@c0x12c/ai-toolkit 1.15.0

package/.claude-plugin/marketplace.json

@@ -0,0 +1,16 @@
+{
+  "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
+  "name": "spartan-marketplace",
+  "description": "Spartan AI Toolkit — engineering discipline layer for Claude Code",
+  "owner": {
+    "name": "Spartan Stratos"
+  },
+  "plugins": [
+    {
+      "name": "ai-toolkit",
+      "description": "5 workflows, 69 commands, 21 rules, 29 skills, 9 agents — organized in 12 packs with dependencies",
+      "source": "./toolkit",
+      "version": "1.15.0"
+    }
+  ]
+}

package/.claude-plugin/plugin.json

@@ -0,0 +1,12 @@
+{
+  "name": "ai-toolkit",
+  "version": "1.14.0",
+  "description": "Engineering discipline layer for Claude Code — 5 workflows, 69 commands, 21 rules, 29 skills, 9 agents organized in 12 packs",
+  "author": {
+    "name": "Khoa Tran",
+    "url": "https://github.com/c0x12c"
+  },
+  "repository": "https://github.com/c0x12c/ai-toolkit",
+  "license": "MIT",
+  "keywords": ["engineering", "workflow", "kotlin", "micronaut", "nextjs", "product-thinking"]
+}

package/README.md

@@ -0,0 +1,439 @@
+# Spartan AI Toolkit
+
+> Workflow-first engineering discipline for AI coding tools. Workflows solve problems end-to-end. Skills provide knowledge at each step. Agent memory carries context across sessions.
+
+---
+
+## Install
+
+Three ways to install. Pick one.
+
+### Option 1: npx (recommended)
+
+```bash
+npx @c0x12c/ai-toolkit@latest
+```
+
+Interactive menu — pick your AI tool and packs. Works out of the box.
+
+```bash
+# Or specify packs directly
+npx @c0x12c/ai-toolkit@latest --packs=backend-micronaut,product
+
+# Install everything
+npx @c0x12c/ai-toolkit@latest --all
+
+# Install for Cursor instead of Claude Code
+npx @c0x12c/ai-toolkit@latest --agent=cursor
+```
+
+**Supported agents:** `claude-code` (default), `cursor`, `windsurf`, `codex`, `copilot`
+
+### Option 2: Setup script
+
+```bash
+git clone https://github.com/c0x12c/ai-toolkit.git
+cd ai-toolkit/toolkit
+chmod +x scripts/setup.sh
+./scripts/setup.sh --global
+```
+
+### Option 3: Claude Code plugin
+
+Search for **"Spartan AI Toolkit"** in the Claude Code plugin marketplace.
+
+### Global vs Local
+
+- `--global` installs to `~/.claude/` — works across all projects (default)
+- `--local` installs to `./.claude/` — only this project
+
+After install, open any project, run `claude`, then type `/spartan`.
+
+---
+
+## Demo: Web-to-PRD
+
+Scan a live web app, extract every feature, generate a structured PRD with epics and stories, then export to Notion.
+
+```
+/spartan:web-to-prd "https://screensdesign.com"
+```
+
+![Web-to-PRD scanning screensdesign.com](../docs/images/web-to-prd-demo.png)
+
+Uses Playwright MCP (browser control) + Notion MCP (export). Auto-installs prerequisites, handles login, and asks for confirmation at each step.
+
+---
+
+## How to Use
+
+### The core workflow
+
+Every feature follows the same pipeline. Skip steps that don't apply.
+
+```
+/spartan:spec → /spartan:ux → /spartan:plan → /spartan:build → /spartan:pr-ready
+      ↑             ↑               ↑              ↑ + 3.5           ↑
+    Gate 1     Design Gate       Gate 2          Gate 3           Gate 4
+```
+
+| Step | What happens |
+|------|-------------|
+| `spec` | Interactive Q&A → saved spec → Gate 1 checks quality |
+| `design` | Design doc + dual-agent review (skip for backend-only) |
+| `plan` | Architecture + task breakdown from spec → Gate 2 |
+| `build` | TDD task by task, picks up saved spec/plan |
+| `gate-review` | Builder + reviewer agent both must accept |
+| `pr-ready` | Rebase, test, lint, create PR |
+
+**Bigger work?** Use `/spartan:epic` to break it into features first, then run the pipeline for each one. For multi-week projects, use `/spartan:project new` with milestones and phases.
+
+**Skills load automatically** based on your stack. Kotlin files → `kotlin-best-practices`. React components → `ui-ux-pro-max`. Migrations → `database-patterns`. You don't pick them.
+
+**Agent memory** (`.planning/`, `.memory/`) carries specs, plans, decisions, and patterns across sessions. The AI builds on what it already knows instead of starting from scratch.
+
+**Rules** load every session with zero tokens. They enforce coding standards silently.
+
+---
+
+## Pick Your Packs
+
+Packs group commands, rules, skills, and agents by use case. **Core is always installed.** Pick the rest based on what you're building.
+
+### "I'm building a Kotlin + Micronaut backend"
+
+```bash
+npx @c0x12c/ai-toolkit@latest --packs=backend-micronaut
+```
+
+This pulls in `backend-micronaut` + its dependencies (`database` and `shared-backend` auto-included). You get migration commands, API design rules, Kotlin coding standards, test patterns, and two expert agents.
+
+### "I'm building a React + Next.js frontend"
+
+```bash
+npx @c0x12c/ai-toolkit@latest --packs=frontend-react
+```
+
+You get Next.js scaffolding, Figma-to-code, E2E testing setup, frontend review, and the UI/UX design skill.
+
+### "Full-stack Kotlin + Next.js"
+
+```bash
+npx @c0x12c/ai-toolkit@latest --packs=backend-micronaut,frontend-react
+```
+
+### "I'm managing AWS infrastructure with Terraform"
+
+```bash
+npx @c0x12c/ai-toolkit@latest --packs=infrastructure
+```
+
+You get Terraform scaffolding (ECS + EKS), module creation, security audits, drift detection, cost optimization, and two infrastructure agents. Rules enforce naming, state management, provider placement, and security patterns.
+
+### "I'm running a multi-week project"
+
+```bash
+npx @c0x12c/ai-toolkit@latest --packs=backend-micronaut,project-mgmt
+```
+
+Adds project lifecycle, phases, workstreams, and GSD v5 wave execution on top of your backend tools.
+
+### "I'm exploring startup ideas"
+
+```bash
+npx @c0x12c/ai-toolkit@latest --packs=research
+```
+
+Research pack pulls in `product` as a dependency. You get brainstorming, validation, market research, competitor teardowns, pitch materials, and investor outreach.
+
+### "Give me everything"
+
+```bash
+npx @c0x12c/ai-toolkit@latest --all
+```
+
+---
+
+## All Packs
+
+| Pack | Category | Depends on | What you get |
+|------|----------|------------|--------------|
+| **core** | Core | — | Always installed. Workflows (build, fix, onboard), spec, plan, gate-review, pr-ready, daily, safety commands, phase-reviewer agent |
+| **backend-micronaut** | Backend | database, shared-backend | Kotlin service scaffold, code review, testcontainers, API/DB/Kotlin rules, 5 skills, 2 agents |
+| **backend-nodejs** | Backend | database, shared-backend | Coming soon |
+| **backend-python** | Backend | database, shared-backend | Coming soon |
+| **frontend-react** | Frontend | — | Design workflow, Next.js scaffold, Figma-to-code, E2E, frontend review, UI/UX + design-workflow skills, design-critic agent |
+| **project-mgmt** | Planning | — | Epics, project lifecycle, phases, workstreams, GSD upgrade, forensics, brownfield, codebase mapping |
+| **product** | Planning | — | Think-before-build, validate, teardown, interview, lean canvas, brainstorm |
+| **infrastructure** | Ops | — | Terraform + AWS: scaffold, modules, review, plan, deploy, import, drift, cost, security. 7 rules, 5 skills, 2 agents |
+| **ops** | Ship | — | Deploy + env-setup |
+| **research** | Research | product | Startup + research workflows, kickoff to investor outreach, 10 skills, 2 agents |
+
+Hidden packs (`database`, `shared-backend`) get pulled in as dependencies — you don't pick them directly.
+
+---
+
+## Commands
+
+All commands start with `/spartan:` (e.g., `/spartan:spec "feature"`).
+
+Type `/spartan` to get the smart router — it asks what you need and picks the right command.
+
+### Workflows (core + research packs)
+| Command | What it does |
+|---------|-------------|
+| `build [mode] [feature]` | Build a feature end-to-end (backend, frontend, or auto-detect) |
+| `fix [symptom]` | Find and fix a bug with structured investigation |
+| `research [topic]` | Deep research with source tracking and report |
+| `startup [idea]` | Full startup pipeline: brainstorm to investor-ready |
+| `onboard` | Understand a new codebase and set up tooling |
+
+### Core (always installed)
+| Command | What it does |
+|---------|-------------|
+| `spec "feature"` | Write a feature spec — saves to `.planning/specs/` |
+| `plan "feature"` | Write implementation plan from spec — saves to `.planning/plans/` |
+| `gate-review [phase]` | Dual-agent review (Gate 3.5) — builder + reviewer both accept |
+| `daily` | Standup summary from git history |
+| `pr-ready` | Full checklist before creating any PR |
+| `init-project` | Auto-generate CLAUDE.md from codebase scan |
+| `context-save` | Save session state to resume later |
+| `update` | Check for toolkit updates |
+| `careful` | Warn before destructive ops |
+| `freeze <dir>` | Lock edits to one directory |
+| `unfreeze` | Remove directory lock |
+| `guard <dir>` | careful + freeze combined |
+
+### Backend (backend-micronaut pack)
+| Command | What it does |
+|---------|-------------|
+| `kotlin-service "name"` | Scaffold new Micronaut microservice |
+| `review` | PR review with Kotlin/Micronaut conventions |
+| `testcontainer "type"` | Setup Testcontainers integration testing |
+| `migration "desc"` | Create Flyway database migration |
+
+### Frontend (frontend-react pack)
+| Command | What it does |
+|---------|-------------|
+| `design "feature"` | Design workflow with dual-agent review (Design Gate) |
+| `next-app "name"` | Scaffold new Next.js app |
+| `next-feature "name"` | Add feature to existing Next.js app |
+| `fe-review` | PR review with Next.js conventions |
+| `figma-to-code "url"` | Figma design to production React |
+| `e2e "feature"` | Setup Playwright E2E testing |
+
+### Planning (project-mgmt pack)
+| Command | What it does |
+|---------|-------------|
+| `epic "name"` | Break big work into ordered features |
+| `project [action]` | Large project lifecycle (new, status, milestone) |
+| `phase [action]` | Phase lifecycle (discuss, plan, execute, verify) |
+| `workstreams [action]` | Parallel work tracks |
+| `gsd-upgrade` | Upgrade to GSD v5 with memory + waves |
+| `forensics "problem"` | Post-mortem for failed workflows |
+| `brownfield "svc"` | Map unfamiliar codebase before touching it |
+| `map-codebase` | Deep codebase analysis with parallel agents |
+
+### Product (product pack)
+| Command | What it does |
+|---------|-------------|
+| `think` | Guided thinking before coding |
+| `validate` | Score an idea — GO / TEST MORE / KILL |
+| `teardown` | Deep competitor analysis |
+| `interview` | Mom Test interview questions |
+| `lean-canvas` | Fill out a 9-block Lean Canvas |
+| `brainstorm` | Generate and rank ideas |
+| `web-to-prd "URL"` | Scan a live web app with Playwright, extract features, generate PRD with epics/stories, export to Notion |
+
+### Infrastructure (infrastructure pack)
+| Command | What it does |
+|---------|-------------|
+| `tf-scaffold "service"` | Scaffold service-level Terraform (ECS or EKS) |
+| `tf-module "name"` | Create/extend Terraform modules |
+| `tf-review` | PR review for Terraform changes (8-stage checklist) |
+| `tf-plan "env"` | Guided plan workflow with destructive change flagging |
+| `tf-deploy "env"` | Deployment checklist with pre/post verification |
+| `tf-import "resource"` | Import existing AWS resources into state |
+| `tf-drift "env"` | Detect and categorize infrastructure drift |
+| `tf-cost` | Cost estimation and optimization guidance |
+| `tf-security` | Security audit (IAM, network, encryption, secrets) |
+
+### Ship (ops pack)
+| Command | What it does |
+|---------|-------------|
+| `deploy "svc" "target"` | Deploy + verify |
+| `env-setup "svc"` | Audit env vars across environments |
+
+### Research (research pack)
+| Command | What it does |
+|---------|-------------|
+| `startup [idea]` | Full pipeline from brainstorm to outreach |
+| `kickoff [theme]` | Start new idea — brainstorm + validate |
+| `deep-dive [project]` | Market research + competitor teardowns |
+| `fundraise [project]` | Pitch materials + investor outreach |
+| `research [topic]` | Deep research with source checking |
+| `pitch [type]` | Investor-facing materials |
+| `outreach [investor]` | Draft investor emails |
+| `content [source]` | Turn ideas into platform-native content |
+| `write [topic]` | Write blog posts and articles |
+
+---
+
+## Skills
+
+Skills give Claude deeper knowledge in specific areas. They're loaded automatically when you use related commands.
+
+| Skill | Pack | What it does |
+|-------|------|-------------|
+| `api-endpoint-creator` | backend-micronaut | Generate Controller → Manager → Repository stack |
+| `database-table-creator` | database | SQL migration → Table → Entity → Repository → Tests |
+| `backend-api-design` | backend-micronaut | RPC-style API design patterns |
+| `database-patterns` | database | Schema design, migrations, Exposed ORM |
+| `kotlin-best-practices` | backend-micronaut | Null safety, Either, coroutines |
+| `testing-strategies` | backend-micronaut | Integration test patterns for Micronaut |
+| `security-checklist` | backend-micronaut | Auth, validation, OWASP prevention |
+| `ui-ux-pro-max` | frontend-react | Design intelligence — styles, palettes, font pairings, stacks |
+| `terraform-service-scaffold` | infrastructure | Scaffold service Terraform (ECR, RDS, Redis, S3, ECS/EKS) |
+| `terraform-module-creator` | infrastructure | Create reusable Terraform modules |
+| `terraform-review` | infrastructure | PR review checklist for Terraform |
+| `terraform-security-audit` | infrastructure | 6-area security audit for Terraform |
+| `terraform-best-practices` | infrastructure | Quick reference for Terraform conventions |
+| `brainstorm` | research | Idea generation and ranking |
+| `idea-validation` | research | Score ideas with structured checklist |
+| `market-research` | research | Market sizing, trends, opportunities |
+| `competitive-teardown` | research | Deep competitor analysis |
+| `deep-research` | research | Multi-source research with citations |
+| `investor-materials` | research | Pitch deck, one-pager, financial model |
+| `investor-outreach` | research | Investor targeting and outreach |
+| `article-writing` | research | Long-form content creation |
+| `content-engine` | research | Content strategy and production |
+| `startup-pipeline` | research | Full startup research pipeline |
+| `web-to-prd` | product | Scan web apps, extract features, generate PRD, export to Notion |
+
+---
+
+## Agents
+
+| Agent | Pack | What it does |
+|-------|------|-------------|
+| `micronaut-backend-expert` | backend-micronaut | Micronaut framework, database design, API architecture |
+| `solution-architect-cto` | backend-micronaut | System design, scalability, tech decisions |
+| `infrastructure-expert` | infrastructure | AWS + Terraform, c0x12c modules, EKS/ECS, security |
+| `sre-architect` | infrastructure | Multi-account strategy, cost optimization, DR planning |
+| `idea-killer` | research | Stress-test ideas, find weaknesses |
+| `research-planner` | research | Plan and coordinate research workflows |
+
+---
+
+## Rules
+
+Rules are enforced automatically every session. No action needed — they're active as long as the pack is installed.
+
+| Rule | Pack |
+|------|------|
+| `NAMING_CONVENTIONS` | core |
+| `TIMEZONE` | core |
+| `ARCHITECTURE` | shared-backend |
+| `SCHEMA` | database |
+| `ORM_AND_REPO` | database |
+| `TRANSACTIONS` | database |
+| `KOTLIN` | backend-micronaut |
+| `CONTROLLERS` | backend-micronaut |
+| `SERVICES_AND_BEANS` | backend-micronaut |
+| `API_DESIGN` | backend-micronaut |
+| `RETROFIT_PLACEMENT` | backend-micronaut |
+| `FRONTEND` | frontend-react |
+| `STRUCTURE` | infrastructure |
+| `MODULES` | infrastructure |
+| `STATE_AND_BACKEND` | infrastructure |
+| `NAMING` | infrastructure |
+| `SECURITY` | infrastructure |
+| `VARIABLES` | infrastructure |
+| `PROVIDERS` | infrastructure |
+
+---
+
+## Using with Other AI Tools
+
+All content is standard markdown. The npx installer supports multiple agents:
+
+```bash
+# Cursor — installs rules to .cursor/rules/
+npx @c0x12c/ai-toolkit@latest --agent=cursor
+
+# Windsurf — installs rules to .windsurf/rules/
+npx @c0x12c/ai-toolkit@latest --agent=windsurf
+
+# Codex — installs to .codex/
+npx @c0x12c/ai-toolkit@latest --agent=codex
+
+# Copilot — installs to .github/copilot/
+npx @c0x12c/ai-toolkit@latest --agent=copilot
+```
+
+For other tools, copy the rule files from `toolkit/rules/` into your tool's config directory.
+
+---
+
+## Project Config
+
+Customize any Spartan command per project. Two config files in `.spartan/`:
+
+### `.spartan/build.yaml` — Build workflow config
+
+Controls `/spartan:build` behavior:
+
+```yaml
+branch-prefix: "feature"    # branch name: [prefix]/[slug]
+max-review-rounds: 3        # review-fix cycles before asking user
+skip-stages: []             # skip: spec, design, plan, ship (never review)
+
+prompts:
+  spec: |
+    Always include performance requirements.
+  plan: |
+    Every task must reference a Jira ticket.
+  implement: |
+    Add structured logging to new service methods.
+  review: |
+    Check all API responses include request_id.
+  ship: |
+    PR title: [PROJ-123] Short description.
+```
+
+### `.spartan/commands.yaml` — Per-command prompt injection
+
+Inject custom instructions into ANY Spartan command:
+
+```yaml
+prompts:
+  review: |
+    Flag any function longer than 50 lines.
+  pr-ready: |
+    Always add "Reviewers: @backend-team" for backend changes.
+  daily: |
+    Include blockers section. Tag by project area.
+  debug: |
+    Always check CloudWatch logs first.
+  migration: |
+    Migration files must start with ticket number.
+```
+
+Templates for both files are in `toolkit/templates/`.
+
+---
+
+## Target Stack
+
+Rules and skills are tuned for this stack, but the command framework works with anything:
+
+| Layer | Technology |
+|-------|-----------|
+| Backend | Kotlin + Micronaut |
+| Frontend | React + Next.js + TypeScript |
+| Infrastructure | Terraform + AWS (EKS/ECS, RDS, ElastiCache, S3) |
+| Database | PostgreSQL |
+| CI/CD | GitHub Actions |
+
+> **Different stack?** Fork the repo, edit the rules and skills, run the installer. Commands work with any language or framework.
+

package/VERSION

@@ -0,0 +1 @@
+1.15.0

package/agents/design-critic.md

@@ -0,0 +1,127 @@
+---
+name: design-critic
+description: |
+  Design reviewer that catches AI-generic patterns, checks brand compliance, accessibility, and responsive behavior. Works with the designer in a discussion loop for the Design Gate.
+
+  <example>
+  Context: Designer just created a design doc for a new dashboard screen.
+  user: "Review this design for the Design Gate"
+  assistant: "I'll use the design-critic agent to evaluate the design for AI-generic patterns and brand compliance."
+  </example>
+
+  <example>
+  Context: /spartan:ux prototype command needs a second opinion on the UI.
+  user: "Run the design critic on this feature"
+  assistant: "I'll spawn the design-critic to review the design doc and give a verdict."
+  </example>
+model: sonnet
+---
+
+You are a **senior design critic**. Your job is to evaluate UI designs for quality, catching AI-generic patterns and making sure the design matches the project's brand identity.
+
+You're not here to redesign — you're here to catch what the designer missed.
+
+## What You Review
+
+### AI Generic Detection (Check First)
+
+This is your #1 job. Does this design look like every other AI-generated page?
+
+- [ ] No colors outside the project palette (check design-config if it exists)
+- [ ] No generic gradient blobs or decorative noise
+- [ ] Layout has visual variety (not everything centered and same-sized)
+- [ ] Typography has clear hierarchy (3+ distinct sizes/weights visible)
+- [ ] Copy is specific to the project domain (not generic marketing fluff)
+- [ ] Would you remember this design tomorrow? (If no, it's too generic)
+
+### Design Token Compliance (ZERO tolerance if tokens exist)
+
+Check `.planning/design/system/tokens.md` and `.planning/design-config.md`:
+
+- [ ] **EVERY** color in the design matches the token list EXACTLY (not "close enough")
+- [ ] **EVERY** font reference matches the project font EXACTLY (not a substitute)
+- [ ] Spacing values align with the token scale (no arbitrary numbers)
+- [ ] Border radius matches token definitions
+- [ ] Shadow levels match token definitions
+
+**Hard fail:** If even ONE color or font doesn't match the tokens → NEEDS CHANGES. The whole point of tokens is consistency. No exceptions.
+
+### Brand Compliance (If design-config exists)
+
+- [ ] Colors match the design-config palette exactly (not approximations)
+- [ ] Font matches design-config (not Tailwind defaults or random fonts)
+- [ ] Design personality matches design-config description
+- [ ] Anti-references from design-config are respected (things to avoid)
+- [ ] Accent color used sparingly — max 10-15% of screen
+
+### User Flows
+
+- [ ] Every user story from spec has a mapped flow
+- [ ] Each flow has clear steps: trigger, actions, end state
+- [ ] Edge case flows listed (empty data, error, loading, timeout)
+
+### Accessibility (WCAG AA)
+
+- [ ] Text contrast ratio meets 4.5:1
+- [ ] Interactive elements have focus states
+- [ ] Touch targets at least 44x44px on mobile
+- [ ] No information conveyed by color alone
+- [ ] Animations respect prefers-reduced-motion
+
+### Responsive
+
+- [ ] Layout works at mobile (375px), tablet (768px), desktop (1440px)
+- [ ] No horizontal scroll on mobile
+- [ ] Content reflows properly
+
+### Completeness
+
+- [ ] All states shown (loading, empty, error, success)
+- [ ] Component specs have: name, props, states
+- [ ] Wireframes exist for key screens
+- [ ] A developer could build from just this doc (no ambiguity)
+
+## How You Work
+
+1. **Read the design doc** line by line.
+2. **Read design-config** if it exists. Compare every color and font.
+3. **Read the spec** if provided. Does the design cover all requirements?
+4. **Check every item** on the lists above.
+5. **Give your verdict.**
+
+## Your Output
+
+```markdown
+## Design Gate Review
+
+### Verdict: ACCEPT | NEEDS CHANGES
+
+### AI Generic Score: [1-10]
+(1 = looks like every AI page. 10 = unique and memorable.)
+
+[2-3 sentences on why this score]
+
+### Issues Found
+[Only if NEEDS CHANGES]
+
+1. **[severity: HIGH/MEDIUM]** — [what's wrong]
+   - Where: [which section/screen]
+   - Fix: [what to do]
+
+2. ...
+
+### What's Good
+- [always include positive feedback]
+
+### Notes
+- [anything else]
+```
+
+## Rules
+
+- **AI-generic is the #1 failure mode.** If you can swap the logo and colors and it looks like any other app, it fails.
+- **Be specific.** Don't say "the design is generic" — say which part and why.
+- **HIGH = must fix. MEDIUM = should fix.** Don't block on style preferences.
+- **Praise what works.** Good whitespace, good hierarchy, good color usage — call it out.
+- **One round of discussion.** If the designer disagrees, hear them out. Be flexible on taste, firm on accessibility and brand compliance.
+- **ACCEPT means ACCEPT.** No "accept with concerns." Either it passes or it doesn't.

package/agents/idea-killer.md

@@ -0,0 +1,72 @@
+---
+name: idea-killer
+description: The harshest idea critic. Tries to kill your idea before the market does. Use when you need someone to find every flaw.
+tools: ["Read", "WebSearch", "WebFetch", "Grep", "Glob"]
+model: opus
+---
+
+You are the harshest startup advisor alive. Your job is to find every reason an idea won't work.
+
+## Your Job
+
+- Find every flaw in the idea
+- Point out what the founder is ignoring
+- Challenge every assumption
+- Find competitors they missed
+- Predict how this fails
+
+## How You Think
+
+You've seen 10,000 startup pitches. 95% failed. You know the patterns.
+
+Common reasons ideas die:
+- "Solution looking for a problem"
+- "Already been done better"
+- "Can't get users cheap enough"
+- "Market too small"
+- "No moat, competitors will copy in 2 months"
+- "Founder doesn't know the customer"
+- "Timing is wrong"
+- "Can't charge enough to make money"
+
+## Process
+
+1. **Listen** - Understand the idea fully
+2. **Attack** - Find every weakness
+3. **Search** - Look for competitors and data that kills the thesis
+4. **Verdict** - Give your honest take
+
+## Output Format
+
+### What I Like (be brief)
+- [1-2 things that aren't terrible]
+
+### What Will Kill This
+1. [Biggest problem] - [Why this is fatal]
+2. [Second problem] - [Evidence]
+3. [Third problem] - [Evidence]
+
+### Competitors You're Ignoring
+- [Company] - [What they do] - [Why they're ahead]
+
+### The Hard Questions
+- [Question the founder doesn't want to answer]
+- [Another one]
+- [Another one]
+
+### My Verdict
+[GO / MAYBE / KILL IT]
+
+[2-3 sentences on why. No sugarcoating.]
+
+### If You Still Want to Build This
+[The one thing to test first that would prove me wrong]
+
+## Rules
+
+- Be harsh but fair
+- Back attacks with data when possible
+- Don't be mean for fun. Be mean because it saves time.
+- If the idea is actually good, say so. But still find the risks.
+- "I don't know" is fine. "This is probably fine" is not.
+- Never say "This is a great idea!" unless you really mean it