pm-claude-skills 28.0.0 → 28.2.0

package/README.md

@@ -4,42 +4,48 @@
   </a>
 </p>
 
-# 🧠 PM Skills — 205 Professional Agent Skills for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes
-
-<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=205+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>
-
-> **Generic AI gives you filler. These give you the structure a senior pro actually uses** — PRDs, exec updates, launch plans, postmortems — as open-source `SKILL.md` files. Across **21 professions**, not just product management. One source, every AI tool.
+# 🧠 PM Skills — 206 Professional Agent Skills for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes
 
 [![Stars](https://img.shields.io/github/stars/mohitagw15856/pm-claude-skills?style=social)](https://github.com/mohitagw15856/pm-claude-skills/stargazers)
 [![npm](https://img.shields.io/npm/v/pm-claude-skills?logo=npm&color=cb3837)](https://www.npmjs.com/package/pm-claude-skills)
+[![npm downloads](https://img.shields.io/npm/dm/pm-claude-skills?logo=npm&color=cb3837&label=installs)](https://www.npmjs.com/package/pm-claude-skills)
 [![PyPI](https://img.shields.io/pypi/v/pm-skills?logo=pypi&logoColor=white&color=3775A9&label=pip)](https://pypi.org/project/pm-skills/)
+[![PyPI downloads](https://img.shields.io/pypi/dm/pm-skills?logo=pypi&logoColor=white&color=3775A9&label=pip%20installs)](https://pypi.org/project/pm-skills/)
 [![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/)
-[![Skills](https://img.shields.io/badge/skills-205-blue)](https://github.com/mohitagw15856/pm-claude-skills)
+[![Smithery](https://smithery.ai/badge/mohit15856/pm-skills)](https://smithery.ai/servers/mohit15856/pm-skills)
+[![Skills](https://img.shields.io/badge/skills-206-blue)](https://github.com/mohitagw15856/pm-claude-skills)
 [![eval](https://img.shields.io/badge/eval--scored-196%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-6-blueviolet)](commands/)
 [![Personas](https://img.shields.io/badge/personas-4-blueviolet)](output-styles/)
 [![Platforms](https://img.shields.io/badge/works%20with-Claude%20%7C%20ChatGPT%20%7C%20Gemini%20%7C%20Cursor%20%7C%20Codex%20%7C%20Hermes-8A2BE2)](#-works-with--cross-tool-compatibility)
+[![Integrations](https://img.shields.io/badge/integrates%20with-n8n%20%C2%B7%20Lovable%20%C2%B7%20Obsidian-0E9F6E)](connectors/)
 [![SkillCheck](https://img.shields.io/github/actions/workflow/status/mohitagw15856/pm-claude-skills/skillcheck.yml?branch=main&label=SkillCheck)](.github/workflows/skillcheck.yml)
 [![Security Audit](https://img.shields.io/github/actions/workflow/status/mohitagw15856/pm-claude-skills/skill-audit.yml?branch=main&label=security%20audit)](.github/workflows/skill-audit.yml)
-[![Version](https://img.shields.io/badge/version-23.0.0-brightgreen)](https://github.com/mohitagw15856/pm-claude-skills/releases)
+[![Version](https://img.shields.io/github/v/release/mohitagw15856/pm-claude-skills?label=version&color=brightgreen)](https://github.com/mohitagw15856/pm-claude-skills/releases)
 [![Install](https://img.shields.io/badge/Install%20in%20Claude%20Code-2%20minutes-orange)](https://github.com/mohitagw15856/pm-claude-skills#-quick-install-2-minutes)
 [![License](https://img.shields.io/badge/license-MIT-lightgrey)](LICENSE)
 [![Sponsor](https://img.shields.io/badge/sponsor-❤️-ff69b4)](https://github.com/sponsors/mohitagw15856)
 
+<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=206+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>
+
+> **Generic AI gives you filler. These give you the structure a senior pro actually uses** — PRDs, exec updates, launch plans, postmortems — as open-source `SKILL.md` files. Across **21 professions**, not just product management. One source, every AI tool.
+
+> **🆕 Now plugs into your stack** — automate skills in **[n8n](connectors/n8n.md)**, build apps on **[Lovable](connectors/lovable.md)**, and run them in your **[Obsidian](connectors/obsidian.md)** vault, all via a read-only **[REST API](mcp-remote/#rest-api-for-n8n-lovable-make-any-http-tool)** on the hosted Worker.
+
 ### ⭐ If this saves you time, [star the repo](https://github.com/mohitagw15856/pm-claude-skills) — it's the #1 way to help others find it.
 
 > **PM stands for Professional, not just Product Management.**
-> 205 professional skills + 4 agent templates across 28 bundles covering 21 professions. Built for Claude Code — and now portable to ChatGPT, Gemini, and Hermes Agent. Built by a PM, used by everyone.
+> 206 professional skills + 4 agent templates across 28 bundles covering 21 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 release (v28.0.0 — live across the whole AI ecosystem):** every channel is now shipped & public — **[`pip install pm-skills`](https://pypi.org/project/pm-skills/)** (LangChain/CrewAI), the **hosted MCP connector** `https://pm-skills-mcp.pm-claude-skills.workers.dev/` (add to **ChatGPT/Claude.ai/Cursor** by URL), and the **[official MCP registry](https://github.com/mohitagw15856/pm-claude-skills/blob/main/server.json)** listing. See the new **[🌍 Use It Anywhere](#-use-it-anywhere--the-ai-ecosystem)** section. Also: **multi-model playground** (run any skill with your own **Claude / OpenAI / Gemini / Ollama** key — local models included), a **[remote MCP connector](mcp-remote/)** (add PM Skills to **ChatGPT, Claude.ai & Cursor** with one URL — no install), the MCP server now exposes skills as **prompts + resources**, **4 new IDE targets** (Cline, Continue, Zed, Roo — 9 platforms total), a **[Python package](python/)** (`pip install pm-skills` → LangChain/CrewAI tools), an **[`llms.txt`](https://mohitagw15856.github.io/pm-claude-skills/llms.txt)** for agent discovery, a reusable **[score-skills GitHub Action](.github/actions/score-skills/)**, and **MCP-registry manifests**. Plus the full library is now **eval-scored: 196 skills, avg 4.8/5**. **205 skills**. See the [changelog](#-changelog).
+**🆕 Latest release (v28.1.0 — Integrations):** PM Skills now plugs into **[n8n](connectors/n8n.md)**, powers **[Lovable](connectors/lovable.md)** apps, and lives in your **[Obsidian](connectors/obsidian.md)** vault — all backed by a read-only **REST API** (`/v1`) on the hosted Worker, auto-deployed via GitHub Actions. *Previously (v28.0.0 — live across the whole AI ecosystem):* every channel is now shipped & public — **[`pip install pm-skills`](https://pypi.org/project/pm-skills/)** (LangChain/CrewAI), the **hosted MCP connector** `https://pm-skills-mcp.pm-claude-skills.workers.dev/` (add to **ChatGPT/Claude.ai/Cursor** by URL), and the **[official MCP registry](https://github.com/mohitagw15856/pm-claude-skills/blob/main/server.json)** listing. See the new **[🌍 Use It Anywhere](#-use-it-anywhere--the-ai-ecosystem)** section. Also: **multi-model playground** (run any skill with your own **Claude / OpenAI / Gemini / Ollama** key — local models included), a **[remote MCP connector](mcp-remote/)** (add PM Skills to **ChatGPT, Claude.ai & Cursor** with one URL — no install), the MCP server now exposes skills as **prompts + resources**, **4 new IDE targets** (Cline, Continue, Zed, Roo — 9 platforms total), a **[Python package](python/)** (`pip install pm-skills` → LangChain/CrewAI tools), an **[`llms.txt`](https://mohitagw15856.github.io/pm-claude-skills/llms.txt)** for agent discovery, a reusable **[score-skills GitHub Action](.github/actions/score-skills/)**, and **MCP-registry manifests**. Plus the full library is now **eval-scored: 196 skills, avg 4.8/5**. **206 skills**. See the [changelog](#-changelog).
 
 ### ▶ See it in action — [try the live Skill Playground](https://mohitagw15856.github.io/pm-claude-skills/)
 
@@ -68,13 +74,13 @@ 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 205 skills](#️-all-205-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 206 skills](#️-all-206-skills) · [**⭐ star the repo**](https://github.com/mohitagw15856/pm-claude-skills/stargazers) so others find it.
 
 ---
 
 ## 🔄 One library, the whole professional workflow
 
-These 205 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 206 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
@@ -93,7 +99,7 @@ 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 205 skills**](#️-all-205-skills) grouped by profession.
+> New here? Start with the [**top-tier skills**](#️-skill-tiers--start-with-the-strongest), or jump straight to [**all 206 skills**](#️-all-206-skills) grouped by profession.
 
 ---
 
@@ -189,7 +195,7 @@ Most skill repos are a folder of prompts. This one is a **system** — measured,
 
 | | **PM Skills** | Typical skill repo |
 |---|:---:|:---:|
-| Skills | **205**, across 21 professions | a handful → dozens, usually one domain |
+| Skills | **206**, across 21 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 |
@@ -214,7 +220,7 @@ Most skill repos are a folder of prompts. This one is a **system** — measured,
 - [📦 Plugin Directory](#-plugin-directory)
 - [🤖 Building Blocks for Agent Templates](#-building-blocks-for-agent-templates)
 - [🏷️ Skill Tiers — start with the strongest](#️-skill-tiers--start-with-the-strongest)
-- [🗂️ All 205 Skills](#️-all-205-skills)
+- [🗂️ All 206 Skills](#️-all-206-skills)
 - [📋 Changelog](#-changelog)
 - [🤝 Contributing](#-contributing--add-your-skill)
 - [🔗 Related Projects](#-related-projects)
@@ -223,13 +229,13 @@ Most skill repos are a folder of prompts. This one is a **system** — measured,
 
 ## 🚀 Quick Install (2 minutes)
 
-**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 205 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 206 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 205
+npx skills add mohitagw15856/pm-claude-skills --skill '*'            # install all 206
 ```
 
 **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:
@@ -238,7 +244,7 @@ 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 205 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 206 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
@@ -295,7 +301,7 @@ ln -s ~/pm-claude-skills/skills/* ~/.claude/skills/
 
 ## 🌍 Use It Anywhere — the AI Ecosystem
 
-The same 205 skills reach you through every channel — pick whatever fits your stack:
+The same 206 skills reach you through every channel — pick whatever fits your stack:
 
 | Channel | Get it |
 |---|---|
@@ -304,12 +310,12 @@ The same 205 skills reach you through every channel — pick whatever fits your
 | 🔌 **`skills` CLI** | `npx skills add mohitagw15856/pm-claude-skills` (works across 60+ agents) |
 | 🐍 **Python / PyPI** | `pip install pm-skills` → `search_skills` / `get_skill` + **LangChain & CrewAI** tools |
 | 🧠 **MCP (local)** | `npx -y pm-claude-skills-mcp` — tools, **prompts & resources**. Listed in the [official MCP registry](https://github.com/mohitagw15856/pm-claude-skills/blob/main/server.json). |
-| ⚡ **MCP (hosted)** | Add **`https://pm-skills-mcp.pm-claude-skills.workers.dev/`** as a connector URL in **ChatGPT, Claude.ai, or Cursor** — no install. ([build your own](mcp-remote/)) |
+| ⚡ **MCP (hosted)** | Add **`https://pm-skills-mcp.pm-claude-skills.workers.dev/`** as a connector URL in **ChatGPT, Claude.ai, or Cursor** — no install. Also on **[Smithery](https://smithery.ai/servers/mohit15856/pm-skills)**. ([build your own](mcp-remote/)) |
 | 🧩 **Browser extension** | A skill picker inside ChatGPT, Claude.ai & Gemini — [`extension/`](extension/) |
 | 🖥️ **IDE rules** | Generated exports for **Cursor, Windsurf, Aider, Cline, Continue, Zed, Roo** — [`exports/`](exports/) |
 | 🤖 **Agents & answer engines** | [`llms.txt`](https://mohitagw15856.github.io/pm-claude-skills/llms.txt) makes the whole library discoverable & citable |
 
-> **196 of 205 skills are eval-scored, averaging 4.8/5** — see the [leaderboard](https://mohitagw15856.github.io/pm-claude-skills/leaderboard.html).
+> **196 of 206 skills are eval-scored, averaging 4.8/5** — see the [leaderboard](https://mohitagw15856.github.io/pm-claude-skills/leaderboard.html).
 
 ---
 
@@ -324,7 +330,7 @@ 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 205 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 206 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? |
 |---|---|---|
@@ -338,6 +344,7 @@ body as a system prompt — for those we ship ready-made [exports](#ready-to-use
 | **Python agents** (LangChain, CrewAI, LlamaIndex) | [`pip install pm-skills`](python/) → `search_skills` / `get_skill` / ready-made tool adapters. | ✅ On demand |
 | **Run on your own key** (Claude / OpenAI / Gemini / Ollama) | The [Playground](https://mohitagw15856.github.io/pm-claude-skills/) runs any skill live — pick a provider, paste a key (or point at local Ollama). | ▶ In browser |
 | **ChatGPT & Gemini (copy-paste)** | Copy a ready-made [export](#ready-to-use-exports) into a Custom GPT or Gem's instructions. | ❌ Paste per use |
+| **Claude.ai & Claude API** | Upload a skill, or paste the body in as a system prompt / project instruction. | ⚙️ Manual |
 | **Any agent / answer engine** | [`llms.txt`](https://mohitagw15856.github.io/pm-claude-skills/llms.txt) makes the whole library discoverable & citable. | ✅ On demand |
 
 **What's verified vs. what varies:** the skill **bodies** — the frameworks, rubrics, and
@@ -468,7 +475,7 @@ 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 205 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 206 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.
 
 ---
 
@@ -504,7 +511,7 @@ Not sure which plugin to install? Here's what each one covers:
 | **pm-advanced** | ai-ethics-review, ai-product-canvas, experiment-designer, design-handoff-brief, multi-source-signal-synthesiser | For PMs working on AI products or running sophisticated experiments. Covers ethical review of AI features, AI-native product canvases, and experiment design. |
 | **pm-analytics** | data-analysis-standard, product-health-analysis, retention-analysis | Turn raw data into PM-ready narratives. Use when you need to frame an analysis, explain health metrics to leadership, or diagnose retention drop-offs. |
 | **pm-business** | board-deck-narrative, investor-update, job-application | For PMs operating at the business layer — writing board narratives, investor updates, or crafting a standout job application. |
-| **pm-cross** | executive-summary, grant-proposal, last-30-days-research, notebooklm-connector, press-release, sycophancy-challenger, teaching-lesson-plan | Cross-profession utility skills that work outside a single domain — writing executive summaries, press releases, running research, and challenging sycophantic AI output. |
+| **pm-cross** | executive-summary, grant-proposal, last-30-days-research, notebooklm-connector, press-release, professional-brain, sycophancy-challenger, teaching-lesson-plan | Cross-profession utility skills that work outside a single domain — writing executive summaries, press releases, running research, and challenging sycophantic AI output, and giving the skills a durable memory with professional-brain. |
 | **pm-cs** | churn-analysis, cs-escalation-brief, cs-health-scorecard, customer-success-plan, qbr-deck, renewal-playbook | For PMs or CSMs responsible for retention. Covers churn diagnosis, escalation briefs, QBR decks, health scorecards, and renewal plays. |
 | **pm-data** | chart-data-extractor, cohort-analysis, dashboard-brief, data-pipeline-spec, metrics-framework, sql-query-explainer | Data-heavy work: extracting insights from charts, building metrics frameworks, explaining SQL queries, designing dashboards, and speccing data pipelines. |
 | **pm-delivery** | ab-test-planner, go-to-market-planner, pptx-slide-auditor, product-launch-checklist, retro-analysis, sprint-brief, sprint-planning, technical-spec-template, user-story-writer | Everything you need to ship: sprint planning, user stories, launch checklists, A/B test design, retros, and PowerPoint auditing. The most-used plugin for day-to-day delivery. |
@@ -544,7 +551,7 @@ 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 205 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 206 skills here are the building blocks for agent templates outside of finance.**
 
 ### What is an agent template?
 
@@ -623,11 +630,11 @@ More templates will follow. If you want to contribute one, see the [template con
 
 ## 📋 Changelog
 
-**Latest: v28.0.0 — live across the whole AI ecosystem.** Now public on every channel: **PyPI** (`pip install pm-skills`), a **hosted MCP connector** URL for ChatGPT/Claude.ai/Cursor, and the **official MCP registry** — plus a new **🌍 Use It Anywhere** section + PyPI/MCP header badges. Builds on the v27 ecosystem work: multi-model playground (Claude / OpenAI / Gemini / **Ollama**); a **remote MCP connector** ([`mcp-remote/`](mcp-remote/)) to add PM Skills to **ChatGPT, Claude.ai & Cursor** by URL; MCP server now serves skills as **prompts + resources**; **4 new IDE export targets** (Cline, Continue, Zed, Roo → 9 platforms); a **Python package** ([`python/`](python/), `pip install pm-skills` with LangChain/CrewAI adapters); an **`llms.txt`** for agent discovery; a reusable **[score-skills Action](.github/actions/score-skills/)**; and **MCP-registry manifests** (`server.json`, `smithery.yaml`). The full library is now eval-scored — **196 skills, avg 4.8/5**. Builds on **v26.0.0** (the Creator stack). **205 skills** across **28 bundles**, **21 professions**.
+**Latest: v28.1.0 — Integrations (n8n, Lovable, Obsidian) + a `/v1` REST API.** PM Skills now runs inside [n8n](connectors/n8n.md), powers [Lovable](connectors/lovable.md) apps, and lives in your [Obsidian](connectors/obsidian.md) vault — all backed by a read-only REST API on the hosted Worker (auto-deployed via a new GitHub Action). Builds on **v28.0.0 — live across the whole AI ecosystem.** Now public on every channel: **PyPI** (`pip install pm-skills`), a **hosted MCP connector** URL for ChatGPT/Claude.ai/Cursor, and the **official MCP registry** — plus a new **🌍 Use It Anywhere** section + PyPI/MCP header badges. Builds on the v27 ecosystem work: multi-model playground (Claude / OpenAI / Gemini / **Ollama**); a **remote MCP connector** ([`mcp-remote/`](mcp-remote/)) to add PM Skills to **ChatGPT, Claude.ai & Cursor** by URL; MCP server now serves skills as **prompts + resources**; **4 new IDE export targets** (Cline, Continue, Zed, Roo → 9 platforms); a **Python package** ([`python/`](python/), `pip install pm-skills` with LangChain/CrewAI adapters); an **`llms.txt`** for agent discovery; a reusable **[score-skills Action](.github/actions/score-skills/)**; and **MCP-registry manifests** (`server.json`, `smithery.yaml`). The full library is now eval-scored — **196 skills, avg 4.8/5**. Builds on **v26.0.0** (the Creator stack). **206 skills** across **28 bundles**, **21 professions**.
 
 Full [Keep a Changelog](https://keepachangelog.com/)-format history — every release back to the start — is in **[CHANGELOG.md](CHANGELOG.md)**.
 
-→ Earlier releases (v20 and before — the road from 6 to 205 skills) are in **[CHANGELOG.md](CHANGELOG.md)**.
+→ Earlier releases (v20 and before — the road from 6 to 206 skills) are in **[CHANGELOG.md](CHANGELOG.md)**.
 
 ---
 
@@ -663,7 +670,7 @@ This repo was built alongside a published 16-part article series on Medium.
 
 ## 🏷️ Skill Tiers — Start With the Strongest
 
-A 205-skill library doesn't have 205 equally-mature skills, and pretending otherwise
+A 206-skill library doesn't have 206 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.**
@@ -676,7 +683,7 @@ If you're new, install `pm-essentials` and try a couple of Production-Ready skil
 
 ---
 
-## 🗂️ All 205 Skills
+## 🗂️ All 206 Skills
 
 Every skill, grouped by profession. **[Browse the full per-skill catalog → SKILLS.md](SKILLS.md)** · **[searchable live catalog](https://mohitagw15856.github.io/pm-claude-skills/catalog.html)** · **[run any skill in the browser](https://mohitagw15856.github.io/pm-claude-skills/)**
 
@@ -699,7 +706,7 @@ Every skill, grouped by profession. **[Browse the full per-skill catalog → SKI
 | 🤝 Sales | `pm-sales` | 6 | `sales-battlecard` |
 | ⚙️ Operations | `pm-operations` | 10 | `sop-writer` |
 | 🏥 Research & Healthcare | `pm-research` | 4 | `literature-review` |
-| 🌐 Cross-Profession | `pm-cross` | 8 | `meeting-notes` · `red-team-review` |
+| 🌐 Cross-Profession | `pm-cross` | 9 | `meeting-notes` · `red-team-review` |
 | 🖼️ Figma | `pm-figma` | 10 | `figma-design-review` |
 | 📱 Social Media | `pm-social` | 5 | `social-media-strategy` |
 | ✍️ Writers & Content | `pm-writers` | 6 | `aeo-optimizer` |
@@ -710,7 +717,7 @@ Every skill, grouped by profession. **[Browse the full per-skill catalog → SKI
 
 ## ❤️ Sponsor This Work
 
-Building and maintaining 205 skills across 28 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 206 skills across 28 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)).
 

package/commands/brain.md

@@ -0,0 +1,13 @@
+---
+description: Set up or use your Professional Brain — init, ingest, recall, or review.
+argument-hint: [init | ingest <thing> | recall <query> | review]
+---
+
+Apply the **professional-brain** skill to: $ARGUMENTS
+
+- `init` — scaffold `brain/` (copy from `templates/brain/`) and migrate any existing `pm-context.md`.
+- `ingest <thing>` — save the original to `source/`, synthesise facts into the durable layer, tag each with provenance.
+- `recall <query>` — answer from memory using `scripts/brain_query.py`, citing each fact's file and tag; say so if memory is thin.
+- `review` — weekly sweep: flag stale hypotheses, decisions due to reopen, and contradictions.
+
+Default the brain location to `./brain/`. Never invent facts the brain doesn't hold, and never drop provenance tags.

package/connectors/README.md

@@ -56,6 +56,23 @@ servers you configured.
 **🔁 A whole recipe, grounded** *(pm-skills + filesystem/github)*
 > Get the `ship-a-feature` workflow, use the notes in `docs/idea.md` as the kickoff, and run the chain end to end.
 
+## 🧩 Tool integrations
+
+Beyond MCP data servers, PM Skills plugs into the tools where work already happens. Each guide
+uses the read-only **REST API / static catalogue** (no auth, open CORS) or the hosted MCP
+connector:
+
+| Tool | What you get | Guide |
+|---|---|---|
+| **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) |
+
+> **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
+> the MCP connector, for any HTTP/no-code tool. Static fallback:
+> [`skills.json`](https://mohitagw15856.github.io/pm-claude-skills/skills.json).
+
 ## How it works
 `pm-skills` exposes `search_skills` / `get_skill` / `get_workflow` over MCP; the assistant
 fetches the right instructions and applies them to whatever the *data* server returns. No

package/connectors/lovable.md

@@ -0,0 +1,106 @@
+# 🔗 Lovable — build skill-powered apps
+
+[Lovable](https://lovable.dev) turns prompts into full-stack web apps (React + Vite +
+Tailwind, usually with a Supabase backend). PM Skills is the **content/brains layer**: your
+Lovable app provides the UI and the model call; PM Skills provides the structure that makes
+the output professional instead of generic.
+
+The bridge is the read-only **REST API / static catalogue** — no SDK, no auth, open CORS, so
+a Lovable app can `fetch()` it directly from the browser or from a Supabase edge function.
+
+---
+
+## Pattern A — client-side, bring-your-own-key (no backend)
+
+This mirrors the official [Skill Playground](https://mohitagw15856.github.io/pm-claude-skills/):
+the user pastes their own model key, the app fetches a skill, and calls the provider
+directly. Nothing touches a server you own.
+
+```js
+// 1) List skills for a picker
+const { skills } = await fetch(
+  'https://pm-skills-mcp.pm-claude-skills.workers.dev/v1/skills'
+).then(r => r.json());
+
+// 2) Pull the chosen skill's instructions
+const skill = await fetch(
+  `https://pm-skills-mcp.pm-claude-skills.workers.dev/v1/skills/${name}`
+).then(r => r.json());
+
+// 3) Run it with the user's own key (Anthropic shown)
+const res = await fetch('https://api.anthropic.com/v1/messages', {
+  method: 'POST',
+  headers: {
+    'x-api-key': userKey,
+    'anthropic-version': '2023-06-01',
+    'anthropic-dangerous-direct-browser-access': 'true',
+    'content-type': 'application/json',
+  },
+  body: JSON.stringify({
+    model: 'claude-opus-4-8',
+    max_tokens: 2048,
+    system: skill.instructions,        // the skill body = the system prompt
+    messages: [{ role: 'user', content: userInput }],
+  }),
+});
+```
+
+> No-deploy fallback: `https://mohitagw15856.github.io/pm-claude-skills/skills.json` is the
+> same catalogue as static JSON (`name`, `title`, `description`, `plugin`, `instructions`).
+
+---
+
+## Pattern B — Supabase edge function (key stays server-side)
+
+For a real product where you don't want the key in the browser, proxy the model call through
+a Supabase edge function. The function fetches the skill, prepends it as the system prompt,
+and calls the provider with a secret key — your React UI only ever talks to your function.
+
+```ts
+// supabase/functions/run-skill/index.ts (sketch)
+const skill = await fetch(`${PM_SKILLS}/v1/skills/${name}`).then(r => r.json());
+const out = await callModel({ system: skill.instructions, user: input, key: Deno.env.get('ANTHROPIC_API_KEY') });
+return new Response(JSON.stringify(out));
+```
+
+---
+
+## Make Lovable's generator skill-aware
+
+Paste the block below into your Lovable project's **Knowledge** (or your first prompt). It
+teaches Lovable how to wire PM Skills into anything it builds — so "add a PRD generator"
+just works.
+
+```text
+KNOWLEDGE: PM Skills integration
+PM Skills is a free, read-only, CORS-open catalogue of 206 professional "skill"
+prompts (PRDs, exec updates, launch plans, etc.). Use it whenever the app needs to
+produce a structured professional document.
+
+Base URL: https://pm-skills-mcp.pm-claude-skills.workers.dev
+- GET /v1/skills              -> list skills: [{name,title,description,bundle,tier}]
+- GET /v1/skills/{name}       -> one skill: {..., instructions}  (the full prompt body)
+- GET /v1/skills/{name}?format=md -> raw Markdown body
+- GET /v1/search?q=<query>    -> keyword search
+- GET /v1/workflows           -> multi-step "recipe" chains
+
+To run a skill: fetch its `instructions`, use that string as the LLM system prompt,
+and pass the user's input as the user message. Prefer the user's own API key on the
+client, or a Supabase edge function if the key must stay secret. No auth is needed to
+read the catalogue.
+```
+
+---
+
+## Ship a starter
+
+The fastest path is to clone the existing Playground (`web/` — vanilla JS, zero backend) as
+a Lovable project and restyle it, then point `fetch` at `/v1/skills`. A polished, forkable
+"Skill Studio on Lovable" reference template is on the roadmap —
+[interested?](https://github.com/mohitagw15856/pm-claude-skills/issues)
+
+## Safety
+
+The PM Skills catalogue is read-only and unauthenticated — it only serves skill text. Treat
+the user's model key like any secret: keep it client-side (Pattern A) or in Supabase secrets
+(Pattern B), never in your repo.

package/connectors/n8n-example-workflow.json

@@ -0,0 +1,42 @@
+{
+  "name": "PM Skills — fetch a skill",
+  "nodes": [
+    {
+      "parameters": {},
+      "id": "a1b2c3d4-0001-4000-8000-000000000001",
+      "name": "When clicking 'Test workflow'",
+      "type": "n8n-nodes-base.manualTrigger",
+      "typeVersion": 1,
+      "position": [240, 300]
+    },
+    {
+      "parameters": {
+        "url": "https://pm-skills-mcp.pm-claude-skills.workers.dev/v1/skills/pr-description-writer?format=md",
+        "options": {}
+      },
+      "id": "a1b2c3d4-0002-4000-8000-000000000002",
+      "name": "Get 'pr-description-writer' skill",
+      "type": "n8n-nodes-base.httpRequest",
+      "typeVersion": 4.2,
+      "position": [480, 300]
+    }
+  ],
+  "connections": {
+    "When clicking 'Test workflow'": {
+      "main": [
+        [
+          {
+            "node": "Get 'pr-description-writer' skill",
+            "type": "main",
+            "index": 0
+          }
+        ]
+      ]
+    }
+  },
+  "pinData": {},
+  "settings": { "executionOrder": "v1" },
+  "meta": {
+    "description": "Minimal PM Skills starter: fetch a skill's Markdown instructions over the read-only REST API, then wire the output into any AI node as a system prompt. See connectors/n8n.md."
+  }
+}

package/connectors/n8n.md

@@ -0,0 +1,104 @@
+# 🔗 n8n — run PM Skills inside your automations
+
+[n8n](https://n8n.io) is an open-source workflow automation tool. PM Skills plugs in as the
+**brains** of a workflow: a trigger fires, a skill turns raw input into a structured
+professional artifact, and the next node routes it where it belongs (Slack, Notion, a doc,
+a ticket).
+
+There are three ways in, from zero-build to native. Pick by how much you want to wire.
+
+---
+
+## Tier 0 — MCP Client node (works today, no build)
+
+n8n's **AI Agent** node can use any external MCP server as a tool via the **MCP Client Tool**
+node. Point it at the hosted PM Skills connector and all 206 skills + 6 workflow recipes
+become tools the agent can call on demand.
+
+1. Add an **AI Agent** node (with your Anthropic/OpenAI credential).
+2. Add an **MCP Client Tool** sub-node → **Endpoint:**
+   `https://pm-skills-mcp.pm-claude-skills.workers.dev/`  (SSE/Streamable HTTP, no auth).
+3. Prompt the agent naturally — *"Search the skills for churn and apply the best one to this
+   account note."* It calls `search_skills` → `get_skill` and applies the result.
+
+The skill supplies the *structure*; your AI Agent node's model does the *thinking*. Nothing
+to host, nothing to maintain.
+
+---
+
+## Tier 1 — HTTP Request node (REST, model-agnostic)
+
+Prefer to keep control of the model call? Use the read-only **REST API** to fetch a skill,
+then feed its instructions into whatever LLM node you like.
+
+> The `/v1` REST API is served by the same Cloudflare Worker as the MCP connector. If you
+> self-host the worker (`mcp-remote/`), deploy the latest version first. The static
+> `skills.json` fallback below needs no deploy and works today.
+
+**Fetch one skill's instructions** — *HTTP Request* node:
+
+```
+Method: GET
+URL:    https://pm-skills-mcp.pm-claude-skills.workers.dev/v1/skills/pr-description-writer?format=md
+```
+
+Returns the raw Markdown body. Wire it into an **Anthropic / OpenAI / AI Agent** node as the
+system prompt, with your trigger data as the user message.
+
+**Other endpoints:**
+
+| Call | Returns |
+|---|---|
+| `GET /v1/skills` | every skill (`?bundle=pm-cs`, `?q=churn`, `?limit=20`) |
+| `GET /v1/skills/{name}` | one skill as JSON (`?format=md` for raw Markdown) |
+| `GET /v1/search?q=pricing` | best keyword matches |
+| `GET /v1/workflows` | the 6 chain recipes |
+| `GET /v1/workflows/{id}` | one recipe with its ordered steps |
+
+**No-deploy fallback** — the catalogue is also static JSON on GitHub Pages, usable from an
+HTTP Request node today:
+
+```
+GET https://mohitagw15856.github.io/pm-claude-skills/skills.json
+```
+
+Each item has `name`, `title`, `description`, `plugin`, and `instructions` (the full body).
+
+---
+
+## Example workflows
+
+A ready-to-import example lives in [`n8n-example-workflow.json`](n8n-example-workflow.json)
+(*Manual trigger → fetch `pr-description-writer` → return its instructions*). In n8n:
+**Workflows → Import from File**.
+
+Patterns worth building:
+
+- **GitHub PR → PR description.** *GitHub Trigger → HTTP (get diff) → HTTP (get
+  `pr-description-writer`) → AI node → GitHub (post comment).*
+- **RSS → competitive signal.** *RSS Trigger → HTTP (get `competitor-signal-tracker`) → AI
+  node → Slack.*
+- **Form → PRD → Notion.** *Form Trigger → HTTP (get `prd-template`) → AI node → Notion
+  (create page).*
+- **Weekly metrics → exec update.** *Schedule → Postgres/Sheets → HTTP (get
+  `executive-update`) → AI node → Email.*
+
+---
+
+## Tier 2 — native community node (roadmap)
+
+A first-class `n8n-nodes-pm-skills` node (List / Search / Get / Run Skill + Run Workflow
+recipe) is on the roadmap so PM Skills is installable from n8n's **Community Nodes** panel.
+Want it sooner? [Open an issue](https://github.com/mohitagw15856/pm-claude-skills/issues).
+
+## Design note — return vs run
+
+Lean on **return the skill** (fetch the body, run it in n8n's own AI node) rather than having
+PM Skills call a model for you. n8n already manages model credentials, retries, and
+streaming — the REST API stays free, stateless, and model-agnostic.
+
+## Safety
+
+The PM Skills endpoints are **read-only** and need no auth — they only serve skill text.
+Any credential in the workflow (GitHub, Slack, your LLM key) lives in n8n's own credential
+store, scoped by you.

package/connectors/obsidian.md

@@ -0,0 +1,88 @@
+# 🔗 Obsidian — skills in your vault
+
+[Obsidian](https://obsidian.md) is a local-first Markdown knowledge base. PM Skills is a
+near-perfect fit: the skills **are** Markdown, the artifacts they produce (PRDs, meeting
+notes, research, retros) are exactly what lives in a vault, and the whole library is
+BYO-key / local-first — the same ethos as Obsidian itself.
+
+Better still, the vault gives the library something it otherwise lacks: **persistent,
+linked project state.** Run `prd-template`, then `rice-prioritisation`, then `go-to-market`,
+and each output is a note that backlinks to the last — your graph view *is* the workflow.
+
+Three ways in, from drop-in to native.
+
+---
+
+## Tier 0 — drop the skills into your vault (no build)
+
+Every skill is exported as a vault-ready note under
+[`exports/obsidian/`](../exports/obsidian/) — frontmatter as Obsidian properties, the skill
+body, and a footer that applies it to your current selection.
+
+```bash
+# clone, then copy the prompt pack into a folder in your vault
+git clone https://github.com/mohitagw15856/pm-claude-skills.git
+cp -r pm-claude-skills/exports/obsidian /path/to/YourVault/PM-Skills
+```
+
+Now they're browsable, linkable (`[[PRD Template]]`), and searchable. On their own they're
+reference notes — to *run* one with AI, use Tier 1.
+
+---
+
+## Tier 1 — run a skill with an AI plugin
+
+The exported notes double as **custom prompts** for the popular Obsidian AI plugins:
+
+- **[Copilot for Obsidian](https://github.com/logancyang/obsidian-copilot)** — point its
+  *Custom Prompts* folder at `PM-Skills/`. Select text in any note → run the skill prompt →
+  it writes the structured output back. (Copilot uses `{}` for the selection — the export's
+  `{{selection}}` footer notes the swap.)
+- **[Text Generator](https://github.com/nhaouari/obsidian-textgenerator-plugin)** — the
+  notes are valid templates; `{{selection}}` and frontmatter work as-is.
+- **Templater** — insert a skill note as a template to scaffold the document structure.
+
+All of these use **your own** model key, configured once in the plugin. Nothing leaves your
+machine except the call to your chosen provider.
+
+---
+
+## Tier 2 — live catalogue (always current)
+
+The exported pack is a snapshot. To pull skills fresh (e.g. from a Templater user script or
+the *Dataview* JS), hit the read-only REST API or the static catalogue — no auth, open CORS:
+
+```
+GET https://pm-skills-mcp.pm-claude-skills.workers.dev/v1/skills
+GET https://pm-skills-mcp.pm-claude-skills.workers.dev/v1/skills/{name}?format=md
+```
+
+No-deploy fallback: `https://mohitagw15856.github.io/pm-claude-skills/skills.json`.
+
+---
+
+## Tie it together — Obsidian ⇄ n8n ⇄ PM Skills
+
+The [Local REST API](https://github.com/coddingtonbear/obsidian-local-rest-api) Obsidian
+plugin exposes your vault over HTTP. Combine the three:
+
+```
+n8n (orchestrate) → PM Skills (the structure) → Obsidian vault (system of record)
+```
+
+e.g. a schedule trigger in [n8n](n8n.md) fetches `executive-update`, runs it on this week's
+metrics, and writes the result straight into a dated note in your vault.
+
+---
+
+## Roadmap — a native plugin
+
+A dedicated `obsidian-pm-skills` community plugin (command palette → *Run PM Skill* on the
+current note, with the workflow recipes as multi-note chains) is on the roadmap. The Tier 1
+export path above needs no plugin and almost no maintenance, so start there.
+
+## Safety
+
+The skill notes are plain instructions — they don't exfiltrate anything. Your model key
+lives only in your AI plugin's settings; the catalogue endpoints are read-only and need no
+auth.