
-**🆕 v40.0.0 — [The Firm](https://mohitagw15856.github.io/pm-claude-skills/firm.html):** charter a standing AI staff who file delta-aware memos, hold board sessions without you, and log falsifiable predictions you can score — performance-review your AI staff. *Earlier, 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. **426 skills · 62 bundles · 25 professions.** → [CHANGELOG](CHANGELOG.md) · [all releases](https://github.com/mohitagw15856/pm-claude-skills/releases).
+**🆕 v41.0.0 — 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. **441 skills · 64 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/)
 
@@ -81,8 +81,8 @@ In Claude Code, [`/firm`](commands/firm.md) runs the same session natively — g
 
 <table>
   <tr>
-    <td width="50%"><a href="https://mohitagw15856.github.io/pm-claude-skills/firm.html"><img src="web/docs-assets/showcase/firm-org.png" alt="The Firm — your charter and staff cards, each with a live calibration record" /></a><br /><sub>Your staff — each card shows their beat, the skill their duty runs on, and their live calibration record.</sub></td>
-    <td width="50%"><a href="https://mohitagw15856.github.io/pm-claude-skills/firm.html"><img src="web/docs-assets/showcase/firm.png" alt="Board minutes from a session the staff held without you — decisions table, dissent preserved, and the prediction ledger" /></a><br /><sub>The minutes from a session they held without you — decisions with asks, dissent preserved, predictions awaiting reality.</sub></td>
+    <td width="50%"><a href="https://mohitagw15856.github.io/pm-claude-skills/firm.html"><img src="web/docs-assets/showcase/firm-org.png" alt="The Firm — a real chartered firm: six staff hired, each card showing their beat and the skill their duty runs on" /></a><br /><sub>A real chartered firm (unretouched session) — six staff hired, each card showing their beat and the library skill their duty runs on.</sub></td>
+    <td width="50%"><a href="https://mohitagw15856.github.io/pm-claude-skills/firm.html"><img src="web/docs-assets/showcase/firm.png" alt="Real board minutes from session 1 — the staff debate two stalled enterprise deals vs rising churn, with five falsifiable predictions in the ledger" /></a><br /><sub>The actual session-1 minutes — the staff met without their principal, argued sequencing vs churn, and logged five falsifiable predictions now awaiting reality.</sub></td>
   </tr>
 </table>
 
@@ -114,7 +114,7 @@ In Claude Code, [`/firm`](commands/firm.md) runs the same session natively — g
   <tr>
     <td width="50%">
       <a href="https://mohitagw15856.github.io/pm-claude-skills/"><img src="web/docs-assets/showcase/cmdbar.png" alt="The command bar — describe your task in plain words and get matched to the right skill instantly" /></a>
-      <b>🪄 <a href="https://mohitagw15856.github.io/pm-claude-skills/">The command bar</a></b> — don't browse 426 cards; just say it: <i>"a blameless postmortem for Friday's outage"</i> → the top three skills, instantly, locally, before you've even entered a key. Enter opens the best match.
+      <b>🪄 <a href="https://mohitagw15856.github.io/pm-claude-skills/">The command bar</a></b> — don't browse 441 cards; just say it: <i>"a blameless postmortem for Friday's outage"</i> → the top three skills, instantly, locally, before you've even entered a key. Enter opens the best match.
     </td>
     <td width="50%">
       <a href="https://mohitagw15856.github.io/pm-claude-skills/galaxy.html"><img src="web/docs-assets/showcase/galaxy.png" alt="Skill Galaxy — the library as a living star map with a guided sky tour" /></a>
@@ -141,7 +141,7 @@ In Claude Code, [`/firm`](commands/firm.md) runs the same session natively — g
 | 🔭 [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 426 skills](#️-all-426-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 441 skills](#️-all-441-skills) · [**⭐ star the repo**](https://github.com/mohitagw15856/pm-claude-skills/stargazers) so others find it.
 
 ---
 
@@ -164,7 +164,7 @@ 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-426-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-441-skills) bundle (résumé, cover letter, bio, LinkedIn, portfolio, one-pager).
 
 ---
 
@@ -173,11 +173,11 @@ 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 426 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 441 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 — 426 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 — 441 skills, the Professional Brain, REST API, integrations, and tooling at a glance." />
   </a>
 </p>
 
@@ -208,7 +208,7 @@ Generic AI forgets everything between sessions, so you re-paste context forever
 <details>
 <summary>Read more ↓</summary>
 
-These 426 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 441 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
@@ -227,7 +227,7 @@ 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 426 skills**](#️-all-426-skills) grouped by profession.
+> New here? Start with the [**top-tier skills**](#️-skill-tiers--start-with-the-strongest), or jump straight to [**all 441 skills**](#️-all-441-skills) grouped by profession.
 
 </details>
 
@@ -393,7 +393,7 @@ Most skill repos are a folder of prompts. This one is a **system** — measured,
 
 | | **PM Skills** | Typical skill repo |
 |---|:---:|:---:|
-| Skills | **426**, across 25 professions | a handful → dozens, usually one domain |
+| Skills | **441**, 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 |
@@ -418,13 +418,13 @@ 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 426 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 441 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 426
+npx skills add mohitagw15856/pm-claude-skills --skill '*'            # install all 441
 ```
 
 **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:
@@ -433,7 +433,7 @@ 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 426 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 441 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
@@ -494,7 +494,7 @@ ln -s ~/pm-claude-skills/skills/* ~/.claude/skills/
 <details>
 <summary>Read more ↓</summary>
 
-The same 426 skills reach you through every channel — pick whatever fits your stack:
+The same 441 skills reach you through every channel — pick whatever fits your stack:
 
 | Channel | Get it |
 |---|---|
@@ -511,7 +511,7 @@ The same 426 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 426 skills are eval-scored, averaging 4.8/5** — see the [leaderboard](https://mohitagw15856.github.io/pm-claude-skills/leaderboard.html).
+> **208 of 441 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)**.
 
@@ -533,7 +533,7 @@ 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 426 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 441 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? |
 |---|---|---|
@@ -695,7 +695,7 @@ 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 426 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 441 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>
 
@@ -791,7 +791,7 @@ 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 426 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 441 skills here are the building blocks for agent templates outside of finance.**
 
 ### What is an agent template?
 
@@ -871,7 +871,7 @@ More templates will follow. If you want to contribute one, see the [template con
 <details>
 <summary>Read more ↓</summary>
 
-**Latest: v40.0.0 — [The Firm](https://mohitagw15856.github.io/pm-claude-skills/firm.html)** (employ a standing AI staff) · *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. 426 skills across 62 bundles, 25 professions. Every tagged release has complete notes on the **[Releases page](https://github.com/mohitagw15856/pm-claude-skills/releases)**.
+**Latest: v41.0.0 — the modern skills wave:** [`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. 441 skills across 64 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)**.
 
@@ -919,7 +919,7 @@ This repo was built alongside a published 16-part article series on Medium.
 <details>
 <summary>Read more ↓</summary>
 
-A 426-skill library doesn't have 426 equally-mature skills, and pretending otherwise
+A 441-skill library doesn't have 441 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.**
@@ -934,7 +934,7 @@ If you're new, install `pm-essentials` and try a couple of Production-Ready skil
 
 ---
 
-## 🗂️ All 426 Skills
+## 🗂️ All 441 Skills
 
 <details>
 <summary>Read more ↓</summary>
@@ -982,7 +982,7 @@ Every skill, grouped by profession. **[Browse the full per-skill catalog → SKI
 <details>
 <summary>Read more ↓</summary>
 
-Building and maintaining 426 skills across 62 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 441 skills across 64 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)).
 
@@ -1014,7 +1014,7 @@ 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-426-skills) above). Want
+eval-scored or security-audited** (that's the [curated library](#️-all-441-skills) above). Want
 your skill *in* the curated library instead? See **Contributing** below.
 
 ---
@@ -1244,7 +1244,7 @@ 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 426 skills | 🔒 Locked |
+| 5,000 ⭐ | Public **contributor leaderboard** + the push to 441 skills | 🔒 Locked |
 
 **[⭐ Star this repo to unlock the next milestone →](https://github.com/mohitagw15856/pm-claude-skills)** — we're at **2,000⭐** next.
 

package/commands/firm.md

@@ -18,4 +18,6 @@ You are the **chief of staff** running a session of the user's standing Firm —
 3. **Hold the board session.** Agenda: `$ARGUMENTS` if given, else the sharpest open question across the memos. Let the staff genuinely disagree where their beats conflict. Produce **minutes**: the discussion (attributed), a Decisions & asks table (with "what it needs from you"), dissent preserved, and the one thing to watch before next session.
 4. **Close the loop.** Save the minutes to `firm-minutes/session-<n>-<date>.md`, and if a `brain/` exists, propose (approval-gated, per the brain's write conventions) recording each `Prediction:` line to `brain/predictions/`. Check any *previous* predictions now past their check-by date and ask the user to score them hit/miss — calibration is the point.
 
+5. **Deliver, if connected.** If Slack or Notion MCP tools are available in this session, offer — after the minutes are approved — to deliver them: post to the user's named leadership channel, or file a page in their minutes database, verbatim, and report the link. Never deliver without the offer being accepted this session ([mcp-pairings](../connectors/mcp-pairings.md)).
+
 Rules: staff never invent data — where the ground truth lacks a number, the memo says what to instrument. Minutes ≤400 words. Dissent is preserved, never averaged away.

package/connectors/README.md

@@ -67,6 +67,7 @@ connector:
 | **n8n** | skills as nodes in any automation (MCP Client or HTTP Request) | [`n8n.md`](n8n.md) |
 | **Lovable** | build skill-powered web apps; make its generator skill-aware | [`lovable.md`](lovable.md) |
 | **Obsidian** | skills as vault notes / AI-plugin prompts; the vault as project state | [`obsidian.md`](obsidian.md) |
+| **MCP pairings** 🆕 | skills that *act*: notes file themselves in Notion, updates post to Slack, plans build the sprint — approval-gated per SkillSpec §5 | [`mcp-pairings.md`](mcp-pairings.md) |
 
 > **REST API** — `GET /v1/skills`, `/v1/skills/{name}` (`?format=md`), `/v1/search?q=`,
 > `/v1/workflows` on `https://pm-skills-mcp.pm-claude-skills.workers.dev`. Same catalogue as

package/connectors/mcp-pairings.md

@@ -0,0 +1,39 @@
+# 🔌 MCP pairings — skills that *act*, not just answer
+
+A skill produces the artifact; a connected **MCP server** delivers it where work actually lives. In Claude Code (or any MCP host), pairing the two turns input→output skills into end-to-end workflows: *meeting notes that file themselves in Notion, stakeholder updates that post to Slack, postmortem action items that become tracker tickets.*
+
+The safety pattern is always the same, and it's the one [SkillSpec §5](../SKILLSPEC.md) formalises:
+
+```
+skill produces the artifact  →  human approves it VERBATIM  →  MCP tool delivers it  →  verify + report the link
+```
+
+The skill never gains network access; the *agent* uses tools it already has, inside the skill's Execution gates.
+
+## The pairing table
+
+| Skill | Pairs with (MCP) | The end-to-end workflow |
+|---|---|---|
+| [`meeting-notes`](../skills/meeting-notes/SKILL.md) | Notion · Linear/Jira | Transcript → structured notes filed as a Notion page; each action item becomes a tracker issue with its owner |
+| [`stakeholder-update`](../skills/stakeholder-update/SKILL.md) | Slack · Gmail | The approved update posts to the exact channel/recipients — its Execution block already specifies the gates |
+| [`incident-postmortem`](../skills/incident-postmortem/SKILL.md) | GitHub/Linear · Slack | Postmortem drafted → action items filed as issues with owners/due dates (via [`action-runner`](../skills/action-runner/SKILL.md)) → doc linked in the incident channel |
+| [`sprint-planning`](../skills/sprint-planning/SKILL.md) | Linear/Jira | The approved plan *builds the sprint*: container created, items moved, points set — its Execution block is the worked example |
+| [`/firm`](../commands/firm.md) | Slack · Notion | Board minutes delivered to your leadership channel / minutes database after each session |
+| [`pm-weekly-review`](../skills/pm-weekly-review/SKILL.md) | Google Calendar · Gmail | The week's calendar becomes review input; the review's commitments become calendar blocks |
+| [`competitive-intelligence-monitor`](../skills/competitive-intelligence-monitor/SKILL.md) | Slack | The weekly delta brief posts itself to `#competitive` — pair with [`schedule-recipe`](../skills/schedule-recipe/SKILL.md) for the cadence |
+| [`renewal-playbook`](../skills/renewal-playbook/SKILL.md) | Salesforce/HubSpot MCPs | Account context pulled live instead of pasted; the save plan's tasks written back |
+
+## Wiring it (Claude Code)
+
+1. Connect the servers you use: `claude mcp add …` (Notion, Slack, Linear, GitHub and hundreds more speak MCP).
+2. Install the skills (`npx pm-claude-skills add --agent claude`).
+3. Ask for the outcome, not the steps: *"take this transcript, file the notes in Notion and create the action items in Linear."* The agent runs the skill, shows you the artifact, and — only after your yes — delivers through the MCP tools.
+
+Skills with a formal `## Execution` block (`sprint-planning`, `stakeholder-update`, `meeting-notes`) make the boundaries explicit: a **closed allow-list** of actions, human approval on anything outward-facing, verification afterwards, and a rollback path. For skills without one, the same discipline applies by convention — the artifact is approved before anything leaves the session.
+
+## House rules
+
+- **Approval precedes delivery, always.** An MCP pairing never auto-sends; "the user said post it last week" does not carry over.
+- **Verbatim means verbatim.** What was approved is what ships — no silent edits between approval and delivery.
+- **Verify and link back.** After delivery, fetch the created page/issue/message and report its URL; a claimed delivery without a link didn't happen.
+- **Least tools.** Load only the MCP servers a workflow needs; a skill that files Notion pages has no business seeing your email.

package/exports/README.md

@@ -8,7 +8,7 @@ by hand; edit the source skill and run:
 node scripts/build-exports.mjs
 ```
 
-Currently exporting **426 skills** to:
+Currently exporting **441 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.
 
-426 skills exported. Copy a `.mdc rule` into the tool to use it.
+441 skills exported. Copy a `.mdc rule` into the tool to use it.
 
 | Skill | Bundle | Path |
 |---|---|---|
@@ -16,13 +16,20 @@
 | 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 Era Pricing | `pm-agentnative` | `pm-agentnative/agent-era-pricing/agent-era-pricing.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 Readiness Audit | `pm-agentnative` | `pm-agentnative/agent-readiness-audit/agent-readiness-audit.md` |
 | Agent Spec | `pm-ai` | `pm-ai/agent-spec/agent-spec.md` |
+| AI-Assisted Performance Review | `pm-aiwork` | `pm-aiwork/ai-assisted-performance-review/ai-assisted-performance-review.md` |
+| AI Code Review | `pm-engineering` | `pm-engineering/ai-code-review/ai-code-review.md` |
+| AI Content Audit | `pm-aiwork` | `pm-aiwork/ai-content-audit/ai-content-audit.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` |
 | AI Feature PRD | `pm-ai` | `pm-ai/ai-feature-prd/ai-feature-prd.md` |
 | AI Product Canvas | `pm-advanced` | `pm-advanced/ai-product-canvas/ai-product-canvas.md` |
+| AI ROI Audit | `pm-aiwork` | `pm-aiwork/ai-roi-audit/ai-roi-audit.md` |
+| AI Usage Policy | `pm-aiwork` | `pm-aiwork/ai-usage-policy/ai-usage-policy.md` |
 | Ambiguity Resolver | `pm-strategy` | `pm-strategy/ambiguity-resolver/ambiguity-resolver.md` |
 | Analyst Relations Brief | `pm-pmm` | `pm-pmm/analyst-relations-brief/analyst-relations-brief.md` |
 | Announcement Card | `pm-visuals` | `pm-visuals/announcement-card/announcement-card.md` |
@@ -33,6 +40,7 @@
 | 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` |
+| Async Decision Memo | `pm-operations` | `pm-operations/async-decision-memo/async-decision-memo.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` |
@@ -40,6 +48,7 @@
 | Bookkeeping Categorization | `pm-accounting` | `pm-accounting/bookkeeping-categorization/bookkeeping-categorization.md` |
 | Boolean Search Builder | `pm-recruiting` | `pm-recruiting/boolean-search-builder/boolean-search-builder.md` |
 | Brag Doc | `pm-career` | `pm-career/brag-doc/brag-doc.md` |
+| Brand Impersonation Response | `pm-crisis` | `pm-crisis/brand-impersonation-response/brand-impersonation-response.md` |
 | Brief Builder | `pm-cross` | `pm-cross/brief-builder/brief-builder.md` |
 | Briefing Note | `pm-gov` | `pm-gov/briefing-note/briefing-note.md` |
 | Budget Builder | `pm-money` | `pm-money/budget-builder/budget-builder.md` |
@@ -160,6 +169,7 @@
 | Exploratory Test Charter | `pm-qa` | `pm-qa/exploratory-test-charter/exploratory-test-charter.md` |
 | Feature Flag Guide | `pm-engineering` | `pm-engineering/feature-flag-guide/feature-flag-guide.md` |
 | Feature Prioritisation | `pm-planning` | `pm-planning/feature-prioritisation/feature-prioritisation.md` |
+| Feature Sunset Plan | `pm-planning` | `pm-planning/feature-sunset-plan/feature-sunset-plan.md` |
 | Figma Annotation Guide | `pm-figma` | `pm-figma/figma-annotation-guide/figma-annotation-guide.md` |
 | Figma Component Audit | `pm-figma` | `pm-figma/figma-component-audit/figma-component-audit.md` |
 | Figma Design Brief | `pm-figma` | `pm-figma/figma-design-brief/figma-design-brief.md` |
@@ -192,6 +202,7 @@
 | HIPAA Safeguards | `pm-compliance` | `pm-compliance/hipaa-safeguards/hipaa-safeguards.md` |
 | Hiring Rubric | `pm-people` | `pm-people/hiring-rubric/hiring-rubric.md` |
 | Hook Writer | `pm-creator` | `pm-creator/hook-writer/hook-writer.md` |
+| Human-in-the-Loop Design | `pm-agentnative` | `pm-agentnative/human-in-the-loop-design/human-in-the-loop-design.md` |
 | i18n Readiness Review | `pm-localization` | `pm-localization/i18n-readiness-review/i18n-readiness-review.md` |
 | IEP Goal Support | `pm-education` | `pm-education/iep-goal-support/iep-goal-support.md` |
 | Impact Report | `pm-nonprofit` | `pm-nonprofit/impact-report/impact-report.md` |
@@ -234,6 +245,7 @@
 | Marketing Funnel Plan | `pm-growth` | `pm-growth/marketing-funnel-plan/marketing-funnel-plan.md` |
 | Marketing Psychology | `pm-growth` | `pm-growth/marketing-psychology/marketing-psychology.md` |
 | Marketplace Listing Optimizer | `pm-ecommerce` | `pm-ecommerce/marketplace-listing-optimizer/marketplace-listing-optimizer.md` |
+| MCP Server Spec | `pm-agentnative` | `pm-agentnative/mcp-server-spec/mcp-server-spec.md` |
 | Media Pitch | `pm-gtm` | `pm-gtm/media-pitch/media-pitch.md` |
 | Meeting Notes | `pm-essentials` | `pm-essentials/meeting-notes/meeting-notes.md` |
 | Messaging Framework | `pm-growth` | `pm-growth/messaging-framework/messaging-framework.md` |
@@ -345,6 +357,7 @@
 | Roadmap Narrative | `pm-planning` | `pm-planning/roadmap-narrative/roadmap-narrative.md` |
 | Roadmap Presentation | `pm-planning` | `pm-planning/roadmap-presentation/roadmap-presentation.md` |
 | ROI Estimator | `pm-calculators` | `pm-calculators/roi-estimator/roi-estimator.md` |
+| Role Redesign For AI | `pm-aiwork` | `pm-aiwork/role-redesign-for-ai/role-redesign-for-ai.md` |
 | Rubric Builder | `pm-education` | `pm-education/rubric-builder/rubric-builder.md` |
 | Runbook Writer | `pm-engineering` | `pm-engineering/runbook-writer/runbook-writer.md` |
 | Runway Calculator | `pm-calculators` | `pm-calculators/runway-calculator/runway-calculator.md` |
@@ -398,6 +411,7 @@
 | Support Macro | `pm-support` | `pm-support/support-macro/support-macro.md` |
 | Support Runbook | `pm-support` | `pm-support/support-runbook/support-runbook.md` |
 | 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` |
 | 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` |
@@ -424,6 +438,7 @@
 | Vendor Evaluation | `pm-operations` | `pm-operations/vendor-evaluation/vendor-evaluation.md` |
 | Vendor Security Review | `pm-compliance` | `pm-compliance/vendor-security-review/vendor-security-review.md` |
 | Viral Content Framework | `pm-social` | `pm-social/viral-content-framework/viral-content-framework.md` |
+| Voice Agent Design | `pm-agentnative` | `pm-agentnative/voice-agent-design/voice-agent-design.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` |

package/exports/aider/pm-agentnative/agent-era-pricing/agent-era-pricing.md

@@ -0,0 +1,65 @@
+# Agent Era Pricing Skill
+
+Seat pricing quietly assumed the user was a human who logs in. Agents break the assumption from both sides: your customers need fewer seats (one operator, ten agents), and your product gets *more* usage than ever. This skill redesigns the model around a value metric that survives non-human users — without torching existing revenue on the way.
+
+## What This Skill Produces
+
+- A **value-metric decision**: what you charge for when seats stop proxying value
+- **Agent-tier design**: how agent/API usage is packaged, fenced, and priced
+- **Cannibalisation math**: what happens to current revenue under the new model, computed on real cohorts
+- A **phased migration plan** for existing customers, with the grandfathering decision made explicitly
+
+## Required Inputs
+
+Ask for (if not already provided):
+- **Current model**: plans, price points, seat definitions, current API/automation pricing if any
+- **The evidence of pressure**: seat contraction, API traffic growth, customer asks, competitor moves
+- **Unit economics**: cost to serve a seat vs an API call/agent action (rough is fine, labelled)
+- **3-5 representative customer profiles** with seat counts and usage (the cannibalisation test set)
+
+## Method
+
+1. **Find the value metric that survives agents.** Test candidates against three questions: does it scale with the value the *customer* receives (not your costs)? · is it counted identically whether a human or agent drives it? · can the customer predict their bill? Strong candidates are usually *outcomes or work-objects* (invoices processed, tickets resolved, campaigns run, records enriched) — not raw API calls (unpredictable, punishes retries) and not seats (dying assumption).
+2. **Price the human and the agent differently, deliberately.** The durable pattern is a hybrid: a **platform/human layer** (flat or few-seats — access, admin, support) plus a **work layer** priced on the value metric, agnostic to who did the work. Decide where agents authenticate: agent traffic on a user's token counted as that user's work, not as a "seat".
+3. **Design the fences.** What separates tiers now that seats don't: volume bands on the value metric, rate/concurrency limits, SSO/audit/compliance (still human-org fences), model/automation quality tiers. Every fence must be *measurable* and *hard to game* — name the gaming vector for each and why it's acceptable.
+4. **Run the cannibalisation math on real cohorts.** For each customer profile: current annual price vs new-model price at current usage, at 2× automation, at 5×. Sum to a revenue bridge. If the new model loses money on your best cohort, the metric or the bands are wrong — fix the model, don't hide the row.
+5. **Phase the migration.** New customers first (cleanest signal) → opt-in for existing (with a calculator showing their number) → forced migration only with long notice and a cap ("no more than X% increase in year one"). Grandfathering is a *decision with a cost*, not a default: state what perpetual legacy plans cost in five years.
+6. **Set the tripwires.** Which metrics reprice this model: value-metric inflation/deflation, gaming detected, agent share of traffic crossing thresholds. Pricing in the agent era is a program, not a project.
+
+## Output Format
+
+### Agent-Era Pricing Plan: [product]
+
+**Diagnosis:** [the seat-erosion evidence, quantified]
+**Value metric:** [chosen metric] — because [the three-question test, answered]. Rejected: [runner-up + why].
+
+**The model**
+| Layer | What's included | Priced on | Tiers/bands |
+|---|---|---|---|
+| Platform (humans) | | | |
+| Work (human or agent) | | | |
+
+**Fences:** [fence → what it separates → gaming vector → why acceptable]
+
+**Cannibalisation bridge**
+| Cohort | Today | New @ current usage | New @ 2× automation | Δ |
+|---|---|---|---|---|
+
+**Migration:** [phase → who → when → the cap/grandfather decision, stated]
+**Tripwires:** [metric → threshold → action]
+
+## Quality Checks
+
+- [ ] The value metric passes all three tests (customer value · human/agent-agnostic · predictable)
+- [ ] Cannibalisation is computed on the provided cohorts, not asserted — assumptions labelled
+- [ ] Every fence names its gaming vector
+- [ ] The migration includes an explicit grandfathering decision with its long-run cost
+- [ ] Agent authentication/attribution is specified — whose usage is whose bill
+
+## Anti-Patterns
+
+- [ ] Do not price raw API calls as the value metric — unpredictable bills punish exactly the automation you want to encourage
+- [ ] Do not bolt an "agent seat" onto seat pricing — an agent is not a discount human; the assumption is what broke
+- [ ] Do not present only the happy cohort — the bridge shows the losers or it isn't math
+- [ ] Do not force-migrate loyal customers without a year-one cap — churn from pricing anger costs more than the uplift
+- [ ] Do not skip tripwires — a static price in a shifting usage regime is a slow leak in one direction or the other

package/exports/aider/pm-agentnative/agent-readiness-audit/agent-readiness-audit.md

@@ -0,0 +1,74 @@
+# Agent Readiness Audit Skill
+
+A growing share of your product's users aren't human: agents research it, evaluate it, onboard onto it, and operate it on their principals' behalf. They can't watch your demo video, guess what an unlabeled icon means, or call support. This skill audits every surface an agent touches and scores how much of your product is invisible or unusable to them.
+
+## What This Skill Produces
+
+- A **readiness score by surface** (discovery, docs, API/auth, errors, onboarding, transactions)
+- **Per-surface findings** with the failing artifact quoted and the fix
+- A **prioritised fix list** ranked by agent-traffic impact vs effort
+- A **re-test protocol** so readiness is measured, not vibed
+
+## Required Inputs
+
+Ask for (if not already provided):
+- **The product** and its public surfaces (site, docs URL, API reference, status page)
+- **What agents will be asked to do** with it — research/compare? sign up? operate it daily?
+- **What exists already**: llms.txt? MCP server? OpenAPI spec? If unknown, the audit checks
+- **Any observed agent failures** (the best audit seed there is)
+
+## The Audit Surfaces
+
+Walk each surface asking one question: *could a capable agent, starting cold, complete its job here without a human unblocking it?*
+
+**1. Discovery — can agents find and understand what you are?**
+`llms.txt` present and current · docs fetchable as clean markdown/text (not JS-rendered walls) · pricing and limits stated in prose an agent can quote · comparison-relevant facts (SOC 2, SSO, data residency) written down anywhere at all — an agent can't infer what you never wrote.
+
+**2. Docs — written for readers who execute?**
+Every task documented as copy-runnable steps with expected outputs · code samples that actually run (agents execute them verbatim) · one canonical way per task (agents can't arbitrate between three contradictory tutorials) · error-message strings from the product appearing verbatim in the docs so search-by-error works.
+
+**3. API & auth — self-serve without a human?**
+Key/token obtainable without a sales call (or the agent path is documented honestly) · OpenAPI spec accurate to the deployed API · rate limits discoverable programmatically · an MCP server, or at least a stated position on one.
+
+**4. Errors — instructive to a retrying machine?**
+Errors name the field and the fix · machine-readable codes stable across releases · 4xx vs 5xx used honestly (agents branch on this) · no CAPTCHAs on API-adjacent flows without a documented alternative.
+
+**5. Onboarding & transactions — can an agent complete them?**
+Signup/checkout completable without image CAPTCHAs, drag-widgets, or SMS-only verification (or agent-appropriate alternatives exist) · forms with real labels, not placeholder-only · the confirmation state readable as text.
+
+**6. Guardrails — do you *know* your agent traffic?**
+Are agents distinguishable in analytics? Is there a stated policy (terms + technical) for agent use — welcome, gated, or forbidden? Silence is a decision made by accident.
+
+Score each surface 0-4: 0 = actively hostile · 2 = humans-only assumptions throughout · 4 = agent-native. Cite the failing artifact for anything below 3.
+
+## Output Format
+
+### Agent Readiness Audit: [product] — [n]/24
+
+| Surface | Score /4 | Sharpest finding |
+|---|---|---|
+
+**Findings** *(per surface, worst first)*
+**[surface] — [score]**: [what fails, with the artifact quoted] → **Fix:** [specific change]
+
+**Fix list, prioritised:**
+| # | Fix | Surface | Impact | Effort |
+|---|---|---|---|---|
+
+**Re-test protocol:** [5-8 cold-start agent tasks ("sign up and send one API request", "find whether SSO is on the cheap plan") — run them with a real agent after fixes; the score is the pass rate, not the checklist]
+
+## Quality Checks
+
+- [ ] Every score below 3 cites the actual failing artifact (URL, error string, form field), not a vibe
+- [ ] Fixes are specific changes, not "improve the docs"
+- [ ] The audit distinguishes *unwritten* facts (agent can't know) from *buried* facts (agent might find)
+- [ ] The fix list is ranked by agent-traffic impact, and states assumptions where traffic is unmeasured
+- [ ] The re-test protocol exists — readiness is a pass rate, not an opinion
+
+## Anti-Patterns
+
+- [ ] Do not audit from memory of the product — fetch the actual surfaces; they've changed
+- [ ] Do not treat "we have great docs" as evidence — great-for-humans routinely scores 1/4 for agents
+- [ ] Do not recommend blocking agents as a fix unless the business genuinely wants that — then say it in terms *and* technically, consistently
+- [ ] Do not conflate this with SEO/AEO — being quotable is surface 1; being *usable* is the other five
+- [ ] Do not skip the guardrails surface — unmeasured agent traffic is how products discover this problem in an outage