cokit-cli 1.0.1 → 1.0.2

package/prompts/ck-worktree.prompt.md

@@ -0,0 +1,127 @@
+---
+agent: 'agent'
+description: 'Create isolated git worktree for parallel development'
+tools: ['search/codebase', 'read/terminalLastCommand']
+---
+
+Create an isolated git worktree for parallel feature development.
+
+## Workflow
+
+### Step 1: Get Repository Info
+
+```bash
+node  info --json
+```
+
+**Response fields:**
+- `repoType`: "monorepo" or "standalone"
+- `baseBranch`: detected base branch
+- `projects`: array of {name, path} for monorepo
+- `envFiles`: array of .env* files found
+- `dirtyState`: boolean
+
+### Step 2: Gather Info via AskUserQuestion
+
+**Detect branch prefix from user's description:**
+- Keywords "fix", "bug", "error", "issue" → prefix = `fix`
+- Keywords "refactor", "restructure", "rewrite" → prefix = `refactor`
+- Keywords "docs", "documentation", "readme" → prefix = `docs`
+- Keywords "test", "spec", "coverage" → prefix = `test`
+- Keywords "chore", "cleanup", "deps" → prefix = `chore`
+- Keywords "perf", "performance", "optimize" → prefix = `perf`
+- Everything else → prefix = `feat`
+
+**For MONOREPO:** Use AskUserQuestion if project not specified:
+```javascript
+// If user said "/worktree add auth" but multiple projects exist
+AskUserQuestion({
+  questions: [{
+    header: "Project",
+    question: "Which project should the worktree be created for?",
+    options: projects.map(p => ({ label: p.name, description: p.path })),
+    multiSelect: false
+  }]
+})
+```
+
+**For env files:** Always ask which to copy:
+```javascript
+AskUserQuestion({
+  questions: [{
+    header: "Env files",
+    question: "Which environment files should be copied to the worktree?",
+    options: envFiles.map(f => ({ label: f, description: "Copy to worktree" })),
+    multiSelect: true
+  }]
+})
+```
+
+### Step 3: Convert Description to Slug
+
+- "add authentication system" → `add-auth`
+- "fix login bug" → `login-bug`
+- Remove filler words, kebab-case, max 50 chars
+
+### Step 4: Execute Command
+
+**Monorepo:**
+```bash
+node  create "<PROJECT>" "<SLUG>" --prefix <TYPE> --env "<FILES>"
+```
+
+**Standalone:**
+```bash
+node  create "<SLUG>" --prefix <TYPE> --env "<FILES>"
+```
+
+**Options:**
+- `--prefix` - Branch type: feat|fix|refactor|docs|test|chore|perf
+- `--env` - Comma-separated .env files to copy
+- `--json` - Output JSON for parsing
+- `--dry-run` - Preview without executing
+
+## Commands
+
+| Command | Usage | Description |
+|---------|-------|-------------|
+| `create` | `create [project] <feature>` | Create new worktree |
+| `remove` | `remove <name-or-path>` | Remove worktree and branch |
+| `info` | `info` | Get repo info |
+| `list` | `list` | List existing worktrees |
+
+## Error Codes
+
+| Code | Meaning | Action |
+|------|---------|--------|
+| `MISSING_ARGS` | Missing project/feature for monorepo | Ask for both |
+| `MISSING_FEATURE` | No feature name (standalone) | Ask for feature |
+| `PROJECT_NOT_FOUND` | Project not in .gitmodules | Show available projects |
+| `MULTIPLE_PROJECTS_MATCH` | Ambiguous project name | Use AskUserQuestion |
+| `MULTIPLE_WORKTREES_MATCH` | Ambiguous worktree for remove | Use AskUserQuestion |
+| `BRANCH_CHECKED_OUT` | Branch in use elsewhere | Suggest different name |
+| `WORKTREE_EXISTS` | Path already exists | Suggest use or remove |
+| `WORKTREE_CREATE_FAILED` | Git command failed | Show git error |
+| `WORKTREE_REMOVE_FAILED` | Cannot remove worktree | Check uncommitted changes |
+
+## Example Session
+
+```
+User: /worktree fix the login validation bug
+
+Claude: [Runs: node  info --json]
+        [Detects: standalone repo, envFiles: [".env.example"]]
+        [Detects prefix from "fix" keyword: fix]
+        [Converts slug: "login-validation-bug"]
+
+Claude: [Uses AskUserQuestion for env files]
+        "Which environment files should be copied?"
+        Options: .env.example
+
+User: .env.example
+
+Claude: [Runs: node  create "login-validation-bug" --prefix fix --env ".env.example"]
+
+Output: Worktree created at ../worktrees/myrepo-login-validation-bug
+        Branch: fix/login-validation-bug
+```

package/rules/README.agents.md

@@ -0,0 +1,55 @@
+# Agents (`.agent.md`)
+
+**Location:** `.github/agents/NAME.agent.md`
+
+## YAML Front Matter
+
+```yaml
+---
+name: agent-name                    # Optional, defaults to filename
+description: What it does           # Required
+target: vscode | github-copilot     # Optional, defaults to both
+tools: [tool1, tool2]               # Optional, defaults to all
+infer: true | false                 # Optional, defaults to true
+metadata:                           # Optional
+  key: value
+---
+```
+
+## Fields
+
+| Field | Required | Type | Default | Notes |
+|-------|----------|------|---------|-------|
+| `name` | No | string | filename | lowercase với hyphens |
+| `description` | **Yes** | string | - | Mô tả purpose |
+| `target` | No | string | both | `vscode` hoặc `github-copilot` |
+| `tools` | No | array/string | all | Tool names |
+| `infer` | No | boolean | true | Auto-invoke based on context |
+| `metadata` | No | object | - | Key-value pairs |
+
+## Checklist
+
+| # | Criteria | ☐ |
+|---|----------|---|
+| 1 | File extension `.agent.md` |  |
+| 2 | YAML front matter between `---` markers |  |
+| 3 | `description` field present (required) |  |
+| 4 | `name` lowercase với hyphens (nếu có) |  |
+| 5 | `tools` là array hoặc string |  |
+| 6 | Body content ≤ 30,000 characters |  |
+| 7 | Valid Markdown syntax trong body |  |
+
+## Example
+
+```markdown
+---
+name: code-reviewer
+description: Reviews code for best practices and security issues
+tools: [codebase, terminal]
+---
+
+You are a senior code reviewer. Focus on:
+- Security vulnerabilities
+- Performance issues
+- Code readability
+```

package/rules/README.collections.md

@@ -0,0 +1,78 @@
+# Collections (`.collection.yml`)
+
+**Location:** `.github/collections/NAME.collection.yml`
+
+## YAML Schema
+
+```yaml
+id: collection-id                   # Required, unique, lowercase-hyphens
+name: Collection Name               # Required
+description: What this collection   # Required
+tags: [tag1, tag2]                  # Optional, lowercase-hyphens
+items:                              # Required
+  - path: prompts/file.prompt.md
+    kind: prompt
+  - path: agents/file.agent.md
+    kind: agent
+  - path: instructions/file.instructions.md
+    kind: instruction
+display:                            # Optional
+  ordering: alpha | manual
+  show_badge: true | false
+  featured: true | false
+```
+
+## Fields
+
+| Field | Required | Type | Notes |
+|-------|----------|------|-------|
+| `id` | **Yes** | string | Unique, lowercase với hyphens |
+| `name` | **Yes** | string | Display name |
+| `description` | **Yes** | string | Purpose description |
+| `tags` | No | array | lowercase với hyphens |
+| `items` | **Yes** | array | List of items |
+| `display` | No | object | Display options |
+
+## Item Fields
+
+| Field | Required | Notes |
+|-------|----------|-------|
+| `path` | **Yes** | Relative path to file |
+| `kind` | **Yes** | `prompt`, `agent`, or `instruction` |
+
+## Checklist
+
+| # | Criteria | ☐ |
+|---|----------|---|
+| 1 | File extension `.collection.yml` |  |
+| 2 | Valid YAML syntax |  |
+| 3 | `id` field present (required) |  |
+| 4 | `id` unique, lowercase với hyphens |  |
+| 5 | `name` field present (required) |  |
+| 6 | `description` field present (required) |  |
+| 7 | `items` array present (required) |  |
+| 8 | Each item có `path` và `kind` |  |
+| 9 | `path` references existing files |  |
+| 10 | `kind` matches file extension |  |
+| 11 | `tags` lowercase với hyphens (nếu có) |  |
+
+## Example
+
+```yaml
+id: react-development
+name: React Development
+description: Tools and prompts for React development workflow
+tags: [react, frontend, typescript]
+items:
+  - path: prompts/generate-component.prompt.md
+    kind: prompt
+  - path: prompts/generate-tests.prompt.md
+    kind: prompt
+  - path: agents/react-expert.agent.md
+    kind: agent
+  - path: instructions/components.instructions.md
+    kind: instruction
+display:
+  ordering: alpha
+  show_badge: true
+```

package/rules/README.copilot-instructions.md

@@ -0,0 +1,66 @@
+# Instructions (`copilot-instructions.md`)
+
+**Location:** `.github/copilot-instructions.md`
+
+## Format
+
+```markdown
+# No YAML front matter required
+
+Natural language instructions in Markdown.
+Each instruction as self-contained statement.
+```
+
+## Rules
+
+- Single file per repository
+- No YAML front matter needed
+- Size ≤ 8KB (~2 pages)
+- Instructions ngắn gọn, self-contained
+- Whitespace between instructions ignored
+
+## Checklist
+
+| # | Criteria | ☐ |
+|---|----------|---|
+| 1 | File path `.github/copilot-instructions.md` |  |
+| 2 | Single file per repository |  |
+| 3 | Valid Markdown syntax |  |
+| 4 | Size ≤ 8KB (~2 pages) |  |
+| 5 | No YAML front matter needed |  |
+| 6 | Instructions ngắn gọn, self-contained |  |
+| 7 | No secrets/credentials |  |
+
+## Content Guidelines
+
+Include:
+- Project summary/description
+- Tech stack
+- Coding conventions
+- Build/test commands
+- Project structure
+- Available tools/resources
+
+## Example
+
+```markdown
+# Project Instructions
+
+This is a React + TypeScript web application using Vite.
+
+## Tech Stack
+- React 18 with TypeScript
+- Tailwind CSS for styling
+- React Query for data fetching
+- Vitest for testing
+
+## Conventions
+- Use functional components with hooks
+- Prefer named exports over default exports
+- Use `const` over `let` when possible
+
+## Commands
+- `npm run dev` - Start development server
+- `npm run build` - Build for production
+- `npm run test` - Run tests
+```

package/rules/README.instructions.md

@@ -0,0 +1,73 @@
+# File-Specific Instructions (`.instructions.md`)
+
+**Location:** `.github/instructions/NAME.instructions.md`
+
+## YAML Front Matter
+
+```yaml
+---
+applyTo: "**/*.ts"                  # Required, glob pattern
+excludeAgent: code-review           # Optional
+---
+```
+
+## Fields
+
+| Field | Required | Type | Notes |
+|-------|----------|------|-------|
+| `applyTo` | **Yes** | string | Glob pattern |
+| `excludeAgent` | No | string | `code-review` hoặc `coding-agent` |
+
+## Glob Patterns
+
+```
+*                    # Current dir files
+**/*                 # All files recursive
+*.py                 # Extension in current dir
+src/**/*.py          # Recursive in subdir
+**/*.{ts,tsx}        # Multiple extensions
+**/test/**/*.ts      # Files in test folders
+```
+
+## Checklist
+
+| # | Criteria | ☐ |
+|---|----------|---|
+| 1 | File extension `.instructions.md` |  |
+| 2 | File trong `.github/instructions/` folder |  |
+| 3 | YAML front matter present |  |
+| 4 | `applyTo` field present (required) |  |
+| 5 | `applyTo` valid glob pattern |  |
+| 6 | `excludeAgent` valid value (nếu có) |  |
+| 7 | Body contains instructions |  |
+| 8 | No overlapping patterns gây conflict |  |
+
+## Example
+
+**tests.instructions.md:**
+```markdown
+---
+applyTo: "**/*.test.ts,**/*.spec.ts"
+---
+
+# Test Guidelines
+
+- Use describe/it pattern
+- Mock external dependencies
+- Aim for 80% coverage
+- Test edge cases
+```
+
+**components.instructions.md:**
+```markdown
+---
+applyTo: "src/components/**/*.tsx"
+excludeAgent: code-review
+---
+
+# Component Guidelines
+
+- Use functional components
+- Props interface above component
+- Extract hooks to separate files
+```

package/rules/README.md

@@ -0,0 +1,39 @@
+# GitHub Copilot Rules
+
+Rules để tạo và verify các file types cho GitHub Copilot.
+
+## File Types
+
+| File | Extension | Location |
+|------|-----------|----------|
+| [Agents](README.agents.md) | `.agent.md` | `.github/agents/` |
+| [Skills](README.skills.md) | `SKILL.md` | `.github/skills/*/` |
+| [Prompts](README.prompts.md) | `.prompt.md` | `.github/prompts/` |
+| [Instructions](README.instructions.md) | `copilot-instructions.md` | `.github/` |
+| [File-Specific Instructions](README.file-instructions.md) | `.instructions.md` | `.github/instructions/` |
+| [Collections](README.collections.md) | `.collection.yml` | `.github/collections/` |
+
+## Directory Structure
+
+```
+.github/
+├── copilot-instructions.md
+├── agents/
+│   └── *.agent.md
+├── prompts/
+│   └── *.prompt.md
+├── instructions/
+│   └── *.instructions.md
+├── skills/
+│   └── skill-name/
+│       └── SKILL.md
+└── collections/
+    └── *.collection.yml
+```
+
+## Sources
+
+- [Custom Agents Configuration - GitHub Docs](https://docs.github.com/en/copilot/reference/custom-agents-configuration)
+- [Agent Skills in VS Code](https://code.visualstudio.com/docs/copilot/customization/agent-skills)
+- [Prompt Files in VS Code](https://code.visualstudio.com/docs/copilot/customization/prompt-files)
+- [Awesome Copilot Repository](https://github.com/github/awesome-copilot)

package/rules/README.prompts.md

@@ -0,0 +1,76 @@
+# Prompts (`.prompt.md`)
+
+**Location:** `.github/prompts/NAME.prompt.md`
+
+## YAML Front Matter
+
+```yaml
+---
+name: prompt-name                   # Optional, defaults to filename
+description: What this prompt does  # Optional but recommended
+agent: ask | edit | agent | custom  # Optional
+model: GPT-4o | Claude-Sonnet-4     # Optional
+mode: edit                          # Optional
+tools: [tool1, tool2]               # Optional
+argument-hint: hint text            # Optional
+---
+```
+
+## Fields
+
+| Field | Required | Type | Default | Notes |
+|-------|----------|------|---------|-------|
+| `name` | No | string | filename | Display name |
+| `description` | No | string | - | For discoverability |
+| `agent` | No | string | current | `ask`, `edit`, `agent`, or custom |
+| `model` | No | string | selected | Language model ID |
+| `mode` | No | string | - | Execution mode |
+| `tools` | No | array | - | Available tools |
+| `argument-hint` | No | string | - | Hint text |
+
+## Variables trong Body
+
+```
+${workspaceFolder}           # Workspace root path
+${workspaceFolderBasename}   # Workspace folder name
+${file}                      # Current file path
+${fileBasename}              # Current file name
+${fileDirname}               # Current file directory
+${selection}                 # Selected text
+${selectedText}              # Same as selection
+${input:varName}             # User input
+${input:varName:placeholder} # User input with placeholder
+```
+
+## Checklist
+
+| # | Criteria | ☐ |
+|---|----------|---|
+| 1 | File extension `.prompt.md` |  |
+| 2 | File trong `.github/prompts/` folder |  |
+| 3 | Filename alphanumeric và spaces |  |
+| 4 | YAML front matter valid (nếu có) |  |
+| 5 | `tools` là array of strings |  |
+| 6 | File references dùng relative paths |  |
+| 7 | Variables syntax đúng `${...}` |  |
+| 8 | Body content present |  |
+
+## Example
+
+```markdown
+---
+name: generate-tests
+description: Generate unit tests for selected code
+agent: agent
+tools: [codebase, terminal]
+---
+
+Generate comprehensive unit tests for the following code:
+
+${selection}
+
+Requirements:
+- Use Jest framework
+- Cover edge cases
+- Mock external dependencies
+```

package/rules/README.skills.md

@@ -0,0 +1,71 @@
+# Skills
+
+**Location:** `.github/skills/SKILL-NAME/SKILL.md`
+
+## Directory Structure
+
+```
+.github/skills/
+└── skill-name/
+    ├── SKILL.md          # Required
+    ├── scripts/          # Optional
+    ├── examples/         # Optional
+    └── resources/        # Optional
+```
+
+## YAML Front Matter (SKILL.md)
+
+```yaml
+---
+name: skill-identifier              # Required, lowercase với hyphens, ≤64 chars
+description: What and when to use   # Required, ≤1024 chars
+---
+```
+
+## Fields
+
+| Field | Required | Type | Limit | Notes |
+|-------|----------|------|-------|-------|
+| `name` | **Yes** | string | 64 chars | lowercase với hyphens |
+| `description` | **Yes** | string | 1024 chars | What + when to use |
+
+## Checklist
+
+| # | Criteria | ☐ |
+|---|----------|---|
+| 1 | Folder name lowercase với hyphens |  |
+| 2 | `SKILL.md` file exists trong folder |  |
+| 3 | `name` field present (required) |  |
+| 4 | `name` lowercase với hyphens |  |
+| 5 | `name` ≤ 64 characters |  |
+| 6 | `description` field present (required) |  |
+| 7 | `description` ≤ 1024 characters |  |
+| 8 | Resources referenced bằng relative paths |  |
+
+## Example
+
+```
+.github/skills/
+└── webapp-testing/
+    ├── SKILL.md
+    ├── scripts/
+    │   └── run-tests.sh
+    └── examples/
+        └── test-template.js
+```
+
+**SKILL.md:**
+```markdown
+---
+name: webapp-testing
+description: Run and debug web application tests using Jest and Playwright
+---
+
+# Web App Testing
+
+Use this skill when testing React/Vue applications.
+
+## Scripts
+- [run-tests.sh](./scripts/run-tests.sh) - Run all tests
+- [test-template.js](./examples/test-template.js) - Example test
+```

package/skills/ck-ai-artist/SKILL.md

@@ -0,0 +1,73 @@
+---
+name: 'ck-ai-artist'
+description: 'Write and optimize prompts for AI-generated outcomes across text and image models. Use when crafting prompts for LLMs (Claude, GPT, Gemini), image generators (Midjourney, DALL-E, Stable Diffusion, Imagen, Flux), or video generators (Veo, Runway). Covers prompt structure, style keywords, negative prompts, chain-of-thought, few-shot examples, iterative refinement, and domain-specific patterns for marketing, code, and creative writing.'
+---
+
+# AI Artist - Prompt Engineering
+
+Craft effective prompts for AI text and image generation models.
+
+## Core Principles
+
+1. **Clarity** - Be specific, avoid ambiguity
+2. **Context** - Set scene, role, constraints upfront
+3. **Structure** - Use consistent formatting (markdown, XML tags, delimiters)
+4. **Iteration** - Refine based on outputs, A/B test variations
+
+## Quick Patterns
+
+### LLM Prompts (Claude/GPT/Gemini)
+
+```
+[Role] You are a {expert type} specializing in {domain}.
+[Context] {Background information and constraints}
+[Task] {Specific action to perform}
+[Format] {Output structure - JSON, markdown, list, etc.}
+[Examples] {1-3 few-shot examples if needed}
+```
+
+### Image Generation (Midjourney/DALL-E/Stable Diffusion)
+
+```
+[Subject] {main subject with details}
+[Style] {artistic style, medium, artist reference}
+[Composition] {framing, angle, lighting}
+[Quality] {resolution modifiers, rendering quality}
+[Negative] {what to avoid - only if supported}
+```
+
+**Example**: `Portrait of a cyberpunk hacker, neon lighting, cinematic composition, detailed face, 8k, artstation quality --ar 16:9 --style raw`
+
+## References
+
+Load for detailed guidance:
+
+| Topic | File | Description |
+|-------|------|-------------|
+| LLM | `references/llm-prompting.md` | System prompts, few-shot, CoT, output formatting |
+| Image | `references/image-prompting.md` | Style keywords, model syntax, negative prompts |
+| Nano Banana | `references/nano-banana.md` | Gemini image prompting, narrative style, multi-image input |
+| Advanced | `references/advanced-techniques.md` | Meta-prompting, chaining, A/B testing |
+| Domain Index | `references/domain-patterns.md` | Universal pattern, links to domain files |
+| Marketing | `references/domain-marketing.md` | Headlines, product copy, emails, ads |
+| Code | `references/domain-code.md` | Functions, review, refactoring, debugging |
+| Writing | `references/domain-writing.md` | Stories, characters, dialogue, editing |
+| Data | `references/domain-data.md` | Extraction, analysis, comparison |
+
+## Model-Specific Tips
+
+| Model | Key Syntax |
+|-------|------------|
+| Midjourney | `--ar`, `--style`, `--chaos`, `--weird`, `--v 6.1` |
+| DALL-E 3 | Natural language, no parameters, HD quality option |
+| Stable Diffusion | Weighted tokens `(word:1.2)`, LoRA, negative prompt |
+| Flux | Natural prompts, style mixing, `--guidance` |
+| Imagen/Veo | Descriptive text, aspect ratio, style references |
+
+## Anti-Patterns
+
+- Vague instructions ("make it better")
+- Conflicting constraints
+- Missing context for domain tasks
+- Over-prompting with redundant details
+- Ignoring model-specific strengths/limits