pm-claude-skills 22.3.0 → 23.0.0

package/README.md

@@ -1,8 +1,8 @@
-# 🧠 PM Skills — 175 Professional Agent Skills for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes
+# 🧠 PM Skills — 180 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=175+eval-scored+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=180+eval-scored+AI+skills;PRDs%2C+roadmaps%2C+launches+%E2%80%94+done+right;Run+any+one+free+in+your+browser" alt="PM Skills" />
   </a>
 </p>
 
@@ -11,14 +11,14 @@
 [![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)
-[![Skills](https://img.shields.io/badge/skills-175-blue)](https://github.com/mohitagw15856/pm-claude-skills)
+[![Skills](https://img.shields.io/badge/skills-180-blue)](https://github.com/mohitagw15856/pm-claude-skills)
 [![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)
 [![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-22.3.0-brightgreen)](https://github.com/mohitagw15856/pm-claude-skills/releases)
+[![Version](https://img.shields.io/badge/version-23.0.0-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)
@@ -26,11 +26,11 @@
 ### ⭐ 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.**
-> 175 professional skills + 4 agent templates across 26 bundles covering 18 professions. Built for Claude Code — and now portable to ChatGPT, Gemini, and Hermes Agent. Built by a PM, used by everyone.
+> 180 professional skills + 4 agent templates across 26 bundles covering 18 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 (v22.3.0 — Monetization & a polished playground):** a [**Sponsors program**](SPONSORS.md) + [**embeddable widget**](web/embed.js) + [**Pro/Teams**](https://mohitagw15856.github.io/pm-claude-skills/pro.html) page, and a redesigned playground with a **⌘K palette**, a hero landing, **favourites**, **light/dark** mode, **compare-models** (Opus/Sonnet/Haiku side by side), and **save-as-image**. Builds on v22.2 (Studio, Auto-Agent, editor extension). **175 skills**, 15 eval-scored. See the [changelog](#-changelog).
+**🆕 Latest release (v23.0.0 — 180 skills + the Ask experience):** five new developer skills (error decoder, regex builder, git troubleshooter, dependency resolver, code explainer) and **[❓ Ask](https://mohitagw15856.github.io/pm-claude-skills/ask.html)** — a coding question routed to the right skill and answered instantly, plus a community [Q&A](https://github.com/mohitagw15856/pm-claude-skills/discussions). Builds on v22.3 (sponsors, embed widget, polished playground). **180 skills**, 20 eval-scored. See the [changelog](#-changelog).
 
 ### ▶ See it in action — [try the live Skill Playground](https://mohitagw15856.github.io/pm-claude-skills/)
 
@@ -59,13 +59,13 @@ 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 175 skills](#️-all-175-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 180 skills](#️-all-180-skills) · [**⭐ star the repo**](https://github.com/mohitagw15856/pm-claude-skills/stargazers) so others find it.
 
 ---
 
 ## 🔄 One library, the whole professional workflow
 
-These 175 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 180 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
@@ -84,7 +84,7 @@ 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 175 skills**](#️-all-175-skills) grouped by profession.
+> New here? Start with the [**top-tier skills**](#️-skill-tiers--start-with-the-strongest), or jump straight to [**all 180 skills**](#️-all-180-skills) grouped by profession.
 
 ---
 
@@ -110,6 +110,8 @@ Individual skills are great. **Chaining** them is the superpower. A *recipe* run
 
 → Full detail and how to add your own in [**WORKFLOWS.md**](WORKFLOWS.md). Recipes run as slash commands in Claude Code, or over MCP via the `get_workflow` tool.
 
+**Got a coding question?** Just [**❓ Ask**](https://mohitagw15856.github.io/pm-claude-skills/ask.html) — an error, a regex, a git mess, a dependency conflict, *"what does this code do?"* — and the right developer skill answers instantly (like StackOverflow, but the answer's already written), with a one-click path to the community [Q&A](https://github.com/mohitagw15856/pm-claude-skills/discussions) for a human follow-up.
+
 **Or build your own visually.** The [**Workflow Canvas**](https://mohitagw15856.github.io/pm-claude-skills/canvas.html) lets you drag any skills into a custom chain and run it in the browser — each step's output feeds the next. Like n8n, but for professional thinking. Don't know which skills to use? The [**✨ Auto-Agent**](https://mohitagw15856.github.io/pm-claude-skills/agent.html) takes a plain-English goal, **plans which skills to chain**, and runs them for you — each step feeding the next:
 
 [![Auto-Agent — a goal becomes a planned chain of skills that runs end to end](web/docs-assets/agent-demo.gif)](https://mohitagw15856.github.io/pm-claude-skills/agent.html)
@@ -178,7 +180,7 @@ Most skill repos are a folder of prompts. This one is a **system** — measured,
 
 | | **PM Skills** | Typical skill repo |
 |---|:---:|:---:|
-| Skills | **175**, across 18 professions | a handful → dozens, usually one domain |
+| Skills | **180**, across 18 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 |
@@ -203,7 +205,7 @@ 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 175 Skills](#️-all-175-skills)
+- [🗂️ All 180 Skills](#️-all-180-skills)
 - [📋 Changelog](#-changelog)
 - [🤝 Contributing](#-contributing--add-your-skill)
 - [🔗 Related Projects](#-related-projects)
@@ -218,7 +220,7 @@ Most skill repos are a folder of prompts. This one is a **system** — measured,
 npx pm-claude-skills add --agent claude     # or: codex · cursor · hermes · openclaw
 ```
 
-**Or one-line MCP** — make all 175 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 180 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
@@ -284,7 +286,7 @@ 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 175 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 180 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? |
 |---|---|---|
@@ -496,7 +498,7 @@ 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 17 professions beyond financial services. **The 175 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 17 professions beyond financial services. **The 180 skills here are the building blocks for agent templates outside of finance.**
 
 ### What is an agent template?
 
@@ -575,11 +577,11 @@ More templates will follow. If you want to contribute one, see the [template con
 
 ## 📋 Changelog
 
-**Latest: v22.3.0 — Monetization & a polished playground.** A Sponsors program, an embeddable "run this skill" widget, and a Pro/Teams page; plus a redesigned playground (⌘K palette, hero landing, favourites, light/dark, compare-models, save-as-image) and a README glow-up. Builds on **v22.2.0** (Studio, Auto-Agent, editor extension). Now **175 skills**, 15 eval-scored.
+**Latest: v23.0.0 — 180 skills + the Ask experience.** Five new developer skills (error decoder, regex builder, git troubleshooter, dependency resolver, code explainer), an **Ask** page (coding question → right skill answers instantly) and a community **Q&A**. Builds on **v22.3.0** (sponsors, embed widget, polished playground). Now **180 skills**, 20 eval-scored.
 
 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 175 skills) are in **[CHANGELOG.md](CHANGELOG.md)**.
+→ Earlier releases (v20 and before — the road from 6 to 180 skills) are in **[CHANGELOG.md](CHANGELOG.md)**.
 
 ---
 
@@ -628,7 +630,7 @@ If you're new, install `pm-essentials` and try a couple of Production-Ready skil
 
 ---
 
-## 🗂️ All 175 Skills
+## 🗂️ All 180 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/)**
 
@@ -636,7 +638,7 @@ Every skill, grouped by profession. **[Browse the full per-skill catalog → SKI
 |---|---|---|---|
 | 🛠️ Product Management | `pm-essentials` · `pm-discovery` · `pm-planning` · `pm-delivery` · `pm-strategy` · `pm-advanced` · `pm-rituals` | 37 | `/prd` · `/rice` |
 | 📣 Marketing & GTM | `pm-gtm` | 8 | `go-to-market` |
-| 👩‍💻 Engineering & Tech | `pm-engineering` | 38 | `incident-postmortem` |
+| 👩‍💻 Engineering & Tech | `pm-engineering` | 43 | `incident-postmortem` |
 | 🤝 Customer Success | `pm-cs` | 6 | `cs-health-scorecard` |
 | 📊 Data & Analytics | `pm-data` · `pm-analytics` | 6 | `metrics-framework` |
 | 🧑‍💼 Leadership & People | `pm-people` | 5 | `executive-update` |
@@ -659,7 +661,7 @@ Every skill, grouped by profession. **[Browse the full per-skill catalog → SKI
 
 ## ❤️ Sponsor This Work
 
-Building and maintaining 175 skills across 26 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 180 skills across 26 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 **174 skills** to:
+Currently exporting **180 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.
 
-174 skills exported. Copy a `.mdc rule` into the tool to use it.
+180 skills exported. Copy a `.mdc rule` into the tool to use it.
 
 | Skill | Bundle | Path |
 |---|---|---|
@@ -29,6 +29,7 @@
 | CI/CD Playbook | `pm-engineering` | `pm-engineering/cicd-playbook/cicd-playbook.md` |
 | Claude Superpowers | `pm-engineering` | `pm-engineering/claude-superpowers/claude-superpowers.md` |
 | Clinical Case Summary | `pm-research` | `pm-research/clinical-case-summary/clinical-case-summary.md` |
+| Code Explainer | `pm-engineering` | `pm-engineering/code-explainer/code-explainer.md` |
 | Code Review Checklist | `pm-engineering` | `pm-engineering/code-review-checklist/code-review-checklist.md` |
 | Cohort Analysis | `pm-data` | `pm-data/cohort-analysis/cohort-analysis.md` |
 | Community Management Playbook | `pm-social` | `pm-social/community-management-playbook/community-management-playbook.md` |
@@ -51,6 +52,7 @@
 | Database Schema Design | `pm-engineering` | `pm-engineering/database-schema-design/database-schema-design.md` |
 | Debugging Log Analyser | `pm-engineering` | `pm-engineering/debugging-log-analyser/debugging-log-analyser.md` |
 | Dependency Audit | `pm-engineering` | `pm-engineering/dependency-audit/dependency-audit.md` |
+| Dependency Conflict Resolver | `pm-engineering` | `pm-engineering/dependency-conflict-resolver/dependency-conflict-resolver.md` |
 | Design Critique | `pm-design` | `pm-design/design-critique/design-critique.md` |
 | Design Handoff Brief | `pm-advanced` | `pm-advanced/design-handoff-brief/design-handoff-brief.md` |
 | Design System Audit | `pm-design` | `pm-design/design-system-audit/design-system-audit.md` |
@@ -64,6 +66,7 @@
 | Employee Engagement Survey | `pm-hr` | `pm-hr/employee-engagement-survey/employee-engagement-survey.md` |
 | Engineering Hiring Rubric | `pm-engineering` | `pm-engineering/engineering-hiring-rubric/engineering-hiring-rubric.md` |
 | Engineering Weekly Report | `pm-engineering` | `pm-engineering/engineering-weekly-report/engineering-weekly-report.md` |
+| Error Decoder | `pm-engineering` | `pm-engineering/error-decoder/error-decoder.md` |
 | Executive Summary | `pm-cross` | `pm-cross/executive-summary/executive-summary.md` |
 | Executive Update | `pm-strategy` | `pm-strategy/executive-update/executive-update.md` |
 | Experiment Designer | `pm-advanced` | `pm-advanced/experiment-designer/experiment-designer.md` |
@@ -81,6 +84,7 @@
 | Figma Variant Matrix | `pm-figma` | `pm-figma/figma-variant-matrix/figma-variant-matrix.md` |
 | Financial Due Diligence | `pm-finance` | `pm-finance/financial-due-diligence/financial-due-diligence.md` |
 | Financial Model Narrative | `pm-finance` | `pm-finance/financial-model-narrative/financial-model-narrative.md` |
+| Git Troubleshooter | `pm-engineering` | `pm-engineering/git-troubleshooter/git-troubleshooter.md` |
 | Go-To-Market | `pm-gtm` | `pm-gtm/go-to-market/go-to-market.md` |
 | Go-to-Market Planner | `pm-delivery` | `pm-delivery/go-to-market-planner/go-to-market-planner.md` |
 | Grant Proposal | `pm-cross` | `pm-cross/grant-proposal/grant-proposal.md` |
@@ -131,7 +135,9 @@
 | Proposal Writer | `pm-sales` | `pm-sales/proposal-writer/proposal-writer.md` |
 | QBR Deck | `pm-cs` | `pm-cs/qbr-deck/qbr-deck.md` |
 | RACI Matrix | `pm-operations` | `pm-operations/raci-matrix/raci-matrix.md` |
+| Red-Team Review | `pm-cross` | `pm-cross/red-team-review/red-team-review.md` |
 | Redundancy Consultation | `pm-hr` | `pm-hr/redundancy-consultation/redundancy-consultation.md` |
+| 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` |
 | Retention Analysis | `pm-analytics` | `pm-analytics/retention-analysis/retention-analysis.md` |

package/exports/aider/pm-cross/red-team-review/red-team-review.md

@@ -0,0 +1,58 @@
+# Red-Team Review Skill
+
+Pressure-test the user's plan the way a hostile, expert room would — *before* reality does. The goal is not to be negative; it's to surface the failure modes the author is too close to see, then convert them into concrete fixes.
+
+## Working from a brief
+
+Always deliver the full review even if the plan is thin. Where detail is missing, infer the most likely version from context and the domain, and mark inferred assumptions as *(assumed — confirm)*. Never refuse for lack of detail and never leave bracketed placeholders.
+
+## Input
+
+The plan/strategy/PRD/launch to stress-test, plus (if given) the goal, audience, timeline, and constraints. If the objective isn't stated, infer it and say so.
+
+## Output Structure
+
+### 1. What I'm reviewing
+One-sentence restatement of the plan and the outcome it's betting on. (If you had to infer the objective, say so.)
+
+### 2. The room — persona critiques
+Channel each persona in their own voice. For each: their single sharpest challenge + the one question the plan must answer. Pick the 5–6 most relevant of:
+
+- **🧮 The skeptical CFO** — ROI, cost, opportunity cost, "what do we stop doing?"
+- **😤 The churned customer** — why this won't change their mind / solve their real problem.
+- **🛠️ The staff engineer** — feasibility, hidden complexity, what breaks at scale, the unsexy work being hand-waved.
+- **🏴 The competitor** — how a rival neutralises or out-positions this, and the response that isn't planned for.
+- **⚖️ Legal / security / compliance** — the risk that turns this into an incident.
+- **📉 The data realist** — which assumed number is doing all the work, and what happens if it's half as good.
+- **🧭 The exec sponsor** — "why now, why us, and why isn't this just a feature?"
+
+### 3. Top blind spots (ranked)
+The 3–5 most dangerous gaps, ordered by **likelihood × impact**. For each: the risk, why it's easy to miss, and an early-warning signal that it's happening.
+
+### 4. Pre-mortem
+"It's 12 months later and this failed. Write the post-mortem headline." Give the 2–3 most plausible failure narratives in one or two sentences each.
+
+### 5. Make it bulletproof
+The specific, prioritised changes that would most reduce risk — what to add, cut, de-risk, or test first. Separate **do before committing** from **monitor after launch**.
+
+## Tone Guidelines
+
+- Be specific and fair, not contrarian for its own right — every critique names a concrete failure mode, not a vibe.
+- Attack the plan, not the person. End on how to strengthen it.
+- Prioritise ruthlessly: one fatal flaw beats ten nitpicks.
+
+## Quality Checks
+
+- [ ] Each persona raises a *distinct*, specific challenge (no overlap, no generic "have you considered…")
+- [ ] The top-risks list is ranked by likelihood × impact, not listed flat
+- [ ] The pre-mortem names plausible, concrete failure narratives
+- [ ] Every major risk has at least one recommended fix or test
+- [ ] The single most dangerous assumption is explicitly called out
+
+## Anti-Patterns
+
+- [ ] Do not produce vague, generic objections ("it might be risky") — name the specific failure mode and trigger
+- [ ] Do not only criticise — every review must end with concrete, prioritised ways to strengthen the plan
+- [ ] Do not give all personas the same critique reworded — each lens must find something the others miss
+- [ ] Do not soften the most dangerous risk to be polite — surface it first and plainly
+- [ ] Do not invent facts about the plan — infer plausibly and label assumptions as *(assumed)*

package/exports/aider/pm-engineering/code-explainer/code-explainer.md

@@ -0,0 +1,39 @@
+# Code Explainer Skill
+
+Make unfamiliar code understandable — fast — without dumbing it down.
+
+## Working from a brief
+
+Infer the language and intent from the code itself; label assumptions *(assumed — confirm)*. Always produce a complete explanation even from a fragment. Match depth to the apparent level of the question.
+
+## Input
+
+The code snippet or file, plus (if given) the language, the reader's level, and what they're trying to understand. Infer the rest.
+
+## Output Structure
+
+### In one line
+What this code does, in a single sentence a busy reader can repeat.
+
+### Step by step
+A walkthrough of the logic in order — group by block/function. Explain *why*, not just *what*, for anything non-trivial. Reference line ranges where helpful.
+
+### Worth knowing
+The non-obvious bits: clever tricks, gotchas, side effects, complexity, dependencies, or assumptions the code makes.
+
+### Anything off?
+Bugs, edge cases, or smells you noticed while reading — with the fix. (If it's clean, say so.)
+
+## Quality Checks
+
+- [ ] The one-line summary stands alone
+- [ ] The walkthrough explains *why*, not just restating the code in words
+- [ ] Non-obvious behaviour (side effects, complexity, edge cases) is surfaced
+- [ ] Any bug/smell spotted is flagged with a fix
+
+## Anti-Patterns
+
+- [ ] Do not narrate line-by-line in English ("this line sets x to 5") — explain intent and structure
+- [ ] Do not skip the gotchas — the value is in the non-obvious parts
+- [ ] Do not assume expert level if the question reads like a beginner's (or vice-versa)
+- [ ] Do not ignore a bug you can see just because you weren't asked to review it

package/exports/aider/pm-engineering/dependency-conflict-resolver/dependency-conflict-resolver.md

@@ -0,0 +1,40 @@
+# Dependency Conflict Resolver Skill
+
+Untangle "could not resolve dependency" hell into a clear, ranked plan.
+
+## Working from a brief
+
+Infer the package manager and ecosystem from the error or files mentioned; label assumptions *(assumed — confirm)*. Always deliver a concrete resolution path even from just the error text.
+
+## Input
+
+The install error / conflict output, plus (if given) the manifest (package.json, requirements.txt, go.mod…) and lockfile, and the manager. Infer what's missing.
+
+## Output Structure
+
+### The conflict
+Plain-English: package **A** needs X of **C**, package **B** needs Y of **C**, and they can't both be satisfied (name the actual packages/versions from the input).
+
+### Options (ranked by safety)
+1. **Safest** — e.g. align versions, upgrade the constrained package, or find a compatible range. Exact command.
+2. **Pragmatic** — e.g. an override/resolution (`overrides`, `resolutions`, constraints file) with the exact snippet — and the risk it carries.
+3. **Last resort** — e.g. `--legacy-peer-deps` / `--force` — clearly flagged as masking the problem, not fixing it.
+
+Give the exact commands/edits for each, and a recommendation of which to pick and why.
+
+### Verify & prevent
+How to confirm the fix (`npm ls <pkg>`, a clean reinstall, the build), and one habit to avoid recurrence (lockfile committed, renovate/dependabot, version pinning policy).
+
+## Quality Checks
+
+- [ ] Names the actual conflicting packages and versions from the input
+- [ ] Options are ranked by safety with the trade-off of each stated
+- [ ] `--force`/`--legacy-peer-deps`-style escapes are flagged as masking, not fixing
+- [ ] Includes a verification step
+
+## Anti-Patterns
+
+- [ ] Do not lead with `--force` / `--legacy-peer-deps` — it hides the conflict and breaks later
+- [ ] Do not delete the lockfile as the first move — explain what that actually does
+- [ ] Do not give a single fix when several are viable — rank them with trade-offs
+- [ ] Do not skip verifying the resolution actually installs/builds

package/exports/aider/pm-engineering/error-decoder/error-decoder.md

@@ -0,0 +1,39 @@
+# Error Decoder Skill
+
+Turn a scary error into a clear answer — the way a senior engineer would read it over your shoulder.
+
+## Working from a brief
+
+You'll often get just an error string or a partial stack trace, with no surrounding code. **Always deliver a complete diagnosis anyway** — infer the language/framework and the likely context from the error itself, and mark inferences as *(assumed — confirm)*. Never refuse for missing context and never leave bracketed placeholders.
+
+## Input
+
+The error message, stack trace, or crash output — plus (if given) the language/runtime, the relevant code, and what the user was doing. Infer anything missing.
+
+## Output Structure
+
+### 1. What it means
+One or two plain-English sentences: what this error is actually saying (translate the jargon).
+
+### 2. Most likely cause
+The top cause given the message, ranked if there are several plausible ones. Point at the exact line/frame in the trace that matters and say why.
+
+### 3. The fix
+Concrete, copy-pasteable steps or code. If the cause is uncertain, give the highest-probability fix first, then the fallback.
+
+### 4. Why it happened / prevent it
+One line on the underlying reason and a guardrail (a check, a type, a test, a config) that stops it recurring.
+
+## Quality Checks
+
+- [ ] The explanation translates the error into plain language (no restating the raw message)
+- [ ] The cause points to a specific line/frame or condition, not "something went wrong"
+- [ ] The fix is concrete and runnable, not "check your code"
+- [ ] Assumptions about language/context are labelled
+
+## Anti-Patterns
+
+- [ ] Do not just paraphrase the error — explain what it *means* and why it happened
+- [ ] Do not give a generic "try reinstalling" answer when the trace points to a specific cause
+- [ ] Do not invent file names or code that wasn't given — infer and label, or ask for the one missing thing only if truly blocking
+- [ ] Do not stop at the fix — always add the one prevention step

package/exports/aider/pm-engineering/git-troubleshooter/git-troubleshooter.md

@@ -0,0 +1,41 @@
+# Git Troubleshooter Skill
+
+Get the user un-stuck from git — calmly, safely, and without destroying work.
+
+## Working from a brief
+
+Infer the current state from what the user describes (and typical git output); label assumptions *(assumed — confirm)*. Always give a concrete command sequence. If a step is destructive, say so loudly *before* it.
+
+## Input
+
+What happened / what they want (e.g. "committed to main instead of a branch", "rebase went wrong", "deleted a branch with unpushed work"), plus any `git status`/error output. Infer the rest.
+
+## Output Structure
+
+### Diagnosis
+One or two lines: what state the repo is in and why the user is stuck.
+
+### Fix — run these in order
+A numbered list of exact commands, each with a one-line note of what it does:
+```
+1. git reflog                # find the lost commit's SHA
+2. git checkout -b rescue <SHA>   # recover it onto a new branch
+```
+Prefer **non-destructive** routes (branch, reflog, `--soft`) over destructive ones. Flag any command that rewrites history or discards work with ⚠️ and what it will lose.
+
+### Safety net
+How to undo if the fix doesn't do what they expected (usually `git reflog` + reset to the prior HEAD), plus a one-line habit to avoid the situation next time.
+
+## Quality Checks
+
+- [ ] The command sequence is exact and ordered (copy-pasteable)
+- [ ] Destructive commands are clearly marked with what they destroy
+- [ ] A non-destructive option is offered first where one exists
+- [ ] A recovery/undo path is included
+
+## Anti-Patterns
+
+- [ ] Do not suggest `git push --force`, `reset --hard`, or `clean -fd` without a ⚠️ and a safer alternative first
+- [ ] Do not give commands without saying what each one does
+- [ ] Do not assume the remote state — ask or label it if it changes the safe path
+- [ ] Do not skip `git reflog` when work might be recoverable — it usually is

package/exports/aider/pm-engineering/regex-builder/regex-builder.md

@@ -0,0 +1,46 @@
+# Regex Builder & Explainer Skill
+
+Produce correct, readable regular expressions — and explain them so the user actually understands what they're shipping.
+
+## Working from a brief
+
+Infer the regex flavor (JavaScript/PCRE/Python/Go) from context; if unstated, default to one and say so *(assumed — confirm)*. Always deliver a working pattern and tests even from a loose description. Never leave placeholders.
+
+## Two modes
+- **Build:** the user describes what to match → produce the regex.
+- **Explain:** the user pastes a regex → break it down.
+Detect which from the input.
+
+## Output Structure
+
+### Pattern
+The regex in a code block, plus the **flavor** and any **flags** (e.g. `i`, `g`, `m`) and why.
+
+### Breakdown
+A token-by-token table or list: each part of the pattern and what it matches.
+
+| Token | Matches |
+|-------|---------|
+| `^` | start of string |
+| … | … |
+
+### Test cases
+- ✅ **Matches:** 3–5 strings it should match
+- ❌ **Rejects:** 3–5 strings it should *not* match (include the tricky near-misses)
+
+### Notes
+Edge cases, catastrophic-backtracking risks, anchoring, Unicode, and a simpler alternative if the regex is getting unwieldy (sometimes "don't use regex" is the right answer — say so).
+
+## Quality Checks
+
+- [ ] The pattern actually passes the listed "matches" and rejects the "rejects"
+- [ ] Flavor and flags are stated
+- [ ] The breakdown covers every token, not just the interesting ones
+- [ ] Edge cases / backtracking risks are flagged
+
+## Anti-Patterns
+
+- [ ] Do not give a regex with no test cases — always prove it
+- [ ] Do not ignore the flavor — `\d`, lookbehind, and named groups differ across engines
+- [ ] Do not produce an unreadable one-liner when a commented/verbose version or a non-regex approach is clearer
+- [ ] Do not silently assume anchoring — state whether it matches the whole string or a substring

package/exports/aider/pm-gtm/go-to-market/go-to-market.md

@@ -2,9 +2,12 @@
 
 This skill produces a complete go-to-market asset pack for a product, feature, or initiative. It follows Geoffrey Moore's positioning framework and structures all outputs for use in sales decks, landing pages, launch emails, and internal alignment docs.
 
-## Required Inputs
+## Working from a brief
+
+You will often get a short brief without every detail. **Always deliver the full GTM pack anyway** — do not stop to ask questions and do not leave bracketed placeholders like `[ADD PROOF POINT]` or `[Technical capability]`. Where a detail is missing (differentiators, proof points, features), infer specific, realistic ones from the product description and the target customer, and mark anything inferred as *(assumed — confirm)*. A concrete, labelled assumption is always better than a blank.
+
+## Inputs (infer any not provided — label assumptions)
 
-Ask the user for these if not provided:
 - **Product/feature name**
 - **One-line description** (what it does, technically)
 - **Target customer** (role, company size, industry if relevant)
@@ -34,7 +37,7 @@ Generate 3–5 messaging pillars. Each pillar must include:
 
 - **Pillar name** (2–4 words, bold)
 - **One-sentence summary** of what this pillar claims
-- **2–3 proof points** (specific, evidence-backed where possible — if the user hasn't provided data, flag with [ADD PROOF POINT])
+- **2–3 proof points** (specific and evidence-backed; if no data was provided, infer a realistic proof point and mark it *(assumed)* — never leave a bare placeholder)
 - **Example use in copy** (one sentence as it would appear in a landing page or deck)
 
 Pillars should be distinct — avoid overlap. Each pillar should be defensible against the primary competitor.
@@ -52,7 +55,7 @@ Produce a two-column table:
 Rules:
 - Never list a feature without a corresponding benefit
 - Benefits should reference the target customer's workflow or pain point
-- Aim for 6–12 rows; ask the user for more features if they've only given 1–2
+- Aim for 6–12 rows; if only 1–2 features were given, infer the rest plausibly from the product description
 - Avoid jargon in the benefit column — write as if explaining to a buyer, not an engineer
 
 ---

package/exports/aider/pm-planning/okr-builder/okr-builder.md

@@ -2,6 +2,10 @@
 
 Write ambitious, measurable OKRs that connect product work to company strategy. Avoid vanity metrics, output-focused key results, and objectives that sound like task lists.
 
+## Working from a brief
+
+You will often get a short brief without every detail (no baselines, no exact numbers). **Always deliver a complete, specific OKR set anyway** — do not stop to ask questions and do not leave bracketed placeholders like `[target]`. Where a baseline or number is missing, infer a realistic value from the brief and the domain, and mark it *(assumed — confirm)*. A clearly-labelled assumed baseline (e.g. "activation 40% *(assumed)* → 60%") is always better than a blank or an invented-as-fact figure.
+
 ## OKR Fundamentals
 
 **Objective:** Qualitative, inspiring, time-bound. Answers "where are we going?"
@@ -55,18 +59,17 @@ At quarter end, score each KR:
 - 0.4–0.6 = Made progress but missed
 - 0.0–0.3 = Missed — needs retrospective discussion
 
-## Required Inputs
+## Inputs (infer any not provided — label assumptions)
 
-Ask the user for these if not provided:
 - **Team or individual** the OKRs are for
 - **Quarter and year**
-- **Company or product North Star metric** (OKRs should connect to this)
+- **Company or product North Star metric** (OKRs should connect to this — if not given, infer a plausible one and label it *(assumed)*)
 - **Top 3 priorities or goals for this quarter** (rough notes are fine)
 - **Any existing OKRs to review or improve** (optional)
 
 ## Guidelines
 
-- Always ask for the company-level or product-level North Star metric before writing OKRs
+- Connect OKRs to the company/product North Star; if it isn't given, infer a plausible one and label it *(assumed)* rather than asking
 - Recommend no more than 3 objectives per team per quarter
 - If user provides output-based goals, always reframe as outcomes
 - Include a "health check" section flagging which KRs have no current baseline data

package/exports/aider/pm-planning/roadmap-narrative/roadmap-narrative.md

@@ -2,9 +2,12 @@
 
 Convert a ranked list of product initiatives into a clear, strategic narrative that connects individual items to company goals and communicates a coherent product direction.
 
-## Required Inputs
+## Working from a brief
+
+You will often get a short brief (a few themes, an audience) without a full initiative list or OKRs. **Always deliver the complete narrative anyway** — do not stop to ask questions and do not leave bracketed placeholders like `[Theme Name]`. Where detail is missing, infer specific, realistic themes, initiatives, and metrics from the brief and the domain, and mark any inferred fact or number as *(assumed — confirm)*. Fill every section with concrete content, not template brackets.
+
+## Inputs (infer any not provided — label assumptions)
 
-Ask the user for these if not provided:
 - **Prioritised initiative list** (with rough timelines or quarters)
 - **Company OKRs or strategic priorities** (to connect roadmap to company goals)
 - **Audience** (all-hands, board, investors, sales team — changes tone and depth)

package/exports/chatgpt/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.
 
-174 skills exported. Copy a `SYSTEM_PROMPT.md` into the tool to use it.
+180 skills exported. Copy a `SYSTEM_PROMPT.md` into the tool to use it.
 
 | Skill | Bundle | Path |
 |---|---|---|
@@ -29,6 +29,7 @@
 | CI/CD Playbook | `pm-engineering` | `pm-engineering/cicd-playbook/SYSTEM_PROMPT.md` |
 | Claude Superpowers | `pm-engineering` | `pm-engineering/claude-superpowers/SYSTEM_PROMPT.md` |
 | Clinical Case Summary | `pm-research` | `pm-research/clinical-case-summary/SYSTEM_PROMPT.md` |
+| Code Explainer | `pm-engineering` | `pm-engineering/code-explainer/SYSTEM_PROMPT.md` |
 | Code Review Checklist | `pm-engineering` | `pm-engineering/code-review-checklist/SYSTEM_PROMPT.md` |
 | Cohort Analysis | `pm-data` | `pm-data/cohort-analysis/SYSTEM_PROMPT.md` |
 | Community Management Playbook | `pm-social` | `pm-social/community-management-playbook/SYSTEM_PROMPT.md` |
@@ -51,6 +52,7 @@
 | Database Schema Design | `pm-engineering` | `pm-engineering/database-schema-design/SYSTEM_PROMPT.md` |
 | Debugging Log Analyser | `pm-engineering` | `pm-engineering/debugging-log-analyser/SYSTEM_PROMPT.md` |
 | Dependency Audit | `pm-engineering` | `pm-engineering/dependency-audit/SYSTEM_PROMPT.md` |
+| Dependency Conflict Resolver | `pm-engineering` | `pm-engineering/dependency-conflict-resolver/SYSTEM_PROMPT.md` |
 | Design Critique | `pm-design` | `pm-design/design-critique/SYSTEM_PROMPT.md` |
 | Design Handoff Brief | `pm-advanced` | `pm-advanced/design-handoff-brief/SYSTEM_PROMPT.md` |
 | Design System Audit | `pm-design` | `pm-design/design-system-audit/SYSTEM_PROMPT.md` |
@@ -64,6 +66,7 @@
 | Employee Engagement Survey | `pm-hr` | `pm-hr/employee-engagement-survey/SYSTEM_PROMPT.md` |
 | Engineering Hiring Rubric | `pm-engineering` | `pm-engineering/engineering-hiring-rubric/SYSTEM_PROMPT.md` |
 | Engineering Weekly Report | `pm-engineering` | `pm-engineering/engineering-weekly-report/SYSTEM_PROMPT.md` |
+| Error Decoder | `pm-engineering` | `pm-engineering/error-decoder/SYSTEM_PROMPT.md` |
 | Executive Summary | `pm-cross` | `pm-cross/executive-summary/SYSTEM_PROMPT.md` |
 | Executive Update | `pm-strategy` | `pm-strategy/executive-update/SYSTEM_PROMPT.md` |
 | Experiment Designer | `pm-advanced` | `pm-advanced/experiment-designer/SYSTEM_PROMPT.md` |
@@ -81,6 +84,7 @@
 | Figma Variant Matrix | `pm-figma` | `pm-figma/figma-variant-matrix/SYSTEM_PROMPT.md` |
 | Financial Due Diligence | `pm-finance` | `pm-finance/financial-due-diligence/SYSTEM_PROMPT.md` |
 | Financial Model Narrative | `pm-finance` | `pm-finance/financial-model-narrative/SYSTEM_PROMPT.md` |
+| Git Troubleshooter | `pm-engineering` | `pm-engineering/git-troubleshooter/SYSTEM_PROMPT.md` |
 | Go-To-Market | `pm-gtm` | `pm-gtm/go-to-market/SYSTEM_PROMPT.md` |
 | Go-to-Market Planner | `pm-delivery` | `pm-delivery/go-to-market-planner/SYSTEM_PROMPT.md` |
 | Grant Proposal | `pm-cross` | `pm-cross/grant-proposal/SYSTEM_PROMPT.md` |
@@ -131,7 +135,9 @@
 | Proposal Writer | `pm-sales` | `pm-sales/proposal-writer/SYSTEM_PROMPT.md` |
 | QBR Deck | `pm-cs` | `pm-cs/qbr-deck/SYSTEM_PROMPT.md` |
 | RACI Matrix | `pm-operations` | `pm-operations/raci-matrix/SYSTEM_PROMPT.md` |
+| Red-Team Review | `pm-cross` | `pm-cross/red-team-review/SYSTEM_PROMPT.md` |
 | Redundancy Consultation | `pm-hr` | `pm-hr/redundancy-consultation/SYSTEM_PROMPT.md` |
+| Regex Builder & Explainer | `pm-engineering` | `pm-engineering/regex-builder/SYSTEM_PROMPT.md` |
 | Renewal Playbook | `pm-cs` | `pm-cs/renewal-playbook/SYSTEM_PROMPT.md` |
 | Research Protocol | `pm-research` | `pm-research/research-protocol/SYSTEM_PROMPT.md` |
 | Retention Analysis | `pm-analytics` | `pm-analytics/retention-analysis/SYSTEM_PROMPT.md` |