cokit-cli 1.0.8 → 1.2.0

package/templates/repo/.github/prompts/ck-spec-tasks.prompt.md

@@ -0,0 +1,193 @@
+---
+agent: 'agent'
+description: 'Generate actionable, dependency-ordered tasks.md from design artifacts'
+handoffs:
+  - label: Analyze For Consistency
+    agent: ck.spec.analyze
+    prompt: Run a project analysis for consistency
+    send: true
+  - label: Implement Project
+    agent: ck.spec.implement
+    prompt: Start the implementation in phases
+    send: true
+scripts:
+  sh: spec-kit/scripts/bash/check-prerequisites.sh --json
+  ps: spec-kit/scripts/powershell/check-prerequisites.ps1 -Json
+---
+
+## User Input
+
+```text
+${input}
+```
+
+You **MUST** consider the user input before proceeding (if not empty).
+
+## Outline
+
+1. **Setup**: Run `{SCRIPT}` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
+
+2. **Load design documents**: Read from FEATURE_DIR:
+   - **Required**: plan.md (tech stack, libraries, structure), spec.md (user stories with priorities)
+   - **Optional**: data-model.md (entities), contracts/ (API endpoints), research.md (decisions), quickstart.md (test scenarios)
+   - Note: Not all projects have all documents. Generate tasks based on what's available.
+
+3. **Execute task generation workflow**:
+   - Load plan.md and extract tech stack, libraries, project structure
+   - Load spec.md and extract user stories with their priorities (P1, P2, P3, etc.)
+   - If data-model.md exists: Extract entities and map to user stories
+   - If contracts/ exists: Map endpoints to user stories
+   - If research.md exists: Extract decisions for setup tasks
+   - Generate tasks organized by user story (see Task Generation Rules below)
+   - Generate dependency graph showing user story completion order
+   - Create parallel execution examples per user story
+   - Validate task completeness (each user story has all needed tasks, independently testable)
+
+4. **Generate hybrid task structure**: Create master file + individual phase files:
+
+   **4a. Create phase files** in `FEATURE_DIR/tasks/`:
+   - `phase-01-setup.md` - Project initialization
+   - `phase-02-foundation.md` - Blocking prerequisites for all user stories
+   - `phase-03-us1-[slug].md` - User Story 1 (P1 priority)
+   - `phase-04-us2-[slug].md` - User Story 2 (P2 priority)
+   - ... (one file per user story, in priority order)
+   - `phase-NN-polish.md` - Final phase: Cross-cutting concerns
+
+   **Phase file structure**:
+   ```markdown
+   # Phase N: [Phase Title]
+
+   **Status**: pending | in-progress | completed
+   **Dependencies**: [List phase dependencies, e.g., "Phase 2 must complete first"]
+
+   ## Goal
+   [Brief description of what this phase delivers]
+
+   ## Test Criteria
+   [How to verify this phase is complete - independently testable]
+
+   ## Tasks
+   - [ ] TXXX [P?] [Story?] Description with file path
+   - [ ] TXXX ...
+
+   ## Checkpoint
+   [What should be true when this phase completes]
+   ```
+
+   **4b. Create master tasks.md** in `FEATURE_DIR/`:
+   Use `spec-kit/templates/tasks-template.md` as reference, generate:
+   - Feature name and overview
+   - Phase summary table with status and links:
+     ```markdown
+     | Phase | Title | Status | Tasks | Dependencies |
+     |-------|-------|--------|-------|--------------|
+     | 1 | [Setup](tasks/phase-01-setup.md) | pending | 3 | - |
+     | 2 | [Foundation](tasks/phase-02-foundation.md) | pending | 6 | Phase 1 |
+     | 3 | [US1: Title](tasks/phase-03-us1-slug.md) | pending | 7 | Phase 2 |
+     ```
+   - Dependency graph (text diagram showing phase order)
+   - Parallel execution notes
+   - Implementation strategy (MVP first, incremental delivery)
+   - Quick reference: Total tasks, parallel opportunities, MVP scope
+
+5. **Report**: Output paths to generated files and summary:
+   - Files created: `tasks.md` + list of `tasks/phase-*.md` files
+   - Total task count and count per phase
+   - Parallel opportunities identified
+   - Independent test criteria for each story
+   - Suggested MVP scope (typically Phase 1-3: Setup + Foundation + US1)
+   - Format validation: Confirm ALL tasks follow the checklist format
+
+Context for task generation: {ARGS}
+
+**Hybrid Structure Benefits**:
+- Master `tasks.md` provides overview and navigation
+- Individual phase files enable parallel work by multiple agents/developers
+- Each phase file is self-contained with clear dependencies
+- Easy to track progress per phase independently
+
+The task files should be immediately executable - each task must be specific enough that an LLM can complete it without additional context.
+
+## Task Generation Rules
+
+**CRITICAL**: Tasks MUST be organized by user story to enable independent implementation and testing.
+
+**Tests are OPTIONAL**: Only generate test tasks if explicitly requested in the feature specification or if user requests TDD approach.
+
+### Checklist Format (REQUIRED)
+
+Every task MUST strictly follow this format:
+
+```text
+- [ ] [TaskID] [P?] [Story?] Description with file path
+```
+
+**Format Components**:
+
+1. **Checkbox**: ALWAYS start with `- [ ]` (markdown checkbox)
+2. **Task ID**: Sequential number (T001, T002, T003...) in execution order
+3. **[P] marker**: Include ONLY if task is parallelizable (different files, no dependencies on incomplete tasks)
+4. **[Story] label**: REQUIRED for user story phase tasks only
+   - Format: [US1], [US2], [US3], etc. (maps to user stories from spec.md)
+   - Setup phase: NO story label
+   - Foundational phase: NO story label  
+   - User Story phases: MUST have story label
+   - Polish phase: NO story label
+5. **Description**: Clear action with exact file path
+
+**Examples**:
+
+- ✅ CORRECT: `- [ ] T001 Create project structure per implementation plan`
+- ✅ CORRECT: `- [ ] T005 [P] Implement authentication middleware in src/middleware/auth.py`
+- ✅ CORRECT: `- [ ] T012 [P] [US1] Create User model in src/models/user.py`
+- ✅ CORRECT: `- [ ] T014 [US1] Implement UserService in src/services/user_service.py`
+- ❌ WRONG: `- [ ] Create User model` (missing ID and Story label)
+- ❌ WRONG: `T001 [US1] Create model` (missing checkbox)
+- ❌ WRONG: `- [ ] [US1] Create User model` (missing Task ID)
+- ❌ WRONG: `- [ ] T001 [US1] Create model` (missing file path)
+
+### Task Organization
+
+1. **From User Stories (spec.md)** - PRIMARY ORGANIZATION:
+   - Each user story (P1, P2, P3...) gets its own phase
+   - Map all related components to their story:
+     - Models needed for that story
+     - Services needed for that story
+     - Endpoints/UI needed for that story
+     - If tests requested: Tests specific to that story
+   - Mark story dependencies (most stories should be independent)
+
+2. **From Contracts**:
+   - Map each contract/endpoint → to the user story it serves
+   - If tests requested: Each contract → contract test task [P] before implementation in that story's phase
+
+3. **From Data Model**:
+   - Map each entity to the user story(ies) that need it
+   - If entity serves multiple stories: Put in earliest story or Setup phase
+   - Relationships → service layer tasks in appropriate story phase
+
+4. **From Setup/Infrastructure**:
+   - Shared infrastructure → Setup phase (Phase 1)
+   - Foundational/blocking tasks → Foundational phase (Phase 2)
+   - Story-specific setup → within that story's phase
+
+### Phase Structure
+
+- **Phase 1**: Setup (project initialization)
+- **Phase 2**: Foundational (blocking prerequisites - MUST complete before user stories)
+- **Phase 3+**: User Stories in priority order (P1, P2, P3...)
+  - Within each story: Tests (if requested) → Models → Services → Endpoints → Integration
+  - Each phase should be a complete, independently testable increment
+- **Final Phase**: Polish & Cross-Cutting Concerns
+
+---
+
+## Suggested Next Steps
+
+| Command | Description | When to Use |
+|---------|-------------|-------------|
+| `/ck.spec.analyze` | Cross-artifact consistency check | Before implementation, validate spec/plan/tasks alignment |
+| `/ck.spec.implement` | Execute implementation | All tasks validated, ready to code |
+| `/ck.spec.taskstoissues` | Create GitHub issues | Track tasks in GitHub project board |
+
+**Workflow:** `/ck.spec.specify` → `/ck.spec.clarify` → `/ck.spec.plan` → `/ck.spec.tasks` → `/ck.spec.implement`

package/templates/repo/.github/prompts/ck-spec-taskstoissues.prompt.md

@@ -0,0 +1,48 @@
+---
+agent: 'agent'
+description: 'Convert tasks into GitHub issues for project tracking'
+tools:
+  - github/github-mcp-server/issue_write
+scripts:
+  sh: spec-kit/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks
+  ps: spec-kit/scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks
+---
+
+## User Input
+
+```text
+${input}
+```
+
+You **MUST** consider the user input before proceeding (if not empty).
+
+## Outline
+
+1. Run `{SCRIPT}` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
+
+2. From the executed script, extract the path to **tasks**.
+
+3. **Verify Git repository and GitHub remote**:
+   - Check if this is a git repository: `git rev-parse --git-dir 2>/dev/null`
+   - If NOT a git repo: **STOP** and inform user "This command requires a git repository with a GitHub remote. Initialize git first or use `/ck.spec.implement` instead."
+   - Get the Git remote: `git config --get remote.origin.url`
+
+> [!CAUTION]
+> ONLY PROCEED TO NEXT STEPS IF THE REMOTE IS A GITHUB URL (contains github.com)
+
+4. For each task in the list, use the GitHub MCP server to create a new issue in the repository that is representative of the Git remote.
+
+> [!CAUTION]
+> UNDER NO CIRCUMSTANCES EVER CREATE ISSUES IN REPOSITORIES THAT DO NOT MATCH THE REMOTE URL
+
+---
+
+## Suggested Next Steps
+
+| Command | Description | When to Use |
+|---------|-------------|-------------|
+| `/ck.spec.implement` | Start implementation | Issues created, ready to code |
+| `/ck.spec.tasks` | Regenerate tasks | Need to update task list |
+| `/ck.kanban` | View project board | Track progress on created issues |
+
+**Usage:** Run after `/ck.spec.tasks` to sync tasks with GitHub Issues for team tracking

package/templates/repo/.github/prompts/ck-test.prompt.md

@@ -1,10 +1,19 @@
 ---
 agent: 'agent'
-description: 'Run tests locally and analyze the summary report.'
-tools: ['search/codebase', 'search/changes', 'read/problems', 'read/terminalLastCommand']
+description: 'Run tests locally and analyze the summary report'
+tools: ['execute/runInTerminal', 'execute/getTerminalOutput', 'execute/runTests', 'execute/testFailure', 'read/problems']
 ---
 
-run tests locally and analyze the summary report.
+Use the `tester` subagent to run tests locally and analyze the summary report.
 
 **IMPORTANT**: **Do not** start implementing.
-**IMPORTANT:** 
+**IMPORTANT:** Analyze the skills catalog and activate the skills that are needed for the task during the process.
+
+---
+
+## Suggested Next Steps
+
+| Command | Description |
+|---------|-------------|
+| `/ck.fix` | Analyze and fix issues |
+| `/ck.review` | Scan and analyze codebase |

package/templates/repo/.github/prompts/ck-watzup.prompt.md

@@ -1,11 +1,19 @@
 ---
 agent: 'agent'
 description: 'Review recent changes and wrap up the work'
-tools: ['search/codebase', 'search/changes', 'read/problems']
+tools: ['search/changes', 'execute/runInTerminal', 'execute/getTerminalOutput', 'search/codebase', 'read/readFile']
 ---
-
 Review my current branch and the most recent commits. 
 Provide a detailed summary of all changes, including what was modified, added, or removed. 
 Analyze the overall impact and quality of the changes.
 
 **IMPORTANT**: **Do not** start implementing.
+
+---
+
+## Suggested Next Steps
+
+| Command | Description |
+|---------|-------------|
+| `/ck.brainstorm` | Explore ideas |
+| `/ck.plan` | Create plan |

package/templates/repo/.github/skills/INSTALLATION.md

@@ -0,0 +1,311 @@
+# Skills Installation Guide
+
+This guide explains how to install dependencies for Claude Code skills.
+
+## Overview
+
+Skills are organized into groups with Python utility scripts. Each skill's scripts directory contains a `requirements.txt` file listing dependencies.
+
+## Automated Installation (Recommended)
+
+Use the provided installation scripts for automated setup:
+
+### Linux/macOS
+
+```bash
+cd $HOME/.copilot/skills
+chmod +x install.sh
+./install.sh
+```
+
+The script will:
+- Detect your OS (Linux or macOS)
+- Install package managers (Homebrew for macOS, apt-get for Linux)
+- Install system dependencies (FFmpeg, ImageMagick)
+- Install Node.js and global packages (rmbg-cli, pnpm, wrangler, repomix)
+- Create Python virtual environment
+- Install Python packages for all skills
+- Install test dependencies
+- Verify all installations
+
+### Windows (PowerShell)
+
+Run as Administrator:
+
+```powershell
+cd .copilot\skills
+Set-ExecutionPolicy Bypass -Scope Process -Force
+.\install.ps1
+```
+
+Options:
+```powershell
+# Skip Chocolatey installation if already installed
+.\install.ps1 -SkipChocolatey
+
+# Show help
+.\install.ps1 -Help
+```
+
+The script will:
+- Install Chocolatey package manager (if needed)
+- Install system dependencies (FFmpeg, ImageMagick)
+- Install Node.js and global packages
+- Create Python virtual environment
+- Install Python packages
+- Verify all installations
+
+### What Gets Installed
+
+**System Tools:**
+- FFmpeg (video/audio processing)
+- ImageMagick (image processing)
+
+**Node.js Packages (global):**
+- rmbg-cli (AI background removal)
+- pnpm (package manager)
+- wrangler (Cloudflare CLI)
+- repomix (repository packaging)
+
+**Python Packages:**
+- google-genai (Gemini API)
+- pypdf, python-docx (document processing)
+- Pillow (image processing)
+- pytest, pytest-cov (testing)
+
+## Manual Installation
+
+If you prefer manual installation or the automated script fails:
+
+## Quick Start
+
+### Option 1: Install All Dependencies (Recommended)
+
+```bash
+# Create virtual environment
+python3 -m venv .venv
+source .venv/bin/activate  # On Windows: .venv\Scripts\activate
+
+# Install test dependencies for development
+pip install pytest pytest-cov pytest-mock
+```
+
+## Skills Dependencies
+
+### Python Package Dependencies
+
+Most skills use only Python standard library and require no external packages.
+
+### System Tool Dependencies
+
+Several skills require external CLI tools:
+
+#### Media Processing CLI Tools
+- **FFmpeg**: Video/audio processing
+  - Ubuntu/Debian: `sudo apt-get install ffmpeg`
+  - macOS: `brew install ffmpeg`
+  - Windows: `choco install ffmpeg`
+- **ImageMagick**: Image processing
+  - Ubuntu/Debian: `sudo apt-get install imagemagick`
+  - macOS: `brew install imagemagick`
+  - Windows: `choco install imagemagick`
+- **RMBG CLI**: AI background removal
+  - All platforms: `npm install -g rmbg-cli`
+
+#### devops
+- **Cloudflare Wrangler**: `npm install -g wrangler`
+- **Docker**: https://docs.docker.com/get-docker/
+- **Google Cloud CLI**: https://cloud.google.com/sdk/docs/install
+
+#### repomix
+- **Node.js 18+**: https://nodejs.org/
+- **Repomix**: `npm install -g repomix`
+
+#### databases
+- **PostgreSQL client**: `sudo apt-get install postgresql-client` (Linux)
+- **MongoDB Shell**: https://www.mongodb.com/try/download/shell
+- **MongoDB Tools**: https://www.mongodb.com/try/download/database-tools
+
+#### ui-styling
+- **Node.js 18+**: https://nodejs.org/
+- **pnpm**: `npm install -g pnpm`
+- **yarn**: `npm install -g yarn`
+
+## Installation by Platform
+
+### Linux (Ubuntu/Debian)
+
+```bash
+# Python environment
+python3 -m venv .venv
+source .venv/bin/activate
+
+# System tools
+sudo apt-get update
+sudo apt-get install -y ffmpeg imagemagick postgresql-client
+
+# Node.js and tools
+curl -fsSL https://deb.nodesource.com/setup_20.x | sudo -E bash -
+sudo apt-get install -y nodejs
+npm install -g pnpm wrangler repomix rmbg-cli
+```
+
+### macOS
+
+```bash
+# Python environment
+python3 -m venv .venv
+source .venv/bin/activate
+
+# System tools via Homebrew
+brew install ffmpeg imagemagick postgresql
+
+# Node.js and tools
+brew install node
+npm install -g pnpm wrangler repomix rmbg-cli
+```
+
+### Windows
+
+```powershell
+# Python environment
+python -m venv .venv
+.venv\Scripts\activate
+
+# System tools via Chocolatey
+choco install ffmpeg imagemagick nodejs
+
+# Node.js tools
+npm install -g pnpm wrangler repomix rmbg-cli
+```
+
+## Testing Dependencies
+
+All skills include test dependencies in `requirements.txt`:
+
+```txt
+pytest>=8.0.0
+pytest-cov>=4.1.0
+pytest-mock>=3.12.0
+```
+
+To run tests for a skill:
+
+```bash
+cd $HOME/.copilot/skills/{skill-name}/scripts
+python -m pytest tests/ -v --cov=. --cov-report=term-missing
+```
+
+## Environment Variables
+
+Skills respect environment variable loading priority:
+
+1. **process.env** (highest priority - runtime environment)
+2. **`$HOME/.copilot/skills/{skill-name}/.env`** (skill-specific config)
+3. **`$HOME/.copilot/skills/.env`** (shared skills config)
+4. **`$HOME/.copilot/.env`** (global Claude config)
+
+Example `.env` files are provided where needed (e.g., `devops/.env.example`).
+
+## Troubleshooting
+
+### "externally-managed-environment" Error
+
+If you see this error when installing packages:
+
+```bash
+# Use virtual environment (recommended)
+python3 -m venv .venv
+source .venv/bin/activate
+pip install -r requirements.txt
+
+# Or use pipx for CLI tools
+pipx install google-genai
+```
+
+### Missing System Tools
+
+If scripts fail with "command not found":
+
+```bash
+# Check if tool is installed
+which ffmpeg
+which docker
+which node
+
+# Verify tool works
+ffmpeg -version
+docker --version
+node --version
+```
+
+### Permission Errors
+
+On Linux/macOS, you may need to make scripts executable:
+
+```bash
+chmod +x $HOME/.copilot/skills/*/scripts/*.py
+```
+
+## Minimal Installation
+
+If you only want to use specific skills:
+
+**For media processing tools only:**
+```bash
+# macOS
+brew install ffmpeg imagemagick
+npm install -g rmbg-cli
+
+# Linux
+sudo apt-get install ffmpeg imagemagick
+npm install -g rmbg-cli
+
+# Windows
+choco install ffmpeg imagemagick
+npm install -g rmbg-cli
+```
+
+**For other skills:**
+Most other skills (repomix, devops, ui-styling, databases) use only Python stdlib and require no `pip install`.
+
+## Development Setup
+
+For contributors working on skills:
+
+```bash
+# Install all test dependencies
+pip install pytest pytest-cov pytest-mock
+
+# Install pre-commit hooks (if available)
+pre-commit install
+
+# Run all tests
+pytest $HOME/.copilot/skills/*/scripts/tests/ -v
+
+# Check coverage across all skills
+pytest $HOME/.copilot/skills/*/scripts/tests/ --cov=.copilot/skills --cov-report=html
+```
+
+## Skill-Specific Notes
+
+### Media Processing Tools
+- FFmpeg must be in PATH
+- ImageMagick must be in PATH
+- RMBG CLI must be installed globally
+- Test with: `ffmpeg -version`, `convert -version`, and `rmbg --version`
+
+### devops
+- Cloudflare: Requires `CLOUDFLARE_API_TOKEN` and `CLOUDFLARE_ACCOUNT_ID`
+- GCloud: Requires `GOOGLE_APPLICATION_CREDENTIALS` path to service account JSON
+- Docker: Must have Docker daemon running
+
+## Getting Help
+
+If dependencies fail to install or scripts don't work:
+
+1. Check the skill's `scripts/requirements.txt` for specific versions
+2. Verify system tools are installed and in PATH
+3. Check environment variables are set correctly
+4. Review skill's `SKILL.md` for additional setup instructions
+5. Open an issue: https://github.com/anthropics/claude-code/issues