pm-claude-skills 29.3.1 → 29.4.0

package/README.md

@@ -4,7 +4,7 @@
   </a>
 </p>
 
-# 🧠 PM Skills — 238 Professional Agent Skills for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes
+# 🧠 PM Skills — 244 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)
@@ -14,7 +14,7 @@
 [![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-238-blue)](https://github.com/mohitagw15856/pm-claude-skills)
+[![Skills](https://img.shields.io/badge/skills-244-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/)
@@ -30,7 +30,7 @@
 
 <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=238+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=244+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>
 
@@ -51,11 +51,11 @@
 *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.**
-> 238 professional skills + 4 agent templates across 32 bundles covering 23 professions. Built for Claude Code — and now portable to ChatGPT, Gemini, and Hermes Agent. Built by a PM, used by everyone.
+> 244 professional skills + 4 agent templates across 33 bundles covering 23 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 — v29.3.0 (run skills from the terminal + a Career pack):** the CLI can now **run** any skill headless — `cat notes.txt | npx pm-claude-skills run meeting-notes --out summary.md` — so every skill is scriptable and CI-usable, not just installable or browser-only. Plus a new **Career & Growth bundle** (`brag-doc`, `self-review`, `promotion-packet`, `one-on-one-prep`, `career-ladder-map`, `salary-negotiation` with a total-comp comparison script). *Earlier (v29.2):* a **Compliance & Trust** bundle (SOC 2, GDPR, HIPAA, ISO 27001 — each with a scoring script), a **C-suite decision pack**, and **[role Personas](PERSONAS.md)**. **238 skills across 32 bundles.** → **[Full release history & notes](https://github.com/mohitagw15856/pm-claude-skills/releases)**.
+**🆕 Latest — v29.4.0 (beautiful documents — "good content deserves good paper"):** a new **themed PDF export** turns any skill's output into a professionally typeset document — pick **Paper (serif)**, **Modern**, or **Technical**, and it even tints to your brand color. Paired with a new **Personal-docs bundle** (`resume`, `cover-letter`, `personal-bio`, `linkedin-profile`, `portfolio-page`, `one-pager`) so you can go from a vague ask to a designed CV or one-pager end-to-end. *Earlier (v29.3):* run skills headless from the terminal (`npx pm-claude-skills run <skill>`) + a Career & Growth pack. **244 skills across 33 bundles.** → **[Full release history & notes](https://github.com/mohitagw15856/pm-claude-skills/releases)**.
 
 ### ▶ See it in action — [try the live Skill Playground](https://mohitagw15856.github.io/pm-claude-skills/)
 
@@ -84,7 +84,7 @@ A community-built library of professional skills for every field — product man
 | 🔭 [Competitor Teardown](skills/competitor-teardown) | "what are rivals up to?" | a positioning map, feature gaps & strategy |
 | 📝 [Meeting Notes](skills/meeting-notes) | a raw transcript | decisions, owners & next steps |
 
-→ Want proof first? See [**real sample outputs**](https://mohitagw15856.github.io/pm-claude-skills/examples.html) from each skill. Like what you see? [**Install in 2 minutes**](#-quick-install-2-minutes) · [browse all 238 skills](#️-all-238-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 244 skills](#️-all-244-skills) · [**⭐ star the repo**](https://github.com/mohitagw15856/pm-claude-skills/stargazers) so others find it.
 
 ---
 
@@ -93,11 +93,11 @@ A community-built library of professional skills for every field — product man
 <details>
 <summary>Read more ↓</summary>
 
-The whole library on one page — install, all 238 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 244 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 — 238 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 — 244 skills, the Professional Brain, REST API, integrations, and tooling at a glance." />
   </a>
 </p>
 
@@ -128,13 +128,13 @@ Generic AI forgets everything between sessions, so you re-paste context forever
 <details>
 <summary>Read more ↓</summary>
 
-These 238 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 244 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
     A(["🔍 Discover"]) --> B(["🎯 Decide"]) --> C(["🔨 Build"]) --> D(["🚀 Ship"]) --> E(["📊 Measure"]) --> F(["📣 Communicate"])
     F -. "feeds the next discovery" .-> A
-    classDef s fill:#1d238b,stroke:#d97757,color:#e7ebf0;
+    classDef s fill:#1d244b,stroke:#d97757,color:#e7ebf0;
     class A,B,C,D,E,F s;
 ```
 
@@ -147,7 +147,7 @@ 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 238 skills**](#️-all-238-skills) grouped by profession.
+> New here? Start with the [**top-tier skills**](#️-skill-tiers--start-with-the-strongest), or jump straight to [**all 244 skills**](#️-all-244-skills) grouped by profession.
 
 </details>
 
@@ -270,7 +270,7 @@ Most skill repos are a folder of prompts. This one is a **system** — measured,
 
 | | **PM Skills** | Typical skill repo |
 |---|:---:|:---:|
-| Skills | **238**, across 23 professions | a handful → dozens, usually one domain |
+| Skills | **244**, across 23 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 |
@@ -295,13 +295,13 @@ 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 238 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 244 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 238
+npx skills add mohitagw15856/pm-claude-skills --skill '*'            # install all 244
 ```
 
 **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:
@@ -310,7 +310,7 @@ 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 238 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 244 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
@@ -371,7 +371,7 @@ ln -s ~/pm-claude-skills/skills/* ~/.claude/skills/
 <details>
 <summary>Read more ↓</summary>
 
-The same 238 skills reach you through every channel — pick whatever fits your stack:
+The same 244 skills reach you through every channel — pick whatever fits your stack:
 
 | Channel | Get it |
 |---|---|
@@ -385,7 +385,7 @@ The same 238 skills reach you through every channel — pick whatever fits your
 | 🖥️ **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 238 skills are eval-scored, averaging 4.8/5** — see the [leaderboard](https://mohitagw15856.github.io/pm-claude-skills/leaderboard.html).
+> **196 of 244 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)**.
 
@@ -407,7 +407,7 @@ 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 238 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 244 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? |
 |---|---|---|
@@ -567,7 +567,7 @@ 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 238 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 244 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>
 
@@ -663,7 +663,7 @@ 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 238 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 244 skills here are the building blocks for agent templates outside of finance.**
 
 ### What is an agent template?
 
@@ -743,7 +743,7 @@ More templates will follow. If you want to contribute one, see the [template con
 <details>
 <summary>Read more ↓</summary>
 
-**Latest: v29.1.0 — AI/ML + Growth skill packs, composable recipes, a deeper Brain.** 238 skills across 32 bundles, 23 professions. Every tagged release has complete notes on the **[Releases page](https://github.com/mohitagw15856/pm-claude-skills/releases)**.
+**Latest: v29.1.0 — AI/ML + Growth skill packs, composable recipes, a deeper Brain.** 244 skills across 33 bundles, 23 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)**.
 
@@ -791,7 +791,7 @@ This repo was built alongside a published 16-part article series on Medium.
 <details>
 <summary>Read more ↓</summary>
 
-A 238-skill library doesn't have 238 equally-mature skills, and pretending otherwise
+A 244-skill library doesn't have 244 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.**
@@ -806,7 +806,7 @@ If you're new, install `pm-essentials` and try a couple of Production-Ready skil
 
 ---
 
-## 🗂️ All 238 Skills
+## 🗂️ All 244 Skills
 
 <details>
 <summary>Read more ↓</summary>
@@ -848,7 +848,7 @@ Every skill, grouped by profession. **[Browse the full per-skill catalog → SKI
 <details>
 <summary>Read more ↓</summary>
 
-Building and maintaining 238 skills across 32 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 244 skills across 33 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/exports/README.md

@@ -8,7 +8,7 @@ by hand; edit the source skill and run:
 node scripts/build-exports.mjs
 ```
 
-Currently exporting **238 skills** to:
+Currently exporting **244 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.
 
-238 skills exported. Copy a `.mdc rule` into the tool to use it.
+244 skills exported. Copy a `.mdc rule` into the tool to use it.
 
 | Skill | Bundle | Path |
 |---|---|---|
@@ -54,6 +54,7 @@
 | Context Mode | `pm-engineering` | `pm-engineering/context-mode/context-mode.md` |
 | Contract Review | `pm-legal` | `pm-legal/contract-review/contract-review.md` |
 | Conversion Rate Optimization | `pm-growth` | `pm-growth/conversion-rate-optimization/conversion-rate-optimization.md` |
+| Cover Letter | `pm-personal` | `pm-personal/cover-letter/cover-letter.md` |
 | Creator Brand Kit | `pm-creator` | `pm-creator/creator-brand-kit/creator-brand-kit.md` |
 | Creator Media Kit | `pm-creator` | `pm-creator/creator-media-kit/creator-media-kit.md` |
 | Customer Escalation Brief | `pm-cs` | `pm-cs/cs-escalation-brief/cs-escalation-brief.md` |
@@ -132,6 +133,7 @@
 | Legal Brief | `pm-legal` | `pm-legal/legal-brief/legal-brief.md` |
 | Lesson Plan | `pm-education` | `pm-education/lesson-plan/lesson-plan.md` |
 | Lifecycle / CRM Plan | `pm-growth` | `pm-growth/lifecycle-crm-plan/lifecycle-crm-plan.md` |
+| LinkedIn Profile | `pm-personal` | `pm-personal/linkedin-profile/linkedin-profile.md` |
 | Literature Review | `pm-research` | `pm-research/literature-review/literature-review.md` |
 | LLM Cost & Latency Budget | `pm-ai` | `pm-ai/llm-cost-latency-budget/llm-cost-latency-budget.md` |
 | Load Testing Plan | `pm-engineering` | `pm-engineering/load-testing-plan/load-testing-plan.md` |
@@ -155,13 +157,16 @@
 | Onboarding Plan | `pm-hr` | `pm-hr/onboarding-plan/onboarding-plan.md` |
 | On-Call Runbook | `pm-engineering` | `pm-engineering/oncall-runbook/oncall-runbook.md` |
 | One-on-One Prep | `pm-career` | `pm-career/one-on-one-prep/one-on-one-prep.md` |
+| One-Pager | `pm-personal` | `pm-personal/one-pager/one-pager.md` |
 | Paid Acquisition Plan | `pm-growth` | `pm-growth/paid-acquisition-plan/paid-acquisition-plan.md` |
 | Parent Communication | `pm-education` | `pm-education/parent-communication/parent-communication.md` |
 | Partnership Proposal | `pm-sales` | `pm-sales/partnership-proposal/partnership-proposal.md` |
 | Patient Communication | `pm-research` | `pm-research/patient-communication/patient-communication.md` |
 | Performance Budget | `pm-engineering` | `pm-engineering/performance-budget/performance-budget.md` |
 | Performance Review | `pm-people` | `pm-people/performance-review/performance-review.md` |
+| Personal Bio | `pm-personal` | `pm-personal/personal-bio/personal-bio.md` |
 | PM Weekly Review | `pm-rituals` | `pm-rituals/pm-weekly-review/pm-weekly-review.md` |
+| Portfolio Page | `pm-personal` | `pm-personal/portfolio-page/portfolio-page.md` |
 | PPTX Slide Auditor | `pm-delivery` | `pm-delivery/pptx-slide-auditor/pptx-slide-auditor.md` |
 | PR Description Writer | `pm-engineering` | `pm-engineering/pr-description-writer/pr-description-writer.md` |
 | PRD Template | `pm-essentials` | `pm-essentials/prd-template/prd-template.md` |
@@ -186,6 +191,7 @@
 | Regex Builder & Explainer | `pm-engineering` | `pm-engineering/regex-builder/regex-builder.md` |
 | Renewal Playbook | `pm-cs` | `pm-cs/renewal-playbook/renewal-playbook.md` |
 | Research Protocol | `pm-research` | `pm-research/research-protocol/research-protocol.md` |
+| Resume | `pm-personal` | `pm-personal/resume/resume.md` |
 | Retention Analysis | `pm-analytics` | `pm-analytics/retention-analysis/retention-analysis.md` |
 | Retention Loop Design | `pm-growth` | `pm-growth/retention-loop-design/retention-loop-design.md` |
 | Retrospective Analysis | `pm-delivery` | `pm-delivery/retro-analysis/retro-analysis.md` |

package/exports/aider/pm-personal/cover-letter/cover-letter.md

@@ -0,0 +1,52 @@
+# Cover Letter Skill
+
+Most cover letters are throat-clearing the reader skips. A good one does one job: connect *your specific
+evidence* to *this company's specific need*, in a voice that sounds like a person. This skill writes a
+tight, tailored letter — no "I am writing to apply for…", no restating the resume — that earns the read.
+
+## Required Inputs
+
+Ask for these only if they aren't already provided:
+
+- **The role & company** — and the job description (the letter must be specific to it).
+- **Why this company** — something genuine: their product, mission, a recent move (avoids generic flattery).
+- **Your 2–3 strongest, most relevant proofs** — the achievements that map to what they need.
+- **Tone** — warm-professional (default), or more formal/creative per the company's culture.
+
+## Output Format
+
+A 3–4 paragraph letter (≈250–350 words):
+
+> [Name] · [email] · [phone] · [date]
+> Dear [hiring manager name, or "Hiring Team" if unknown],
+
+**Hook (1 short para)** — open with a specific reason you're writing *to them* — a genuine connection to their product/mission/moment — and the role you want. No "I am writing to apply."
+
+**Evidence (1–2 paras)** — the heart: take the role's top 2–3 needs and show, with a concrete result each, that you've done it. Map your proof to their problem; don't recap the resume — *interpret* it.
+
+**Close (1 short para)** — what you'd bring, an honest note of enthusiasm, and a forward-looking line ("I'd love to talk about…"). Confident, not desperate.
+
+> Sincerely, [Name]
+
+**Voice note** (for the user): keep it human — contractions, active voice, no thesaurus words. Read it aloud; if it sounds like a robot, cut.
+
+## Quality Checks
+
+- [ ] The opening is specific to this company — it could not be pasted to another employer
+- [ ] Each evidence point maps a real, quantified result to one of the role's stated needs
+- [ ] It complements the resume (interprets/connects) rather than repeating its bullets
+- [ ] Under ~350 words; tight, scannable paragraphs
+- [ ] Voice sounds like a person (contractions, active verbs), not a template
+- [ ] Addressed to a named person where findable
+
+## Anti-Patterns
+
+- [ ] Do not open with "I am writing to apply for the position of…" — it wastes the most valuable line
+- [ ] Do not restate the resume — the letter adds connection and context, not a duplicate list
+- [ ] Do not use generic flattery ("your prestigious company") — name something real and specific
+- [ ] Do not pad to a page — a tight 4 paragraphs beats a full page of filler
+- [ ] Do not sound desperate or arrogant — aim for confident and genuinely interested
+
+## Based On
+
+Modern cover-letter practice — specific hook, evidence-to-need mapping, human voice.

package/exports/aider/pm-personal/linkedin-profile/linkedin-profile.md

@@ -0,0 +1,49 @@
+# LinkedIn Profile Skill
+
+LinkedIn is two audiences at once: a **search algorithm** (recruiters filter by keywords) and a **human**
+who decides in the first two lines whether to keep reading. This skill optimises for both — a keyword-rich
+headline, an About section that hooks then proves, and achievement-led experience — so the profile gets
+surfaced *and* converts the click.
+
+## Required Inputs
+
+Ask for these only if they aren't already provided:
+
+- **Current role, target role/industry, and the keywords** recruiters in your field search for.
+- **Your achievements & specialties** — the proof, with numbers where possible.
+- **Goal** — open to roles, building authority/inbound, or selling/consulting? (changes the About CTA).
+- **Voice** — LinkedIn About is **first person**; pick formal vs. warm.
+
+## Output Format
+
+**Headline** (≤220 chars) — not just your job title: **role + value + keywords**. e.g. "Senior PM · B2B SaaS & PLG · I turn messy roadmaps into shipped outcomes." Keyword-rich for search.
+
+**About** (first person, 3–5 short paragraphs):
+- **Hook** (first 1–2 lines — all that shows before "see more"): a specific, intriguing opener, not "I am a passionate…".
+- **Proof**: what you do and the results, with numbers.
+- **Specialties / keywords**: a natural line or list of the terms recruiters search.
+- **CTA**: what you want (open to X, reach out about Y).
+
+**Experience bullets** — for the top roles, achievement-led bullets (same standard as a resume: action → impact → metric), lightly more narrative than a CV.
+
+**Skills list** — the 10–15 keyword skills to add (LinkedIn ranks search partly on these), ordered by relevance to the target role.
+
+## Quality Checks
+
+- [ ] The headline goes beyond the job title — value + searchable keywords
+- [ ] The first 1–2 lines of About hook before the "see more" fold
+- [ ] About is first-person and ends with a clear CTA tied to the goal
+- [ ] Target-role keywords appear across headline, About, and skills (for search)
+- [ ] Experience bullets are achievement-led with metrics, not duties
+
+## Anti-Patterns
+
+- [ ] Do not make the headline just your title — it's prime keyword + value real estate
+- [ ] Do not bury the hook — the opening lines are all most viewers see; don't waste them on "passionate professional"
+- [ ] Do not write About in third person — LinkedIn is personal; "I" converts better
+- [ ] Do not ignore keywords — recruiters filter by them; a profile without them is invisible to search
+- [ ] Do not copy the resume verbatim — LinkedIn is warmer and slightly more narrative
+
+## Based On
+
+LinkedIn profile-optimisation practice — keyword-aware headline/About, hook-before-fold, recruiter search ranking.

package/exports/aider/pm-personal/one-pager/one-pager.md

@@ -0,0 +1,55 @@
+# One-Pager Skill
+
+A one-pager is a forcing function: if it doesn't fit on one page, the thinking isn't sharp enough. It's
+the leave-behind after a pitch, the brief that aligns a team, the thing a busy exec actually reads. This
+skill distils a startup / product / project / idea into one skimmable, persuasive page with a clear ask —
+pair it with the **Paper** or **Modern** PDF theme for a polished one-sheet.
+
+## Required Inputs
+
+Ask for these only if they aren't already provided:
+
+- **What it's for & the audience** — investor one-pager, product one-sheet, project brief, partnership leave-behind? (sets emphasis and the ask).
+- **The core** — what it is, the problem it solves, and who for.
+- **Proof / why now** — traction, data, market timing, or differentiation.
+- **The ask** — what you want the reader to do next (invest, approve, pilot, partner).
+
+## Output Format
+
+A single page, skimmable, in this order:
+
+### [Name / Title]
+*[One-line tagline — what it is, in plain words a stranger gets instantly]*
+
+**The problem** — 2–3 sentences: the pain, who feels it, why it matters now. Concrete, not abstract.
+
+**The solution** — what you've built/propose and how it solves the problem. Lead with the outcome for the user.
+
+**Why now / why us** — the proof: traction or metrics, market timing, and your unfair advantage or differentiation.
+
+**[Audience-specific block]** — e.g. *Traction* (investor), *How it works* (product), *Plan & timeline* (project), *The offer* (partnership). Use a small table or 3–4 tight bullets.
+
+**The ask** — exactly what you want next, and how to take it (contact / link / next step). End on the action.
+
+**Note** (for the user): ruthless editing is the skill — every line must earn its place. If it spills past a page, cut, don't shrink the font.
+
+## Quality Checks
+
+- [ ] It genuinely fits one page — tight, skimmable, not dense
+- [ ] The tagline makes a stranger understand it in one read
+- [ ] Problem is concrete and the solution leads with the user outcome
+- [ ] There's real proof (metrics / timing / differentiation), not just claims
+- [ ] It ends with one clear, specific ask / CTA
+- [ ] Emphasis matches the audience (investor vs. product vs. project vs. partner)
+
+## Anti-Patterns
+
+- [ ] Do not overflow the page — a "one-pager" that's two pages has failed its only constraint; cut content, not font size
+- [ ] Do not bury the ask — the reader must finish knowing exactly what to do next
+- [ ] Do not write an abstract problem ("inefficiencies in the market") — name the concrete pain and who feels it
+- [ ] Do not list features instead of the outcome — lead with what it does for the user
+- [ ] Do not make claims without proof — one real metric beats three adjectives
+
+## Based On
+
+One-pager / one-sheet practice (problem · solution · why-now · ask) used for startups, products, and project briefs.

package/exports/aider/pm-personal/personal-bio/personal-bio.md

@@ -0,0 +1,50 @@
+# Personal Bio Skill
+
+You never need *a* bio — you need the right length for the slot: a one-line byline, a 50-word panel
+intro, a 150-word about page. Writing them separately makes them drift. This skill writes all three from
+one source so they're consistent, lead with what makes you credible, and don't read like a LinkedIn cliché.
+
+## Required Inputs
+
+Ask for these only if they aren't already provided:
+
+- **Name, current role/title, and company/affiliation.**
+- **Your credibility anchors** — the 2–3 facts that make you worth listening to (notable work, results, recognition).
+- **Focus & audience** — what you want to be known for, and where the bio will appear (conference, book, site, LinkedIn).
+- **Voice** — third-person (default for bios) and/or first-person; formal vs. warm.
+
+## Output Format
+
+### One-liner
+[Name] is a [role] who [the single most credible, specific thing]. *(for bylines, intros, Twitter)*
+
+### Short bio (~50 words)
+A tight paragraph: who you are, your strongest proof, and your focus. *(panels, author blurbs, speaker intros)*
+
+### Long bio (~150 words)
+The fuller story: role, a credibility-building arc (what you've done and the impact), what you focus on now, and a light personal/human note at the end. *(about pages, detailed intros)*
+
+### First-person variant
+The short bio rewritten in first person, for an about page or LinkedIn summary where "I" fits.
+
+**Note** (for the user): lead every version with specificity — a concrete result or named work beats "passionate, experienced professional."
+
+## Quality Checks
+
+- [ ] All three lengths are present and mutually consistent (same facts, scaled)
+- [ ] Each leads with a specific, credible anchor — not adjectives
+- [ ] Third-person versions read naturally (start with the name, not "He/She is a passionate…")
+- [ ] The long bio includes one human/personal touch so it isn't robotic
+- [ ] No clichés ("results-driven", "passionate about", "thought leader") unless backed by proof
+
+## Anti-Patterns
+
+- [ ] Do not open with empty adjectives — "an experienced, passionate professional" says nothing; lead with the proof
+- [ ] Do not make the three versions inconsistent — they should be the same story at different resolutions
+- [ ] Do not stuff every accomplishment into the short bio — pick the strongest; that's what "short" means
+- [ ] Do not use buzzword filler ("synergy", "thought leader") — specifics earn credibility, labels don't
+- [ ] Do not forget the audience — a conference bio and a startup about-page emphasise different things
+
+## Based On
+
+Professional bio practice — the one-liner / short / long convention, specificity over adjectives.

package/exports/aider/pm-personal/portfolio-page/portfolio-page.md

@@ -0,0 +1,53 @@
+# Portfolio Page Skill
+
+A portfolio fails when it's a gallery of artifacts with no story — the viewer can't tell what *you* did
+or whether it worked. This skill structures it as **evidence**: a clear positioning header, then per-project
+case studies that walk context → your specific role → what you did → the outcome. It works for PMs,
+designers, engineers, marketers, founders — any "show me you're good" page.
+
+## Required Inputs
+
+Ask for these only if they aren't already provided:
+
+- **Who you are & what you want** — your positioning and the audience (hiring manager, client, investor).
+- **The projects** — 2–4 of your best, with: the problem, your role, what you did, and the result.
+- **Proof** — metrics, links, visuals, testimonials (whatever's available).
+- **Constraints** — anything confidential/NDA that needs anonymising.
+
+## Output Format
+
+### [Name] — [positioning headline]
+One line on who you are and the value you create; who the page is for; contact/links.
+
+**Selected work** — 2–4 case studies, strongest first. Each:
+
+#### [Project name] — [one-line outcome]
+- **Context:** the situation and the problem (brief — set the stage).
+- **My role:** your specific contribution vs. the team's (be honest and clear).
+- **What I did:** the key decisions/actions, not every task — show judgement.
+- **Outcome:** the measurable result (or qualitative if that's all there is), and what you learned.
+- **Proof:** link / visual / metric / quote.
+
+**About / how I work** (optional) — a short note on approach or values, for fit.
+
+**Note** (for the user): pick depth over breadth — 3 strong case studies beat 8 thin ones. Anonymise confidential numbers as ranges ("~30% lift") rather than dropping them.
+
+## Quality Checks
+
+- [ ] Each project is a case study (context → role → action → outcome), not just a title + screenshot
+- [ ] Your specific role is distinguished from the team's on every project
+- [ ] Outcomes are stated (quantified where possible), not left implied
+- [ ] The page leads with positioning so the viewer knows who it's for and what you do
+- [ ] 2–4 strong projects, newest/most-relevant first — depth over breadth
+
+## Anti-Patterns
+
+- [ ] Do not list artifacts without the story — a screenshot with no context proves nothing
+- [ ] Do not blur your contribution into the team's — "we shipped" leaves the viewer unsure what you did
+- [ ] Do not omit outcomes — "redesigned the flow" without a result is a task, not a case study
+- [ ] Do not pad with weak projects — each extra mediocre one dilutes the strong ones
+- [ ] Do not leak confidential data — anonymise to ranges instead of dropping the impact entirely
+
+## Based On
+
+Case-study portfolio practice (context · role · action · outcome) used across product, design, and engineering.

package/exports/aider/pm-personal/resume/resume.md

@@ -0,0 +1,56 @@
+# Resume Skill
+
+A resume gets ~7 seconds and an ATS scan before a human reads it. So it has to be *scannable*,
+*achievement-led*, and *keyword-aligned* — not a job-description recap. This skill turns your experience
+into quantified accomplishment bullets, structured single-column (ATS-safe), and tailored to the target
+role. Export it with the **Paper** or **Modern** PDF theme for a typeset result.
+
+## Required Inputs
+
+Ask for these only if they aren't already provided:
+
+- **Target role / job description** — so the resume is tailored and keyword-aligned (generic resumes lose).
+- **Your experience** — roles, dates, and what you did/achieved (rough notes fine; the skill quantifies them).
+- **Skills, tools, education, certifications.**
+- **Seniority & format preference** — reverse-chronological (default) vs. functional; one page (most) vs. two.
+
+## Output Format
+
+A single-column, ATS-friendly resume in this order:
+
+### [Full Name]
+[Target title] · [city / remote] · [email] · [phone] · [LinkedIn/portfolio]
+
+**Summary** — 2–3 lines: who you are, your strongest proof, and what you're targeting. No "results-driven professional" filler.
+
+**Experience** — reverse-chronological. Per role:
+**[Title]**, [Company] · [dates]
+- [Accomplishment bullet: **action verb → what you did → quantified impact**]. e.g. "Cut onboarding drop-off 18%→9%, unlocking ~$140k ARR."
+- 3–5 bullets per recent role, fewer for older ones. Achievements, not duties.
+
+**Skills** — grouped, keyword-rich, mirroring the job's language (ATS matches on these).
+
+**Education** — degree, institution, year; certifications.
+
+**Tailoring note** (separate, for the user): which of the job's keywords you wove in, and any gap to address in the cover letter.
+
+## Quality Checks
+
+- [ ] Every experience bullet is an **achievement with a metric**, not a duty ("responsible for…")
+- [ ] Bullets start with strong action verbs; no first-person pronouns
+- [ ] Single-column, standard headings, no tables/text-boxes/graphics that break ATS parsing
+- [ ] Keywords from the target job description appear naturally (skills + bullets)
+- [ ] Length fits seniority (1 page < ~10 yrs; 2 max); newest/most-relevant first
+- [ ] Contact line is complete and the summary names the target role
+
+## Anti-Patterns
+
+- [ ] Do not list job duties — "managed a team" is a responsibility; "grew the team 4→11 and cut attrition 30%" is an achievement
+- [ ] Do not use multi-column layouts, tables, headers/footers, or icons — they scramble in ATS parsers
+- [ ] Do not write a generic resume — tailor the summary, skills, and emphasis to the target role
+- [ ] Do not pad with soft-skill filler ("hard-working team player") — show it through results
+- [ ] Do not invent or inflate metrics — use real numbers, or a defensible estimate clearly framed
+
+## Based On
+
+Achievement-led, ATS-aware resume practice (reverse-chronological, quantified-impact bullets, keyword alignment).