cokit-cli 1.0.8 → 1.2.0

package/instructions/ck-frontend-design-pro.instructions.md

@@ -1,58 +0,0 @@
----
-description: 'Creates jaw-dropping, production-ready frontend interfaces AND delivers perfectly matched real photos (Unsplash/Pexels direct links) OR flawless custom image-generation prompts for hero images, backgrounds, and illustrations. Zero AI slop, zero fake URLs.'
-applyTo: '**/*.{tsx,jsx,css}'
----
-
-You are a world-class creative frontend engineer AND visual director. Every interface you build must feel like a $50k+ agency project.
-
-## 1. Choose One Bold Aesthetic Direction (commit 100%)
-| Style Category              | Core Keywords (copy-paste ready)                                      | Color Palette Ideas                                      | Signature Effects & Details                                                                      |
-|-----------------------------|----------------------------------------------------------------------|----------------------------------------------------------|--------------------------------------------------------------------------------------------------|
-| Minimalism & Swiss Style    | clean, swiss, grid-based, generous whitespace, typography-first     | Monochrome + one bold accent, beige/gray neutrals        | Razor-sharp hierarchy, subtle hover lifts, micro-animations, perfect alignment                   |
-| Neumorphism                 | soft ui, embossed, concave/convex, subtle depth, monochromatic      | Single pastel + light/dark variations                    | Multi-layer soft shadows, press/release animations, no hard borders                             |
-| Glassmorphism               | frosted glass, translucent, vibrant backdrop, blur, layered         | Aurora/sunset backgrounds + semi-transparent whites      | backdrop-filter: blur(), glowing borders, light reflections, floating layers                    |
-| Brutalism                   | raw, unpolished, asymmetric, high contrast, intentionally ugly      | Harsh primaries, black/white, occasional neon            | Sharp corners, huge bold text, exposed grid, "broken" aesthetic                                  |
-| Claymorphism                | clay, chunky 3D, toy-like, bubbly, double shadows, pastel           | Candy pastels, soft gradients                            | Inner + outer shadows, squishy press effects, oversized rounded elements                         |
-| Aurora / Mesh Gradient      | aurora, northern lights, mesh gradient, luminous, flowing           | Teal → purple → pink smooth blends                       | Animated/static CSS or SVG mesh gradients, subtle color breathing, layered translucency         |
-| Retro-Futurism / Cyberpunk  | vaporwave, 80s sci-fi, crt scanlines, neon glow, glitch, chrome     | Neon cyan/magenta on deep black, chrome accents          | Scanlines, chromatic aberration, glitch transitions, long glowing shadows                       |
-| 3D Hyperrealism             | realistic textures, skeuomorphic, metallic, WebGL, tactile           | Rich metallics, deep gradients                           | Three.js / CSS 3D, physics-based motion, realistic lighting & reflections                        |
-| Vibrant Block / Maximalist  | bold blocks, duotone, high contrast, geometric, energetic           | Complementary/triadic brights, neon on dark             | Large colorful sections, scroll-snap, dramatic hover scales, animated patterns                  |
-| Dark OLED Luxury            | deep black, oled-optimized, subtle glow, premium, cinematic         | #000000 + vibrant accents (emerald, amber, electric blue)| Minimal glows, velvet textures, cinematic entrances, reduced-motion support                     |
-| Organic / Biomorphic        | fluid shapes, blobs, curved, nature-inspired, hand-drawn            | Earthy or muted pastels                                  | SVG morphing, gooey effects, irregular borders, gentle spring animations                        |
-
-## 2. Non-Negotiable Frontend Rules
-- NEVER use Inter, Roboto, Arial, system-ui, or any default AI font
-- Use characterful fonts (GT America, Reckless, Obviously, Neue Machina, Clash Display, Satoshi, etc.)
-- CSS custom properties everywhere
-- One dominant color + sharp accent(s)
-- At least one unforgettable signature detail (grain, custom cursor, animated mesh, diagonal split, etc.)
-- Break the centered-card grid: asymmetry, overlap, diagonal flow
-- Heroic, perfectly timed motion > scattered micro-interactions
-- Full WCAG AA/AAA, focus styles, semantic HTML, prefers-reduced-motion
-
-## 3. PERFECT IMAGES SYSTEM (new — never break)
-When the design needs images (hero, background, cards, illustrations, etc.):
-
-1. Real-world photography (people, office, nature, products, textures)  
-   → Use ONLY real Unsplash → Pexels → Pixabay photos  
-   → Provide DIRECT image URL ending in .jpg/.png with ?w=1920&q=80  
-   → Deliver ready <img> tag + SEO alt text  
-   Example:  
-   <img src="https://images.unsplash.com/photo-1708282114148-9e0e8d0f2f83?w=1920&q=80" alt="Developer focused on code in dark luxury studio">
-
-2. Hero images, custom backgrounds, conceptual scenes, illustrations  
-   → Write a hyper-detailed, copy-paste-ready prompt for Flux / Midjourney v6 / Ideogram  
-   → Wrap exactly like this:
-
-   [IMAGE PROMPT START]  
-   Cinematic photograph of [exact scene that matches the design 100%], dramatic rim lighting, ultra-realistic, perfect composition, 16:9 --ar 16:9 --v 6 --q 2 --stylize 650  
-   [IMAGE PROMPT END]
-
-3. Never invent fake links or low-effort AI slop
-
-## 4. Deliver
-- Production-grade, copy-paste-ready code (HTML + Tailwind/CSS, React, Vue, etc.)
-- Fully responsive + performant
-- Every image is either a perfect real photo OR a flawless custom prompt
-
-Now go build interfaces that look like they cost a fortune — because visually, they just did.

package/instructions/ck-google-adk-python.instructions.md

@@ -1,242 +0,0 @@
----
-description: 'Guidelines for google-adk-python'
-applyTo: '**/*.py'
----
-
-# Google ADK Python Skill
-
-You are an expert guide for Google's Agent Development Kit (ADK) Python - an open-source, code-first toolkit for building, evaluating, and deploying AI agents.
-
-## When to Use This Skill
-
-Use this skill when users need to:
-- Build AI agents with tool integration and orchestration capabilities
-- Create multi-agent systems with hierarchical coordination
-- Implement workflow agents (sequential, parallel, loop) for predictable pipelines
-- Integrate LLM-powered agents with Google Search, Code Execution, or custom tools
-- Deploy agents to Vertex AI Agent Engine, Cloud Run, or custom infrastructure
-- Evaluate and test agent performance systematically
-- Implement human-in-the-loop approval flows for tool execution
-
-## Core Concepts
-
-### Agent Types
-
-**LlmAgent**: LLM-powered agents capable of dynamic routing and adaptive behavior
-- Define with name, model, instruction, description, and tools
-- Supports sub-agents for delegation and coordination
-- Intelligent decision-making based on context
-
-**Workflow Agents**: Structured, predictable orchestration patterns
-- **SequentialAgent**: Execute agents in defined order
-- **ParallelAgent**: Run multiple agents concurrently
-- **LoopAgent**: Repeat execution with iteration logic
-
-**BaseAgent**: Foundation for custom agent implementations
-
-### Key Components
-
-**Tools Ecosystem**:
-- Pre-built tools (google_search, code_execution)
-- Custom Python functions as tools
-- OpenAPI specification integration
-- Tool confirmation flows for human approval
-
-**Multi-Agent Architecture**:
-- Hierarchical agent composition
-- Specialized agents for specific domains
-- Coordinator agents for delegation
-
-## Installation
-
-```bash
-# Stable release (recommended)
-pip install google-adk
-
-# Development version (latest features)
-pip install git+https://github.com/google/adk-python.git@main
-```
-
-## Implementation Patterns
-
-### Single Agent with Tools
-
-```python
-from google.adk.agents import LlmAgent
-from google.adk.tools import google_search
-
-agent = LlmAgent(
-    name="search_assistant",
-    model="gemini-2.5-flash",
-    instruction="You are a helpful assistant that searches the web for information.",
-    description="Search assistant for web queries",
-    tools=[google_search]
-)
-```
-
-### Multi-Agent System
-
-```python
-from google.adk.agents import LlmAgent
-
-# Specialized agents
-researcher = LlmAgent(
-    name="Researcher",
-    model="gemini-2.5-flash",
-    instruction="Research topics thoroughly using web search.",
-    tools=[google_search]
-)
-
-writer = LlmAgent(
-    name="Writer",
-    model="gemini-2.5-flash",
-    instruction="Write clear, engaging content based on research.",
-)
-
-# Coordinator agent
-coordinator = LlmAgent(
-    name="Coordinator",
-    model="gemini-2.5-flash",
-    instruction="Delegate tasks to researcher and writer agents.",
-    sub_agents=[researcher, writer]
-)
-```
-
-### Custom Tool Creation
-
-```python
-from google.adk.tools import Tool
-
-def calculate_sum(a: int, b: int) -> int:
-    """Calculate the sum of two numbers."""
-    return a + b
-
-# Convert function to tool
-sum_tool = Tool.from_function(calculate_sum)
-
-agent = LlmAgent(
-    name="calculator",
-    model="gemini-2.5-flash",
-    tools=[sum_tool]
-)
-```
-
-### Sequential Workflow
-
-```python
-from google.adk.agents import SequentialAgent
-
-workflow = SequentialAgent(
-    name="research_workflow",
-    agents=[researcher, summarizer, writer]
-)
-```
-
-### Parallel Workflow
-
-```python
-from google.adk.agents import ParallelAgent
-
-parallel_research = ParallelAgent(
-    name="parallel_research",
-    agents=[web_researcher, paper_researcher, expert_researcher]
-)
-```
-
-### Human-in-the-Loop
-
-```python
-from google.adk.tools import google_search
-
-# Tool with confirmation required
-agent = LlmAgent(
-    name="careful_searcher",
-    model="gemini-2.5-flash",
-    tools=[google_search],
-    tool_confirmation=True  # Requires approval before execution
-)
-```
-
-## Deployment Options
-
-### Cloud Run Deployment
-
-```bash
-# Containerize agent
-docker build -t my-agent .
-
-# Deploy to Cloud Run
-gcloud run deploy my-agent --image my-agent
-```
-
-### Vertex AI Agent Engine
-
-```python
-# Deploy to Vertex AI for scalable agent hosting
-# Integrates with Google Cloud's managed infrastructure
-```
-
-### Custom Infrastructure
-
-```python
-# Run agents locally or on custom servers
-# Full control over deployment environment
-```
-
-## Model Support
-
-**Optimized for Gemini**:
-- gemini-2.5-flash
-- gemini-2.5-pro
-- gemini-1.5-flash
-- gemini-1.5-pro
-
-**Model Agnostic**: While optimized for Gemini, ADK supports other LLM providers through standard APIs.
-
-## Best Practices
-
-1. **Code-First Philosophy**: Define agents in Python for version control, testing, and flexibility
-2. **Modular Design**: Create specialized agents for specific domains, compose into systems
-3. **Tool Integration**: Leverage pre-built tools, extend with custom functions
-4. **Evaluation**: Test agents systematically against test cases
-5. **Safety**: Implement confirmation flows for sensitive operations
-6. **Hierarchical Structure**: Use coordinator agents for complex multi-agent workflows
-7. **Workflow Selection**: Choose workflow agents for predictable pipelines, LLM agents for dynamic routing
-
-## Common Use Cases
-
-- **Research Assistants**: Web search + summarization + report generation
-- **Code Assistants**: Code execution + documentation + debugging
-- **Customer Support**: Query routing + knowledge base + escalation
-- **Content Creation**: Research + writing + editing pipelines
-- **Data Analysis**: Data fetching + processing + visualization
-- **Task Automation**: Multi-step workflows with conditional logic
-
-## Development UI
-
-ADK includes built-in interface for:
-- Testing agent behavior interactively
-- Debugging tool calls and responses
-- Evaluating agent performance
-- Iterating on agent design
-
-## Resources
-
-- GitHub: https://github.com/google/adk-python
-- Documentation: https://google.github.io/adk-docs/
-- llms.txt: https://raw.githubusercontent.com/google/adk-python/refs/heads/main/llms.txt
-
-## Implementation Workflow
-
-When implementing ADK-based agents:
-
-1. **Define Requirements**: Identify agent capabilities and tools needed
-2. **Choose Architecture**: Single agent, multi-agent, or workflow-based
-3. **Select Tools**: Pre-built, custom functions, or OpenAPI integrations
-4. **Implement Agents**: Create agent definitions with instructions and tools
-5. **Test Locally**: Use development UI for iteration
-6. **Add Evaluation**: Create test cases for systematic validation
-7. **Deploy**: Choose Cloud Run, Vertex AI, or custom infrastructure
-8. **Monitor**: Track agent performance and iterate
-
-Remember: ADK treats agent development like traditional software engineering - use version control, write tests, and follow engineering best practices.

package/plans/260106-1102-cokit-implementation/phases/phase-01-cli-tool.md

@@ -1,151 +0,0 @@
-# Phase 1: CLI Tool (npm package)
-
-**Effort:** 4h | **Status:** DONE (2026-01-06)
-
-## Objective
-
-Create `npx cokit` CLI that non-technical users can run without thinking.
-
-## User Stories
-
-```
-As a developer, I want to run ONE command to set up Copilot workflows
-So I don't have to manually copy files or read docs
-```
-
-## CLI Commands
-
-### `npx cokit init`
-
-Interactive setup wizard:
-```
-? What do you want to set up?
-  › Project templates (.github/)     ← Default
-    Personal skills (~/.copilot/)
-    Both
-
-? This will create files in .github/. Continue? (Y/n)
-
-✓ Created .github/copilot-instructions.md
-✓ Created .github/AGENTS.md
-✓ Created .github/prompts/fix.prompt.md
-✓ Created .github/prompts/plan.prompt.md
-...
-✓ Created .vscode/settings.json
-
-🎉 Done! Open VS Code and start using Copilot.
-   Try typing /fix in Copilot Chat.
-```
-
-### `npx cokit init --global`
-
-```
-? Install personal skills to ~/.copilot/skills/? (Y/n)
-
-✓ Created ~/.copilot/skills/debugging/
-✓ Created ~/.copilot/skills/code-review/
-...
-
-🎉 Skills installed! They'll work in all your projects.
-```
-
-### `npx cokit add <skill>`
-
-```bash
-npx cokit add debugging     # Add one skill
-npx cokit add --list        # Show available skills
-```
-
-### `npx cokit doctor`
-
-Diagnose setup issues:
-```
-Checking CoKit setup...
-
-✓ .github/copilot-instructions.md exists
-✓ .github/prompts/ has 6 prompts
-✗ ~/.copilot/skills/ not found
-  → Run: npx cokit init --global
-
-✓ VS Code detected
-✓ Copilot extension installed
-✗ Agent Skills not enabled
-  → Enable: Settings → github.copilot.chat.useAgentSkills
-```
-
-## Technical Implementation
-
-### Package Structure
-
-```
-cokit/
-├── package.json
-├── bin/
-│   └── cokit.js              # #!/usr/bin/env node entry
-└── src/
-    ├── index.js              # CLI router
-    ├── commands/
-    │   ├── init.js           # init command
-    │   ├── add.js            # add command
-    │   ├── list.js           # list command
-    │   ├── update.js         # update command
-    │   └── doctor.js         # doctor command
-    └── utils/
-        ├── copy.js           # Copy templates
-        ├── prompt.js         # Interactive prompts
-        ├── colors.js         # Console colors
-        └── paths.js          # Platform-aware paths
-```
-
-### Dependencies (minimal)
-
-```json
-{
-  "name": "cokit",
-  "version": "1.0.0",
-  "bin": { "cokit": "./bin/cokit.js" },
-  "dependencies": {
-    "commander": "^12.0.0",
-    "prompts": "^2.4.2",
-    "chalk": "^5.3.0"
-  }
-}
-```
-
-### Key Functions
-
-**copy.js:**
-```javascript
-// Copy template directory to destination
-// Handle existing files (prompt user)
-// Skip .gitkeep files
-```
-
-**paths.js:**
-```javascript
-// Cross-platform path resolution
-// Windows: %USERPROFILE%\.copilot\skills\
-// Unix: ~/.copilot/skills/
-```
-
-## Tasks
-
-- [x] 1.1 Initialize npm package with package.json
-- [x] 1.2 Create bin/cokit.js entry point
-- [x] 1.3 Implement `init` command with interactive prompts
-- [x] 1.4 Implement `add` command for individual skills
-- [x] 1.5 Implement `list` command
-- [x] 1.6 Implement `doctor` command
-- [x] 1.7 Add colorized output (chalk)
-- [x] 1.8 Handle existing file conflicts (prompt user)
-- [x] 1.9 Test on Windows + macOS + Linux
-- [x] 1.10 Publish to npm
-
-## Validation
-
-- [x] `npx cokit` shows help without error
-- [x] `npx cokit init` creates .github/ structure
-- [x] `npx cokit init --global` creates ~/.copilot/skills/
-- [x] Interactive prompts work (not just flags)
-- [x] Colors display correctly in terminal
-- [x] Windows paths work correctly

package/plans/260106-1102-cokit-implementation/phases/phase-02-repo-level-templates.md

@@ -1,198 +0,0 @@
-# Phase 2: Repo-Level Templates
-
-**Effort:** 3h | **Status:** DONE (2026-01-06)
-
-## Objective
-
-Create `.github/` structure templates for repo-level installation.
-
-## Directory Structure
-
-```
-templates/repo/
-├── copilot-instructions.md
-├── AGENTS.md
-├── instructions/
-│   ├── development.instructions.md
-│   ├── frontend.instructions.md
-│   ├── backend.instructions.md
-│   └── testing.instructions.md
-├── prompts/
-│   └── (covered in Phase 4)
-├── skills/
-│   └── (subset of user-level skills)
-└── .cokit-version
-```
-
-## Tasks
-
-### 2.1 Create copilot-instructions.md
-
-**File:** `templates/repo/copilot-instructions.md`
-
-**Content (port from CLAUDE.md pattern):**
-```markdown
-# Project Instructions
-
-## Role
-You are an expert software engineer following YAGNI, KISS, DRY principles.
-
-## Coding Standards
-- Read ./docs/code-standards.md before implementation
-- Keep files under 200 lines
-- Use kebab-case for file names
-
-## Architecture
-- Reference ./docs/system-architecture.md for decisions
-- Follow existing patterns in codebase
-
-## Quality
-- Write tests for new features
-- Review code for security before committing
-- No TODO/FIXME without tracking issue
-```
-
-**Conversion notes:**
-- Remove `$HOME` references (static only)
-- Inline critical workflow rules
-- Reference project docs with relative paths
-
-### 2.2 Create AGENTS.md
-
-**File:** `templates/repo/AGENTS.md`
-
-**Content (merge from agents/*.md):**
-```markdown
-# Agent Guidelines
-
-## General
-- Follow YAGNI, KISS, DRY principles
-- Be honest, concise, straight to the point
-- Verify before claiming success
-
-## When Planning
-- Research before proposing solutions
-- Create plans in ./plans directory
-- Use decomposition and working backwards
-- Break complex tasks into phases
-
-## When Implementing
-- Read plan completely before coding
-- Mark tasks complete as done
-- Run type checking after changes
-- Do not skip testing
-
-## When Testing
-- Write comprehensive unit tests
-- Cover happy path, edge cases, error cases
-- All tests must pass before proceeding
-- No mocks to fake passing tests
-
-## When Reviewing
-- Check security vulnerabilities
-- Verify error handling
-- Ensure test coverage
-- Push back on invalid suggestions
-
-## When Debugging
-- NO FIXES WITHOUT ROOT CAUSE FIRST
-- Trace backward through call stack
-- Verify fix with fresh test run
-```
-
-### 2.3 Create Instructions Files
-
-#### 2.3.1 development.instructions.md
-
-**File:** `templates/repo/instructions/development.instructions.md`
-
-```yaml
----
-applyTo: "**/*"
----
-# Development Rules
-
-- YAGNI: Don't add features until needed
-- KISS: Prefer simple solutions
-- DRY: Extract repeated code
-- File size: Keep under 200 lines
-- Naming: kebab-case for files, camelCase for variables
-- No hardcoded secrets
-- Verify before claiming complete
-```
-
-#### 2.3.2 frontend.instructions.md
-
-```yaml
----
-applyTo: "**/*.tsx,**/*.jsx,**/*.vue,**/*.svelte"
----
-# Frontend Guidelines
-
-- Use functional components with hooks
-- Prefer composition over inheritance
-- Extract reusable components
-- Handle loading/error states
-- Accessibility: Use semantic HTML
-- Responsive: Mobile-first approach
-```
-
-#### 2.3.3 backend.instructions.md
-
-```yaml
----
-applyTo: "**/*.ts,**/*.py,**/*.go,**/api/**"
-excludeAgent: "code-review"
----
-# Backend Guidelines
-
-- Validate all inputs
-- Handle errors explicitly
-- Log at appropriate levels
-- Use transactions for data integrity
-- Rate limit external API calls
-- Document API endpoints
-```
-
-#### 2.3.4 testing.instructions.md
-
-```yaml
----
-applyTo: "**/*.test.ts,**/*.spec.ts,**/*.test.js"
----
-# Testing Guidelines
-
-- One concept per test
-- Descriptive test names
-- Arrange-Act-Assert pattern
-- Mock external dependencies only
-- No flaky tests
-- Cover edge cases
-```
-
-### 2.4 Create Repo-Level Skills (Subset)
-
-Include lightweight versions of core skills in repo:
-- `debugging/` (simplified, no scripts)
-- `code-review/` (simplified)
-
-Full skills with scripts go to user-level only.
-
-### 2.5 Create Marker File
-
-**File:** `templates/repo/.cokit-version`
-
-```
-1.0.0
-# CoKit installation marker - do not delete
-# https://github.com/camping89/cokit
-```
-
-## Validation
-
-- [x] copilot-instructions.md is <2000 tokens
-- [x] AGENTS.md covers all merged agent behaviors
-- [x] Instructions files have valid `applyTo` patterns
-- [x] .cokit-version enables upgrade detection
-- [x] No `$HOME` or `$ARGUMENTS` references
-- [x] No Claude-specific tool references (Task, TodoWrite)