@relipa/ai-flow-kit 0.0.4 → 0.0.5-beta.1

package/docs/architecture.md

@@ -1,394 +0,0 @@
-# AI Flow Kit Architecture
-
-This document explains how AI Flow Kit works and how to customize it for your team.
-
-## System Overview
-
-```
-┌─────────────────────────────────────────────────────────┐
-│                   Developer                              │
-│              (runs aiflow commands)                      │
-└────────────────────┬────────────────────────────────────┘
-                     │
-        ┌────────────▼──────────────┐
-        │      CLI (bin/aiflow.js)  │
-        │  ├─ init                  │
-        │  ├─ use (load context)    │
-        │  ├─ prompt (generate)     │
-        │  ├─ detect (task type)    │
-        │  ├─ update                │
-        │  ├─ doctor                │
-        │  └─ validate              │
-        └────────────────┬──────────┘
-                         │
-        ┌────────────────┼──────────────────┐
-        │                │                  │
-   ┌────▼────┐   ┌──────▼──────┐   ┌───────▼──────┐
-   │ Scripts │   │ Adapters    │   │ Config       │
-   │ ├─ init │   │ ├─ jira     │   │ (.aiflowrc)  │
-   │ ├─ use  │   │ ├─ backlog  │   └──────────────┘
-   │ ├─ detect
-   │ ├─ context
-   │ └─ validate
-   └────┬────┘   │ └─ sheets   │
-        │        └─────┬──────┘
-        │              │
-   ┌────┴──────┬──────┴───┐
-   │            │          │
-┌──▼──┐  ┌──────▼──┐  ┌───▼────┐
-│.claude   │.rules  │  │.aiflow  │
-│          │        │  │(state)  │
-│├─skills  │├─code  │  └─────────┘
-│├─context ││  style│
-│└─prompts │├─naming│
-│          │└─review│
-└──────────└────────┘
-          ▲
-          │
-    ┌─────┴──────┐
-    │   Upstream │
-    │ (obra.dev) │
-    │   Skills   │
-    │ & Prompts  │
-    └────────────┘
-```
-
-## Key Components
-
-### 1. CLI (bin/aiflow.js)
-
-Entry point for all user commands. Routes to appropriate script.
-
-**Commands:**
-- `init` — Initialize project with skills and templates
-- `use` — Load context from ticket or file
-- `prompt` — Generate AI prompt with context
-- `detect` — Auto-detect task type from description
-- `update` — Update to latest version
-- `doctor` — Health check
-- `validate` — Validate AI output quality
-
-### 2. Configuration System
-
-Three levels of configuration:
-
-**Global** (`~/.claude/ai-flow-kit.json`)
-```json
-{
-  "defaultModel": "claude-opus-4-6",
-  "globalSkills": ["investigate-bug"]
-}
-```
-
-**Project** (`.aiflowrc.json`)
-```json
-{
-  "team": "engineering",
-  "adapters": ["jira"],
-  "frameworks": ["laravel"],
-  "autoDetectTasks": true
-}
-```
-
-**Local** (`.aiflow/state.json`)
-```json
-{
-  "current_version": "1.0.0",
-  "current_context": "JIRA-123"
-}
-```
-
-### 3. Skill System
-
-Skills are step-by-step instructions for AI workflows.
-
-**Upstream skills** (from obra/superpowers):
-- `brainstorming` — Explore ideas
-- `writing-plans` — Create implementation plans
-- `executing-plans` — Execute plans with checkpoints
-- `systematic-debugging` — Debug issues methodically
-- `test-driven-development` — TDD workflow
-- etc.
-
-**Custom skills** (in `custom/skills/`):
-- `investigate-bug` — Trace bugs through data flow
-- `impact-analysis` — Assess change scope
-- `generate-spec` — Create feature specifications
-- etc.
-
-Skills are merged during `aiflow init` and `aiflow update`.
-
-### 4. Task Detection
-
-Auto-classifies what the developer is doing:
-
-```
-Input: "Payment integration broken in checkout"
-  ↓
-Analysis:
-  - Contains: "broken" (bug indicator)
-  - Location: "checkout" (specific area)
-  - Type: Bug fix
-  ↓
-Output: "investigate-bug" skill
-```
-
-**Detection rules** (in `scripts/detect.js`):
-- Keywords: "bug", "error", "broken", "crash" → bug fix
-- Keywords: "add", "create", "build", "new" → feature
-- Keywords: "improve", "optimize", "refactor" → refactor
-- Keywords: "analyze", "investigate", "understand" → investigation
-
-### 5. Context System
-
-Stores task information for AI reference.
-
-**Structure:**
-```
-.claude/context/
-├── current.json        # Current task
-├── history/
-│   ├── JIRA-123.json
-│   ├── JIRA-124.json
-│   └── ...
-└── templates/
-    ├── bug-fix.json
-    ├── feature.json
-    └── ...
-```
-
-**Content:**
-```json
-{
-  "taskId": "JIRA-123",
-  "taskType": "bug-fix",
-  "title": "Payment processing fails",
-  "description": "Users see error...",
-  "acceptanceCriteria": ["...", "..."],
-  "context": {
-    "files": ["src/Payment.php"],
-    "services": ["PaymentService"],
-    "models": ["Transaction"],
-    "relatedTickets": ["JIRA-120", "JIRA-121"]
-  },
-  "metadata": {
-    "created": "2024-04-03T10:00:00Z",
-    "loadedFrom": "jira",
-    "adapter": "jira"
-  }
-}
-```
-
-### 6. MCP Adapter System
-
-Integrates with external tools (Jira, Backlog, etc).
-
-**How it works:**
-1. User runs: `aiflow use JIRA-123`
-2. CLI checks MCP config for `jira` server
-3. Calls Jira API via MCP to fetch issue
-4. Parses and stores in `context/current.json`
-5. Generates prompt with context
-
-**Adapters:**
-```json
-custom/mcp-presets/jira.json
-{
-  "mcpServers": {
-    "jira": {
-      "command": "npx",
-      "args": ["@modelcontextprotocol/server-jira"],
-      "env": {
-        "JIRA_API_TOKEN": "{{API_TOKEN}}",
-        "JIRA_EMAIL": "{{EMAIL}}",
-        "JIRA_DOMAIN": "{{DOMAIN}}"
-      }
-    }
-  }
-}
-```
-
-### 7. Template System
-
-Pre-made structures for different task types and frameworks.
-
-**Prompt Templates** (`custom/prompts/`):
-- `bug-fix.md` — Template for bug fixing workflow
-- `feature.md` — Template for feature building
-- `investigation.md` — Template for code investigation
-- etc.
-
-**Framework Templates** (`custom/templates/`):
-- `laravel.md` — Laravel-specific rules and patterns
-- `nextjs.md` — Next.js specific rules
-- etc.
-
-## Data Flow Examples
-
-### Example 1: Load and Prompt
-
-```
-aiflow use JIRA-123
-  ↓
-[Load from MCP Adapter]
-  - Fetch issue from Jira
-  - Parse description, criteria
-  - Save to .aiflow/context/current.json
-  ↓
-aiflow prompt bug-fix
-  ↓
-[Generate Prompt]
-  - Read context from current.json
-  - Load bug-fix template
-  - Load laravel rules
-  - Merge all content
-  - Print to console (copy to Claude)
-  ↓
-Developer copies → Claude Code
-  ↓
-Claude runs appropriate skill (auto-detected)
-```
-
-### Example 2: Auto-Detection
-
-```
-Prompt: "We have users reporting that orders aren't saved"
-  ↓
-aiflow detect "We have users reporting that orders aren't saved"
-  ↓
-[Analysis]
-  Keywords: "orders aren't saved" (bug pattern)
-  Type: Bug fix
-  Confidence: 95%
-  ↓
-Output: Use "investigate-bug" skill
-  ↓
-Claude will follow:
-  1. Understand context
-  2. Trace data flow
-  3. Check git history
-  4. Propose solution
-```
-
-## Folder Structure
-
-```
-ai-flow-kit/
-├── bin/
-│   └── aiflow.js                 # CLI entry point
-│
-├── scripts/                      # Core functionality
-│   ├── init.js                   # Initialize project
-│   ├── update.js                 # Update version
-│   ├── use.js                    # Load context
-│   ├── detect.js                 # Detect task type
-│   ├── doctor.js                 # Health check
-│   ├── validate.js               # Validate output
-│   ├── context.js                # Context management
-│   ├── config.js                 # Config loader
-│   └── memory.js                 # Memory system
-│
-├── custom/                       # Team customizations
-│   ├── skills/                   # Custom skills
-│   │   ├── investigate-bug/
-│   │   ├── impact-analysis/
-│   │   ├── report-customer/
-│   │   └── generate-spec/
-│   ├── rules/                    # Team standards
-│   │   ├── code-style.md
-│   │   ├── naming.md
-│   │   └── review-checklist.md
-│   ├── templates/                # Framework rules
-│   │   ├── laravel.md
-│   │   ├── nextjs.md
-│   │   └── vue-nuxt.md
-│   ├── prompts/                  # Task templates
-│   │   ├── bug-fix.md
-│   │   ├── feature.md
-│   │   ├── investigation.md
-│   │   └── refactor.md
-│   └── mcp-presets/              # MCP configs
-│       ├── jira.json
-│       ├── backlog.json
-│       └── google-sheets.json
-│
-├── upstream/                     # Original obra/superpowers
-│   ├── skills/
-│   ├── agents/
-│   └── commands/
-│
-├── docs/                         # Documentation
-│   ├── architecture.md           # This file
-│   ├── getting-started.md
-│   ├── configuration.md
-│   ├── cli-reference.md
-│   ├── workflows/
-│   │   ├── bug-fix.md
-│   │   ├── feature.md
-│   │   ├── investigation.md
-│   │   └── refactor.md
-│   └── troubleshooting.md
-│
-├── docs/                         # Documentation
-├── package.json
-└── index.js
-```
-
-## Customization Points
-
-### Add a Custom Skill
-
-1. Create `custom/skills/my-skill/SKILL.md`
-2. Follow skill format (see technical documentation)
-3. Run `aiflow update` to activate
-4. Skill appears in `.claude/skills/`
-
-### Add a Rule
-
-1. Create `custom/rules/my-rule.md`
-2. Describe the rule with examples
-3. Run `aiflow update`
-4. Rule appears in prompts via `aiflow prompt`
-
-### Add a Task Type
-
-1. Create `custom/prompts/my-task.md`
-2. Design template structure
-3. Run `aiflow update`
-4. Use with `aiflow prompt my-task`
-
-### Add Framework Support
-
-1. Create `custom/templates/my-framework.md`
-2. Define framework-specific rules
-3. Users can: `aiflow init --framework my-framework`
-
-## Extension Points
-
-The system is designed to extend:
-
-- **Custom skills:** Add domain-specific workflows
-- **Rules:** Add team standards and best practices
-- **Adapters:** Connect to more tools (Linear, GitHub, etc)
-- **Validators:** Check output quality
-- **Plugins:** Custom commands and functionality
-
-See technical documentation for details.
-
-## Best Practices
-
-1. **Keep upstream separate** — Don't modify `upstream/`. Copy to `custom/` if needed.
-
-2. **Version your customizations** — Track `custom/` in git, not `upstream/`.
-
-3. **Document team rules** — Add to `custom/rules/`. Make them explicit.
-
-4. **Use configuration** — Store team settings in `.aiflowrc.json`.
-
-5. **Test before sharing** — Use `aiflow doctor` and test each contribution.
-
-6. **Share with team** — Version control makes updates easy: `git pull && aiflow update`.
-
----
-
-**Understanding the architecture helps you customize AI Flow Kit for your team's needs!**

package/docs/developer-overview.md

@@ -1,126 +0,0 @@
-# AI Flow Kit — Developer Rollout Guide
-
-Welcome to the **AI Flow Kit**! This guide is designed to get you up and running with our standardized AI development workflow.
-
-## 1. What is AI Flow Kit?
-
-It's a "Zero-Config" framework for AI-assisted development. It automatically:
-- Pulls ticket context (requirements, comments) from Backlog/Jira.
-- Orchestrates a **5-Gate Workflow** (Analyze → Plan → Code → Review → PR).
-- Enforces team coding standards and architecture rules.
-- Synchronizes state across different AI tools (Claude, Cursor, Gemini).
-
----
-
-## 2. Prerequisites
-
-Before starting, ensure you have:
-1. **Node.js** (v18 or higher).
-2. **AI Tool(s)**:
-   - **Claude Code CLI** (Recommended for analysis and heavy tasks).
-   - **Cursor AI** (Recommended for coding and UI work).
-   - **Gemini CLI** or **GitHub Copilot** (Alternative options).
-
----
-
-## 3. Installation
-
-Run this command to install the CLI tool globally:
-
-```bash
-# Stable version
-npm install -g @relipa/ai-flow-kit
-
-# Beta version (recommend for newest features)
-npm install -g @relipa/ai-flow-kit@beta
-
-# Verification
-aiflow --version
-
-# Uninstall
-npm uninstall -g @relipa/ai-flow-kit
-
----
-
-## 4. First-time Setup
-
-In your project root, run:
-
-```bash
-aiflow init --framework [your-framework] --adapter [backlog/jira]
-```
-*Example: `aiflow init --framework nestjs --adapter backlog`*
-
-**What this does:**
-1. Verifies your API keys.
-2. Creates instruction files: `CLAUDE.md`, `.cursorrules`, `GEMINI.md`.
-3. Installs "Superpowers" skills.
-
----
-
-## 5. Daily Task Workflow (The 5 Gates)
-
-### Step 1: Start a Task
-Load the ticket context from your issue tracker:
-```bash
-aiflow use PROJ-33
-```
-
-### Step 2: Open your AI Tool
-- **Claude Code**: Type `claude`. The AI will automatically start **Gate 1**.
-- **Cursor**: Just start chatting with Cursor. It will detect the active ticket and start analyzing.
-
-### Step 3: Follow the Gates
-The AI *must* pass each gate in order. You act as the **Reviewer**.
-
-1. **⛩️ Gate 1: Requirement Analysis**
-   - AI reads code + ticket.
-   - AI outputs `plan/PROJ-33/requirement.md`.
-   - **Your Action**: Read the doc. If OK, type `APPROVED`.
-
-2. **⛩️ Gate 2: Implementation Plan**
-   - AI creates a step-by-step TDD plan.
-   - **Your Action**: Type `APPROVED` to start coding.
-
-3. **⛩️ Gate 3: Coding (TDD)**
-   - AI writes tests first, then code.
-   - **Your Action**: Monitor.
-
-4. **⛩️ Gate 4: Self-Review**
-   - AI verifies tests and checks a review-checklist.
-   - **Your Action**: Review the final diff. If OK, type `APPROVED`.
-
-5. **⛩️ Gate 5: Pull Request**
-   - AI helps you write a detailed PR description.
-   - **Your Action**: Create the PR and ask for a peer review.
-
----
-
-## 6. Switching AI Tools Mid-Task
-
-You can switch tools at any time because the "brain" (the State) is stored in your project files.
-
-**Example Scenario:**
-1. Use **Claude Code CLI** for **Gate 1** (Analysis) because it's great at exploring many files.
-2. Once you type `APPROVED`, close Claude.
-3. Open **Cursor** for **Gate 3** (Coding) to take advantage of its excellent editor integration. Cursor will see you've already finished the analysis and will continue from the plan.
-
----
-
-## 7. Best Practices
-
-- **One question at a time**: If the AI asks 5 questions, answer them one by one or ignore the irrelevant ones.
-- **Small commits**: Let the AI commit frequently (default behavior).
-- **Be the Pilot**: The AI is your co-pilot. If its solution looks over-engineered, tell it: *"Simplify this by using [X] pattern"*.
-
----
-
-## 8. Troubleshooting
-
-- **AI is stuck**: Type `reset context` or use `aiflow doctor` to check setup.
-- **Credentials fail**: Re-run `aiflow init --adapter backlog` to update keys.
-- **Rules not followed**: Remind the AI: *"Follow the rules in CLAUDE.md"*.
-
----
-
-**Happy Coding!** สำหรับรายละเอียดเชิงลึก โปรดดู [AIFLOW.md](../AIFLOW.md).

package/upstream/tests/brainstorm-server/package-lock.json

@@ -1,36 +0,0 @@
-{
-  "name": "brainstorm-server-tests",
-  "version": "1.0.0",
-  "lockfileVersion": 3,
-  "requires": true,
-  "packages": {
-    "": {
-      "name": "brainstorm-server-tests",
-      "version": "1.0.0",
-      "dependencies": {
-        "ws": "^8.19.0"
-      }
-    },
-    "node_modules/ws": {
-      "version": "8.19.0",
-      "resolved": "https://registry.npmjs.org/ws/-/ws-8.19.0.tgz",
-      "integrity": "sha512-blAT2mjOEIi0ZzruJfIhb3nps74PRWTCz1IjglWEEpQl5XS/UNama6u2/rjFkDDouqr4L67ry+1aGIALViWjDg==",
-      "license": "MIT",
-      "engines": {
-        "node": ">=10.0.0"
-      },
-      "peerDependencies": {
-        "bufferutil": "^4.0.1",
-        "utf-8-validate": ">=5.0.2"
-      },
-      "peerDependenciesMeta": {
-        "bufferutil": {
-          "optional": true
-        },
-        "utf-8-validate": {
-          "optional": true
-        }
-      }
-    }
-  }
-}