@trieungoctam/vibekit 1.0.0 → 1.0.4

package/README.md

@@ -2,6 +2,27 @@
 
 Unified IDE configuration system with multi-IDE support.
 
+## Quick Start
+
+```bash
+# In your project directory
+npx @trieungoctam/vibekit init
+```
+
+## CLI Options
+
+```bash
+# Select specific IDEs
+npx @trieungoctam/vibekit init --no-interactive --ide claude cursor
+
+# Overwrite existing files
+npx @trieungoctam/vibekit init --force
+
+# Install globally
+npm install -g @trieungoctam/vibekit
+vibekit init
+```
+
 ## Supported IDEs
 
 - Claude Code
@@ -11,8 +32,17 @@ Unified IDE configuration system with multi-IDE support.
 
 ## Installation
 
+### Via npm (Recommended)
+```bash
+npx @trieungoctam/vibekit init
+```
+
+### Local development
 ```bash
-./install.sh
+git clone https://github.com/trieungoctam/vibekit.git
+cd vibekit
+npm install
+node bin/vibekit.js init
 ```
 
 Windows:
@@ -46,19 +76,19 @@ vibekit/
 └── .opencode/        # OpenCode config
 ```
 
-## Skills
+## Skills (all with `vk:` prefix)
 
-### Core (13)
-brainstorm, plan, tdd, debug, code-review, execute, subagent-dev, verify, fix, cook, test, simplify, update-config
+### Core (11)
+`vk:brainstorm`, `vk:plan`, `vk:tdd`, `vk:debug`, `vk:code-review`, `vk:execute`, `vk:subagent-dev`, `vk:verify`, `vk:fix`, `vk:cook`, `vk:test`
 
 ### Dev (8)
-frontend-dev, backend-dev, databases, git, git-worktree, devops, frontend-design, context-engineering
+`vk:frontend-dev`, `vk:backend-dev`, `vk:databases`, `vk:git`, `vk:git-worktree`, `vk:devops`, `vk:frontend-design`, `vk:context-engineering`
 
 ### AI (4)
-ai-multimodal, ai-artist, mcp-management, agent-browser
+`vk:ai-multimodal`, `vk:ai-artist`, `vk:mcp-management`, `vk:agent-browser`
 
 ### Utils (13)
-bootstrap, docs-manager, sequential-thinking, scout, repomix, preview, research, ask, kanban, journal, ck-help, write-skill, copywriting
+`vk:bootstrap`, `vk:docs`, `vk:sequential-thinking`, `vk:scout`, `vk:repomix`, `vk:preview`, `vk:research`, `vk:ask`, `vk:kanban`, `vk:journal`, `vk:help`, `vk:write-skill`, `vk:copywriting`
 
 ## Agents
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@trieungoctam/vibekit",
-  "version": "1.0.0",
+  "version": "1.0.4",
   "description": "Unified IDE configuration - setup rules/skills directly in your repo",
   "type": "module",
   "bin": {

package/skills/ai/{mcp-management → vk:mcp-management}/SKILL.md

@@ -81,7 +81,7 @@ echo "Take a screenshot of https://example.com" | gemini -y -m <gemini.model>
 npx tsx scripts/cli.ts call-tool memory create_entities '{"entities":[...]}'
 ```
 
-**Fallback: mcp-manager Subagent**
+**Fallbavk: mcp-manager Subagent**
 
 See [references/gemini-cli-integration.md](references/gemini-cli-integration.md) for complete examples.
 
@@ -185,7 +185,7 @@ See [references/mcp-protocol.md](references/mcp-protocol.md) for:
 ### Execution Priority
 
 1. **Gemini CLI** (Primary): Fast, automatic, intelligent tool selection
-   - Check: `command -v gemini`
+   - Chevk: `command -v gemini`
    - Execute: `echo "<task>" | gemini -y -m <gemini.model>`
    - **IMPORTANT**: Use stdin piping, NOT `-p` flag (deprecated, skips MCP init)
    - Best for: All tasks when available

package/skills/core/{code-review → vk:code-review}/SKILL.md

@@ -56,7 +56,7 @@ SITUATION?
 - No performative agreement: "You're absolutely right!", "Great point!"
 - No implementation before verification
 - Restate, ask questions, push back with reasoning, or just work
-- YAGNI check: grep for usage before implementing "proper" features
+- YAGNI chevk: grep for usage before implementing "proper" features
 
 **Source handling:**
 - Human partner: Trusted - implement after understanding
@@ -81,7 +81,7 @@ SITUATION?
 **When:** After implementation, before requesting code-reviewer
 
 **Process:**
-1. Invoke `/ck:scout` with edge-case-focused prompt
+1. Invoke `/vk:scout` with edge-case-focused prompt
 2. Scout analyzes: affected files, data flows, error paths, boundary conditions
 3. Review scout findings for potential issues
 4. Address critical gaps before code review
@@ -134,8 +134,8 @@ TaskCreate: "Verify fixes pass"        → pending, blockedBy: [fix]
 
 | Subcommand | Reference | Purpose |
 |------------|-----------|---------|
-| `/ck:code-review codebase` | `references/codebase-scan-workflow.md` | Scan & analyze the codebase |
-| `/ck:code-review codebase parallel` | `references/parallel-review-workflow.md` | Ultrathink edge cases, then parallel verify |
+| `/vk:code-review codebase` | `references/codebase-scan-workflow.md` | Scan & analyze the codebase |
+| `/vk:code-review codebase parallel` | `references/parallel-review-workflow.md` | Ultrathink edge cases, then parallel verify |
 
 ## Bottom Line
 

package/skills/core/{cook → vk:cook}/SKILL.md

@@ -92,7 +92,7 @@ Human review required at these checkpoints (skipped with `--auto`):
 | Phase | Subagent | Requirement |
 |-------|----------|-------------|
 | Research | `researcher` | Optional in fast/code |
-| Scout | `ck:scout` | Optional in code |
+| Scout | `vk:scout` | Optional in code |
 | Plan | `planner` | Optional in code |
 | UI Work | `ui-ux-designer` | If frontend work |
 | Testing | `tester`, `debugger` | **MUST** spawn |

package/skills/core/{debug → vk:debug}/SKILL.md

@@ -80,7 +80,7 @@ Track investigation pipelines via Claude Native Tasks (TaskCreate, TaskUpdate, T
 
 ### 10. Frontend Verification (`references/frontend-verification.md`)
 
-Visual verification of frontend implementations via Chrome MCP (Claude Chrome Extension) or `ck:chrome-devtools` skill fallback. Detect if frontend-related → check Chrome MCP availability → screenshot + console error check → report. Skip if not frontend.
+Visual verification of frontend implementations via Chrome MCP (Claude Chrome Extension) or `vk:chrome-devtools` skill fallback. Detect if frontend-related → check Chrome MCP availability → screenshot + console error check → report. Skip if not frontend.
 
 **Load when:** Implementation touches frontend files (tsx/jsx/vue/svelte/html/css), UI bugs, visual regressions
 
@@ -104,10 +104,10 @@ Frontend fix   → frontend-verification.md (Chrome/devtools)
 
 - **Database:** `psql` for PostgreSQL queries and diagnostics
 - **CI/CD:** `gh` CLI for GitHub Actions logs and pipeline debugging
-- **Codebase:** `ck:docs-seeker` skill for package/plugin docs; `repomix` for codebase summary
-- **Scouting:** `/ck:scout` or `/ck:scout ext` for finding relevant files
-- **Frontend:** Chrome browser or `ck:chrome-devtools` skill for visual verification (screenshots, console, network)
-- **Skills:** Activate `ck:problem-solving` skill when stuck on complex issues
+- **Codebase:** `vk:docs-seeker` skill for package/plugin docs; `repomix` for codebase summary
+- **Scouting:** `/vk:scout` or `/vk:scout ext` for finding relevant files
+- **Frontend:** Chrome browser or `vk:chrome-devtools` skill for visual verification (screenshots, console, network)
+- **Skills:** Activate `vk:problem-solving` skill when stuck on complex issues
 
 ## Red Flags
 

package/skills/core/{fix → vk:fix}/SKILL.md

@@ -32,7 +32,7 @@ See `references/mode-selection.md` for AskUserQuestion format.
 
 ### Step 2: Debug
 
-- Activate `ck:debug` skill.
+- Activate `vk:debug` skill.
 - Guess all possible root causes.
 - Spawn multiple `Explore` subagents in parallel to verify each hypothesis.
 - Create report with all findings for the next step.
@@ -73,8 +73,8 @@ Classify before routing. See `references/complexity-assessment.md`.
 
 See `references/skill-activation-matrix.md` for complete matrix.
 
-**Always activate:** `ck:debug` (all workflows)
-**Conditional:** `ck:problem-solving`, `ck:sequential-thinking`, `ck:brainstorm`, `ck:context-engineering`
+**Always activate:** `vk:debug` (all workflows)
+**Conditional:** `vk:problem-solving`, `vk:sequential-thinking`, `vk:brainstorm`, `vk:context-engineering`
 **Subagents:** `debugger`, `researcher`, `planner`, `code-reviewer`, `tester`, `Bash`
 **Parallel:** Multiple `Explore` agents for scouting, `Bash` agents for verification
 
@@ -96,7 +96,7 @@ Load as needed:
 - `references/mode-selection.md` - AskUserQuestion format for mode
 - `references/complexity-assessment.md` - Classification criteria
 - `references/task-orchestration.md` - Native Claude Task patterns for moderate+ workflows
-- `references/workflow-quick.md` - Quick: debug → fix → review
+- `references/workflow-quick.md` - Quivk: debug → fix → review
 - `references/workflow-standard.md` - Standard: full pipeline with Tasks
 - `references/workflow-deep.md` - Deep: research + brainstorm + plan with Tasks
 - `references/review-cycle.md` - Review logic (autonomous vs HITL)

package/skills/core/{plan → vk:plan}/SKILL.md

@@ -55,7 +55,7 @@ This structure informs the task decomposition. Each task should produce self-con
 
 **Architecture:** [2-3 sentences about approach]
 
-**Tech Stack:** [Key technologies/libraries]
+**Tech Stavk:** [Key technologies/libraries]
 
 ---
 ```

package/skills/core/{test → vk:test}/SKILL.md

@@ -42,7 +42,7 @@ Execute test suites, analyze results, generate coverage. Supports JS/TS (Jest/Vi
 
 ### 2. UI Testing (`references/ui-testing-workflow.md`)
 
-Browser-based visual testing via `ck:chrome-devtools` skill. Screenshots, responsive checks, accessibility audits, form automation, console error collection. Includes auth injection for protected routes.
+Browser-based visual testing via `vk:chrome-devtools` skill. Screenshots, responsive checks, accessibility audits, form automation, console error collection. Includes auth injection for protected routes.
 
 **Load when:** Visual regression testing, UI bugs, responsive layout checks, accessibility audits
 
@@ -74,17 +74,17 @@ Reports        → report-format.md
 3. Execute appropriate test suites
 4. Analyze results — focus on failures
 5. Generate coverage reports if applicable
-6. For frontend: run UI tests via `ck:chrome-devtools` skill
+6. For frontend: run UI tests via `vk:chrome-devtools` skill
 7. Produce structured summary report
 
 ## Tools Integration
 
 - **Test runners**: Jest, Vitest, Mocha, pytest, go test, cargo test, flutter test
 - **Coverage**: Istanbul/c8/nyc, pytest-cov, go cover
-- **Browser**: `ck:chrome-devtools` skill for UI testing (screenshots, ARIA, console, network)
-- **Analysis**: `ck:ai-multimodal` skill for screenshot analysis
-- **Debugging**: `ck:debug` skill when tests reveal bugs requiring investigation
-- **Thinking**: `ck:sequential-thinking` skill for complex test failure analysis
+- **Browser**: `vk:chrome-devtools` skill for UI testing (screenshots, ARIA, console, network)
+- **Analysis**: `vk:ai-multimodal` skill for screenshot analysis
+- **Debugging**: `vk:debug` skill when tests reveal bugs requiring investigation
+- **Thinking**: `vk:sequential-thinking` skill for complex test failure analysis
 
 ## Quality Standards
 

package/skills/dev/{frontend-design → vk:frontend-design}/SKILL.md

@@ -20,11 +20,11 @@ Choose workflow based on input type:
 | Complex/award-quality | Full immersive | `./references/workflow-immersive.md` |
 | From scratch | Design Thinking below | - |
 
-**All workflows**: Activate `ck:ui-ux-pro-max` skill FIRST for design intelligence.
+**All workflows**: Activate `vk:ui-ux-pro-max` skill FIRST for design intelligence.
 
 ## Screenshot/Video Replication (Quick Reference)
 
-1. **Analyze** with `ck:ai-multimodal` skill - extract colors, fonts, spacing, effects
+1. **Analyze** with `vk:ai-multimodal` skill - extract colors, fonts, spacing, effects
 2. **Plan** with `ui-ux-designer` subagent - create phased implementation
 3. **Implement** - match source precisely
 4. **Verify** - compare to original
@@ -49,7 +49,7 @@ Before coding, commit to a BOLD aesthetic direction:
 - **Motion**: CSS-first, anime.js for complex (`./references/animejs.md`). Orchestrated page loads > scattered micro-interactions.
 - **Spatial**: Unexpected layouts. Asymmetry. Overlap. Negative space OR controlled density.
 - **Backgrounds**: Atmosphere over solid colors. Gradients, noise, patterns, shadows, grain.
-- **Assets**: Generate with `ck:ai-multimodal`, process with `ck:media-processing`
+- **Assets**: Generate with `vk:ai-multimodal`, process with `vk:media-processing`
 
 ## Asset & Analysis References
 

package/skills/dev/{git → vk:git}/SKILL.md

@@ -21,7 +21,7 @@ If invoked without arguments, use `AskUserQuestion` to present available git ope
 Present as options via `AskUserQuestion` with header "Git Operation", question "What would you like to do?".
 
 Execute git workflows via `git-manager` subagent to isolate verbose output.
-Activate `ck:context-engineering` skill.
+Activate `vk:context-engineering` skill.
 
 **IMPORTANT:**
 - Sacrifice grammar for the sake of concision.

package/skills/utils/{ask → vk:ask}/SKILL.md

@@ -37,7 +37,7 @@ You operate by the holy trinity of software engineering: **YAGNI** (You Aren't G
 
 ## Process
 1. **Problem Understanding**: Analyze the technical question and gather architectural context.
-   - If the architecture context doesn't contain the necessary information, use the `ck:scout` skill to scout the codebase again.
+   - If the architecture context doesn't contain the necessary information, use the `vk:scout` skill to scout the codebase again.
 2. **Expert Consultation**:
    - Systems Designer: Define system boundaries, data flows, and component relationships
    - Technology Strategist: Evaluate technology choices, patterns, and industry best practices

package/skills/utils/{bootstrap → vk:bootstrap}/SKILL.md

@@ -63,20 +63,20 @@ Check if Git initialized. If not:
 After early phases (research, tech stack, design), trigger downstream skills:
 
 ### Planning Phase
-Activate **ck:plan** skill with mode-appropriate flag:
-- `--full` → `/ck:plan --hard <requirements>` (thorough research + validation)
-- `--auto` → `/ck:plan --auto <requirements>` (auto-detect complexity)
-- `--fast` → `/ck:plan --fast <requirements>` (skip research)
-- `--parallel` → `/ck:plan --parallel <requirements>` (file ownership + dependency graph)
+Activate **vk:plan** skill with mode-appropriate flag:
+- `--full` → `/vk:plan --hard <requirements>` (thorough research + validation)
+- `--auto` → `/vk:plan --auto <requirements>` (auto-detect complexity)
+- `--fast` → `/vk:plan --fast <requirements>` (skip research)
+- `--parallel` → `/vk:plan --parallel <requirements>` (file ownership + dependency graph)
 
 Planning skill outputs a plan path. Pass this to cook.
 
 ### Implementation Phase
-Activate **ck:cook** skill with the plan path and mode-appropriate flag:
-- `--full` → `/ck:cook <plan-path>` (interactive review gates)
-- `--auto` → `/ck:cook --auto <plan-path>` (skip review gates)
-- `--fast` → `/ck:cook --auto <plan-path>` (skip review gates)
-- `--parallel` → `/ck:cook --parallel <plan-path>` (multi-agent execution)
+Activate **vk:cook** skill with the plan path and mode-appropriate flag:
+- `--full` → `/vk:cook <plan-path>` (interactive review gates)
+- `--auto` → `/vk:cook --auto <plan-path>` (skip review gates)
+- `--fast` → `/vk:cook --auto <plan-path>` (skip review gates)
+- `--parallel` → `/vk:cook --parallel <plan-path>` (multi-agent execution)
 
 ## Role
 

package/skills/utils/{docs → vk:docs}/SKILL.md

@@ -24,9 +24,9 @@ Present as options via `AskUserQuestion` with header "Documentation Operation",
 
 | Subcommand | Reference | Purpose |
 |------------|-----------|---------|
-| `/ck:docs init` | `references/init-workflow.md` | Analyze codebase and create initial documentation |
-| `/ck:docs update` | `references/update-workflow.md` | Analyze codebase and update existing documentation |
-| `/ck:docs summarize` | `references/summarize-workflow.md` | Quick analysis and update of codebase summary |
+| `/vk:docs init` | `references/init-workflow.md` | Analyze codebase and create initial documentation |
+| `/vk:docs update` | `references/update-workflow.md` | Analyze codebase and update existing documentation |
+| `/vk:docs summarize` | `references/summarize-workflow.md` | Quick analysis and update of codebase summary |
 
 ## Routing
 

package/skills/utils/{ck-help → vk:help}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: ck-help
+name: vk:help
 description: "ClaudeKit usage guide — discover commands, skills, workflows naturally."
 argument-hint: "[category|command|task description]"
 ---
@@ -35,7 +35,7 @@ The Python script only understands English keywords. If `$ARGUMENTS` is in anoth
 ## Execution
 
 ```bash
-python .claude/skills/ck-help/scripts/ck-help.py "$ARGUMENTS"
+python .claude/skills/vk:help/scripts/vk:help.py "$ARGUMENTS"
 ```
 
 ## Output Type Detection
@@ -97,6 +97,6 @@ Never replace or summarize the script output. Always show it fully, then enhance
 
 ## Important: Correct Workflows
 
-- **`/ck:plan` → `/ck:cook`**: Best for high-risk or complex changes
-- **`/ck:cook`**: Standalone for straightforward implementation
-- **NEVER** claim `/ck:plan` is mandatory before `/ck:cook`
+- **`/vk:plan` → `/vk:cook`**: Best for high-risk or complex changes
+- **`/vk:cook`**: Standalone for straightforward implementation
+- **NEVER** claim `/vk:plan` is mandatory before `/vk:cook`

package/skills/utils/{kanban → vk:kanban}/SKILL.md

@@ -10,9 +10,9 @@ Plans dashboard with progress tracking and timeline visualization.
 
 ## Usage
 
-- `/ck:kanban` - View dashboard for ./plans directory
-- `/ck:kanban <dir>` - View dashboard for specific directory
-- `/ck:kanban --stop` - Stop running server
+- `/vk:kanban` - View dashboard for ./plans directory
+- `/vk:kanban <dir>` - View dashboard for specific directory
+- `/vk:kanban --stop` - Stop running server
 
 ## Features
 
@@ -77,7 +77,7 @@ After starting, parse the JSON output and report:
 
 ## Future Plans
 
-The `/ck:kanban` command will evolve into **VibeKanban-inspired** AI agent orchestration:
+The `/vk:kanban` command will evolve into **VibeKanban-inspired** AI agent orchestration:
 
 ### Phase 1 (Current - MVP)
 - Task board with progress tracking

package/skills/utils/{preview → vk:preview}/SKILL.md

@@ -26,15 +26,15 @@ Present as options via `AskUserQuestion` with header "Preview Operation", questi
 ## Usage
 
 ### View Mode
-- `/ck:preview <file.md>` - View markdown file in novel-reader UI
-- `/ck:preview <directory/>` - Browse directory contents
-- `/ck:preview --stop` - Stop running server
+- `/vk:preview <file.md>` - View markdown file in novel-reader UI
+- `/vk:preview <directory/>` - Browse directory contents
+- `/vk:preview --stop` - Stop running server
 
 ### Generation Mode
-- `/ck:preview --explain <topic>` - Generate visual explanation (ASCII + Mermaid + prose)
-- `/ck:preview --slides <topic>` - Generate presentation slides (one concept per slide)
-- `/ck:preview --diagram <topic>` - Generate focused diagram (ASCII + Mermaid)
-- `/ck:preview --ascii <topic>` - Generate ASCII-only diagram (terminal-friendly)
+- `/vk:preview --explain <topic>` - Generate visual explanation (ASCII + Mermaid + prose)
+- `/vk:preview --slides <topic>` - Generate presentation slides (one concept per slide)
+- `/vk:preview --diagram <topic>` - Generate focused diagram (ASCII + Mermaid)
+- `/vk:preview --ascii <topic>` - Generate ASCII-only diagram (terminal-friendly)
 
 ## Argument Resolution
 
@@ -65,10 +65,10 @@ When processing arguments, follow this priority order:
 | Error | Action |
 |-------|--------|
 | Invalid topic (empty) | Ask user to provide a topic |
-| Flag without topic | Ask user: "Please provide a topic: `/ck:preview --explain <topic>`" |
+| Flag without topic | Ask user: "Please provide a topic: `/vk:preview --explain <topic>`" |
 | Topic becomes empty after sanitization | Ask for topic with alphanumeric characters |
 | File write failure | Report error, suggest checking permissions |
-| Server startup failure | Check if port in use, try `/ck:preview --stop` first |
+| Server startup failure | Check if port in use, try `/vk:preview --stop` first |
 | No generation flag + unresolvable reference | Ask user to clarify which file they meant |
 | Existing file at output path | Overwrite with new content (no prompt) |
 | Server already running | Reuse existing server instance, just open new URL |

package/skills/utils/{research → vk:research}/SKILL.md

@@ -37,7 +37,7 @@ You will employ a multi-source research strategy:
    - **IMPORTANT:** You are allowed to perform at most **5 researches (max 5 tool calls)**, user might request less than this amount, **strictly respect it**, think carefully based on the task before performing each related research topic.
 
 2. **Deep Content Analysis**:
-   - When you found a potential Github repository URL, use `ck:docs-seeker` skill to find read it.
+   - When you found a potential Github repository URL, use `vk:docs-seeker` skill to find read it.
    - Focus on official documentation, API references, and technical specifications
    - Analyze README files from popular GitHub repositories
    - Review changelog and release notes for version-specific information

package/src/commands/init.js

@@ -45,6 +45,9 @@ export async function initCommand(options) {
   // Copy .vibekit folder (skills, agents, hooks, rules)
   await setupVibekitFolder(targetDir, options.force);
 
+  // Setup plans folder
+  await setupPlansFolder(targetDir, options.force);
+
   // Setup each IDE
   for (const ide of ides) {
     await setupIDE(ide, targetDir, options.force);
@@ -54,7 +57,7 @@ export async function initCommand(options) {
   console.log(chalk.gray('Next steps:'));
   console.log(chalk.gray('  - Restart your IDE'));
   console.log(chalk.gray('  - Edit .vibekit/rules/ for project-specific rules'));
-  console.log(chalk.gray('  - Run /brainstorm or /plan to test skills\n'));
+  console.log(chalk.gray('  - Run /vk:brainstorm or /vk:plan to test skills\n'));
 }
 
 async function setupVibekitFolder(targetDir, force) {
@@ -82,6 +85,43 @@ async function setupVibekitFolder(targetDir, force) {
   }
 }
 
+async function setupPlansFolder(targetDir, force) {
+  const plansDir = path.join(targetDir, 'plans');
+
+  if (fs.existsSync(plansDir) && !force) {
+    console.log(chalk.yellow('  plans/ already exists, use --force to overwrite'));
+    return;
+  }
+
+  console.log(chalk.blue('📋 Setting up plans/'));
+
+  // Create plans directory structure
+  fs.ensureDirSync(plansDir);
+  fs.ensureDirSync(path.join(plansDir, 'reports'));
+
+  // Copy templates
+  const templatesDir = path.join(VIBEKIT_ROOT, 'templates', 'plans');
+  if (fs.existsSync(templatesDir)) {
+    // Copy plan.md template
+    const planTemplate = path.join(templatesDir, 'plan.md');
+    if (fs.existsSync(planTemplate)) {
+      fs.copySync(planTemplate, path.join(plansDir, 'plan-template.md'), { overwrite: force });
+      console.log(chalk.gray('   ✓ plan-template.md'));
+    }
+
+    // Copy phase.md template
+    const phaseTemplate = path.join(templatesDir, 'phase.md');
+    if (fs.existsSync(phaseTemplate)) {
+      fs.copySync(phaseTemplate, path.join(plansDir, 'phase-template.md'), { overwrite: force });
+      console.log(chalk.gray('   ✓ phase-template.md'));
+    }
+  }
+
+  // Create .gitkeep for reports
+  fs.writeFileSync(path.join(plansDir, 'reports', '.gitkeep'), '');
+  console.log(chalk.gray('   ✓ reports/'));
+}
+
 async function setupIDE(ide, targetDir, force) {
   switch (ide) {
     case 'claude':
@@ -105,6 +145,22 @@ async function setupClaudeCode(targetDir, force) {
   const claudeDir = path.join(targetDir, '.claude');
   fs.ensureDirSync(claudeDir);
 
+  // Copy skills directly to .claude/skills (for slash commands)
+  const skillsDir = path.join(claudeDir, 'skills');
+  const srcSkills = path.join(VIBEKIT_ROOT, 'skills');
+  if (fs.existsSync(srcSkills)) {
+    fs.copySync(srcSkills, skillsDir, { overwrite: force });
+    console.log(chalk.gray('   ✓ .claude/skills/'));
+  }
+
+  // Copy agents to .claude/agents
+  const agentsDir = path.join(claudeDir, 'agents');
+  const srcAgents = path.join(VIBEKIT_ROOT, 'agents');
+  if (fs.existsSync(srcAgents)) {
+    fs.copySync(srcAgents, agentsDir, { overwrite: force });
+    console.log(chalk.gray('   ✓ .claude/agents/'));
+  }
+
   // CLAUDE.md
   const claudeMd = path.join(targetDir, 'CLAUDE.md');
   if (!fs.existsSync(claudeMd) || force) {
@@ -116,13 +172,14 @@ This project uses VibeKit for AI assistance.
 See \`.vibekit/rules/\` for development rules.
 
 ## Skills
-See \`.vibekit/skills/\` for available skills.
+See \`.claude/skills/\` for available skills (all with \`vk:\` prefix).
 
 ## Workflows
-- \`/brainstorm\` - Design & brainstorm
-- \`/plan\` - Create implementation plan
-- \`/debug\` - Debug issues
-- \`/test\` - Run tests
+- \`/vk:brainstorm\` - Design & brainstorm
+- \`/vk:plan\` - Create implementation plan
+- \`/vk:debug\` - Debug issues
+- \`/vk:test\` - Run tests
+- \`/vk:cook\` - End-to-end implementation
 
 ## Project-Specific Rules
 <!-- Add your project-specific rules here -->
@@ -173,13 +230,20 @@ async function setupCursor(targetDir, force) {
   const cursorDir = path.join(targetDir, '.cursor');
   fs.ensureDirSync(cursorDir);
 
-  // rules symlink/folder reference
+  // Copy rules directly into .cursor/rules
   const rulesDir = path.join(cursorDir, 'rules');
-  if (!fs.existsSync(rulesDir) || force) {
-    fs.removeSync(rulesDir);
-    // Create symlink to .vibekit/rules
-    fs.symlinkSync(path.join(targetDir, '.vibekit/rules'), rulesDir, 'junction');
-    console.log(chalk.gray('   ✓ .cursor/rules → .vibekit/rules'));
+  const srcRules = path.join(VIBEKIT_ROOT, 'rules');
+  if (fs.existsSync(srcRules)) {
+    fs.copySync(srcRules, rulesDir, { overwrite: force });
+    console.log(chalk.gray('   ✓ .cursor/rules/'));
+  }
+
+  // Copy skills directly into .cursor/skills
+  const skillsDir = path.join(cursorDir, 'skills');
+  const srcSkills = path.join(VIBEKIT_ROOT, 'skills');
+  if (fs.existsSync(srcSkills)) {
+    fs.copySync(srcSkills, skillsDir, { overwrite: force });
+    console.log(chalk.gray('   ✓ .cursor/skills/'));
   }
 
   await addToGitignore(targetDir, ['.cursor/']);
@@ -191,6 +255,22 @@ async function setupCodex(targetDir, force) {
   const codexDir = path.join(targetDir, '.codex');
   fs.ensureDirSync(codexDir);
 
+  // Copy agents directly into .codex/agents
+  const agentsDir = path.join(codexDir, 'agents');
+  const srcAgents = path.join(VIBEKIT_ROOT, 'agents');
+  if (fs.existsSync(srcAgents)) {
+    fs.copySync(srcAgents, agentsDir, { overwrite: force });
+    console.log(chalk.gray('   ✓ .codex/agents/'));
+  }
+
+  // Copy skills directly into .codex/skills
+  const skillsDir = path.join(codexDir, 'skills');
+  const srcSkills = path.join(VIBEKIT_ROOT, 'skills');
+  if (fs.existsSync(srcSkills)) {
+    fs.copySync(srcSkills, skillsDir, { overwrite: force });
+    console.log(chalk.gray('   ✓ .codex/skills/'));
+  }
+
   // AGENTS.md
   const agentsMd = path.join(targetDir, 'AGENTS.md');
   if (!fs.existsSync(agentsMd) || force) {
@@ -199,7 +279,10 @@ async function setupCodex(targetDir, force) {
 This project uses VibeKit for AI assistance.
 
 ## Available Agents
-See \`.vibekit/agents/\` for agent definitions.
+See \`.codex/agents/\` for agent definitions.
+
+## Skills
+See \`.codex/skills/\` for available skills (all with \`vk:\` prefix).
 
 `);
     console.log(chalk.gray('   ✓ AGENTS.md'));
@@ -211,14 +294,35 @@ See \`.vibekit/agents/\` for agent definitions.
 async function setupOpenCode(targetDir, force) {
   console.log(chalk.blue('\n🔶 Setting up OpenCode'));
 
+  const opencodeDir = path.join(targetDir, '.opencode');
+  fs.ensureDirSync(opencodeDir);
+
+  // Copy rules directly into .opencode/rules
+  const rulesDir = path.join(opencodeDir, 'rules');
+  const srcRules = path.join(VIBEKIT_ROOT, 'rules');
+  if (fs.existsSync(srcRules)) {
+    fs.copySync(srcRules, rulesDir, { overwrite: force });
+    console.log(chalk.gray('   ✓ .opencode/rules/'));
+  }
+
+  // Copy skills directly into .opencode/skills
+  const skillsDir = path.join(opencodeDir, 'skills');
+  const srcSkills = path.join(VIBEKIT_ROOT, 'skills');
+  if (fs.existsSync(srcSkills)) {
+    fs.copySync(srcSkills, skillsDir, { overwrite: force });
+    console.log(chalk.gray('   ✓ .opencode/skills/'));
+  }
+
   // opencode.json
   const opencodeJson = path.join(targetDir, 'opencode.json');
   if (!fs.existsSync(opencodeJson) || force) {
     fs.writeJsonSync(opencodeJson, {
-      instructions: ['.vibekit/rules/*.md', 'CLAUDE.md']
+      instructions: ['.opencode/rules/*.md', 'CLAUDE.md']
     }, { spaces: 2 });
     console.log(chalk.gray('   ✓ opencode.json'));
   }
+
+  await addToGitignore(targetDir, ['.opencode/']);
 }
 
 async function addToGitignore(targetDir, entries) {