@hienlh/ppm 0.9.81 → 0.9.82

package/.opencode/commands/ckm-worktree.md

@@ -1,125 +0,0 @@
----
-description: "Create isolated git worktree for parallel development - Args: [feature-description] OR [project] [feature] (monorepo)"
----
-
-Create an isolated git worktree for parallel feature development.
-
-## Workflow
-
-### Step 1: Get Repository Info
-
-```bash
-node .opencode/scripts/worktree.cjs 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 .opencode/scripts/worktree.cjs create "<PROJECT>" "<SLUG>" --prefix <TYPE> --env "<FILES>"
-```
-
-**Standalone:**
-```bash
-node .opencode/scripts/worktree.cjs 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 .opencode/scripts/worktree.cjs 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 .opencode/scripts/worktree.cjs create "login-validation-bug" --prefix fix --env ".env.example"]
-
-Output: Worktree created at ../worktrees/myrepo-login-validation-bug
-        Branch: fix/login-validation-bug
-```

package/.opencode/commands/ckm-write-audit.md

@@ -1,97 +0,0 @@
----
-description: "Audit content quality against copywriting, SEO, and platform standards - Args: <file-path>"
----
-
-Audit content quality and provide actionable scores.
-
-<file_path>$ARGUMENTS</file_path>
-
-## Scoring Dimensions (0-10 each)
-
-### 1. Copywriting (40%)
-- **Hook/Headline**: First line stops scroll? 4U formula (Useful, Unique, Urgent, Ultra-specific)?
-- **Structure**: Clear hierarchy? AIDA/PAS flow?
-- **CTA**: Clear action? First-person ("Get MY...")?
-- **Specificity**: Numbers, data, concrete claims vs vague?
-- **Readability**: Grade 6 level? Short sentences? Active voice?
-
-### 2. SEO (30%) - for articles/blogs only
-- **Keywords**: Primary keyword in title, H1, first 100 words?
-- **Structure**: H2/H3 hierarchy? Internal links?
-- **Meta**: Title <60 chars? Description <160 chars?
-- **Length**: 1500+ words for comprehensive topics?
-
-### 3. Platform Compliance (20%)
-| Platform | Char Limit | Hashtags | Media |
-|----------|------------|----------|-------|
-| Twitter/X | 280 | 1-2 | Required |
-| LinkedIn | 3000 | 3-5 | Optional |
-| Instagram | 2200 | 20-30 | Required |
-| TikTok | 2200 | 3-5 | Required |
-
-### 4. Brand Voice (10%)
-- Tone consistency with brand guidelines?
-- Terminology alignment?
-
-## Workflow
-
-1. **Read File**
-   - Load content from `<file_path>`
-   - Detect content type (social, article, infographic, email)
-
-2. **Apply Relevant Criteria**
-   - Social posts → Copywriting + Platform
-   - Articles → Copywriting + SEO
-   - Emails → Copywriting + CTA focus
-   - Infographics → Visual hierarchy + Data accuracy
-
-3. **Score Each Dimension**
-   - 0-3: Poor (needs rewrite)
-   - 4-6: Acceptable (needs improvement)
-   - 7-8: Good (minor tweaks)
-   - 9-10: Excellent (ready to publish)
-
-4. **Generate Report**
-
-## Output Format
-
-```markdown
-# Content Audit: {filename}
-
-**Overall Score: X/10** | **Status: [Publish Ready / Needs Work / Rewrite]**
-
-## Scores
-
-| Dimension | Score | Weight | Weighted |
-|-----------|-------|--------|----------|
-| Copywriting | X/10 | 40% | X.X |
-| SEO | X/10 | 30% | X.X |
-| Platform | X/10 | 20% | X.X |
-| Brand Voice | X/10 | 10% | X.X |
-| **Total** | | | **X.X/10** |
-
-## Findings
-
-### ✅ Strengths
-- ...
-
-### ⚠️ Issues
-- ...
-
-### 🔧 Recommendations
-1. ...
-2. ...
-3. ...
-```
-
-## Skills Used
-- `copywriting` - formulas, headline templates
-- `seo-optimization` - keyword, structure checks
-- `social-media` - platform specs
-- `brand-guidelines` - voice consistency
-
-## Examples
-```
-/write/audit assets/posts/251225-never-gonna-give-you-up-all-platforms.md
-/write/audit assets/articles/251225-rickroll-phenomenon.md
-```

package/.opencode/commands/ckm-write-blog-youtube.md

@@ -1,158 +0,0 @@
----
-description: "💡💡 Generate SEO-optimized blog article from YouTube video - Args: ['youtube-url']"
----
-
-Generate a well-researched, SEO-friendly blog article from a YouTube video URL.
-
-<youtube_url>$ARGUMENTS</youtube_url>
-
-## Mission
-
-Transform YouTube video content into a comprehensive blog article with citations, multiple perspectives, visual elements, and SEO optimization.
-
-## Workflow
-
-### 1. Writing Style Selection
-- Scan `assets/writing-styles/` for available styles
-- If multiple styles exist: use `AskUserQuestion` to let user select
-- If only `default.md` exists: use it automatically
-- Load selected style guidelines for content creation
-
-### 2. Video Content Extraction
-- Activate `youtube-handling` skill
-- Extract from YouTube URL:
-  - Video metadata (title, description, channel)
-  - Full transcript/captions
-  - AI-generated summary with key points
-  - Screenshots at key moments (for illustrations)
-
-```bash
-# Get video info & summary
-python .opencode/skills/youtube-handling/scripts/vidcap.py info "$URL"
-python .opencode/skills/youtube-handling/scripts/vidcap.py summary "$URL" --screenshot
-python .opencode/skills/youtube-handling/scripts/vidcap.py caption "$URL" --locale en --ext vtt
-```
-
-If screenshots are not available, activate `ai-multimodal` skill to generate relevant visuals for the specific content sections.
-
-### 3. Research & Enrichment
-- Use multiple `researcher` agents in parallel to:
-  - Find supporting sources and citations for claims
-  - Gather different perspectives on the topic
-  - Identify related statistics and data
-  - Find expert opinions and counterarguments
-- Compile research findings for article enrichment
-
-### 4. SEO Optimization
-- Activate `seo-optimization` skill
-- Use `seo-specialist` agent for:
-  - Primary/secondary keyword identification
-  - Search intent analysis
-  - Meta description optimization
-  - Heading structure (H2-H4)
-  - Internal linking opportunities
-
-### 5. Visual Content Creation
-- Activate `ai-multimodal` skill
-- Generate visuals using Imagen 4:
-  - Hero/featured image
-  - Section illustrations or infographics
-  - Quote cards for key takeaways
-- Use video screenshots as supplementary visuals
-
-### 6. Content Creation
-- Use `content-creator` agent for main article body
-- Use `copywriter` agent for:
-  - Engaging introduction hook
-  - Compelling conclusion with CTA
-  - Pull quotes and highlights
-- Apply selected writing style throughout
-- Integrate citations naturally with proper attribution
-
-### 7. Quality Review
-- Use `content-reviewer` agent for:
-  - Brand voice consistency
-  - SEO checklist verification
-  - Fact-checking citations
-  - Readability optimization
-
-## Agents Used
-
-| Agent | Purpose |
-|-------|---------|
-| `researcher` | Find citations, perspectives, supporting data |
-| `seo-specialist` | Keyword research, SEO optimization |
-| `content-creator` | Main article body writing |
-| `copywriter` | Hooks, conclusions, highlights |
-| `content-reviewer` | Quality assurance |
-
-## Skills Used
-
-| Skill | Purpose |
-|-------|---------|
-| `youtube-handling` | Extract video content |
-| `seo-optimization` | SEO best practices |
-| `ai-multimodal` | Generate images/infographics |
-| `content-marketing` | Content frameworks |
-
-## Output Format
-
-```yaml
----
-title: "SEO-Optimized Article Title"
-slug: keyword-optimized-slug
-description: "Meta description under 160 chars"
-keywords: [primary, secondary, long-tail]
-source_video: "YouTube URL"
-featured_image: "path/to/generated-hero.png"
-schema: Article
----
-
-# Article Title
-
-[Hook/Introduction - 2-3 paragraphs]
-
-## Section Heading (H2)
-[Content with citations]
-> Key quote from video
-
-![Illustration](path/to/image.png)
-
-## Another Section
-[Research-enriched content]
-
-### Subsection (H3)
-[Supporting details]
-
-## Key Takeaways
-- Bullet point summary
-- With actionable insights
-
-## Conclusion
-[CTA and wrap-up]
-
----
-**Sources:**
-- [Citation 1](url)
-- [Citation 2](url)
-- Original video: [Title](youtube-url)
-```
-
-## Output Location
-
-- Article: `content/blog/{date}-{slug}.md`
-- Images: `content/blog/images/{date}-{slug}/`
-
-## Examples
-
-```
-/write:blog:youtube "https://youtube.com/watch?v=abc123"
-/write:blog:youtube "https://youtu.be/xyz789"
-```
-
-## Token Efficiency
-
-- Extract video content once, reuse across agents
-- Run researcher agents in parallel
-- Generate images only after content is finalized
-- Use progressive disclosure for long transcripts

package/.opencode/commands/ckm-write-blog.md

@@ -1,85 +0,0 @@
----
-description: "💡💡 Create SEO-optimized blog content - Args: ['topic']"
----
-
-Create SEO-optimized blog content with keyword targeting and meta optimization.
-
-<topic>$ARGUMENTS</topic>
-
-## Workflow
-
-1. **SEO Research**
-   - Use `seo-specialist` agent for keyword research on topic
-   - Activate `seo-optimization` skill
-   - Identify:
-     - Primary keyword
-     - Secondary keywords
-     - Related long-tail keywords
-     - Search intent
-
-2. **Content Planning**
-   - Use `planner` agent for outline structure
-   - Activate `content-marketing` skill
-   - Generate:
-     - SEO-optimized title (H1)
-     - Meta description
-     - Heading structure (H2-H4)
-     - Internal linking opportunities
-
-3. **Content Creation**
-   - Use `content-creator` agent for blog content
-   - Use `copywriter` agent for engaging intro/conclusion
-   - Integrate keywords naturally
-   - Add CTA sections
-
-4. **SEO Optimization**
-   - Use `seo-specialist` for final review
-   - Generate schema markup (Article/BlogPosting)
-   - Image alt text suggestions
-   - URL slug recommendation
-
-5. **Output**
-   - Blog post → `assets/articles/{date}-{slug}/{date}-{slug}.md`
-   - Blog images → `assets/articles/{date}-{slug}/images/`
-   - SEO metadata in frontmatter
-
-## Agents Used
-- `seo-specialist` - Keyword research and optimization
-- `content-creator` - Blog content writing
-- `copywriter` - Engaging copy
-- `planner` - Content structure
-
-## Skills Used
-- `seo-optimization` - SEO best practices
-- `content-marketing` - Content frameworks
-- `creativity` - Visual style suggestions for blog imagery and graphics
-- `assets-organizing` - Standardized output paths
-
-## Output
-- Blog post → `assets/articles/{date}-{slug}/{date}-{slug}.md`
-- Blog images → `assets/articles/{date}-{slug}/images/`
-
-## Output Format
-```yaml
----
-title: "SEO Optimized Title"
-slug: keyword-slug
-description: "Meta description under 160 chars"
-keywords: [primary, secondary, related]
-schema: Article
----
-```
-
-## Quality Gate (Auto-Triggered)
-
-**After generating content, MUST run:**
-1. `/write/audit` → Score content (target: ≥8.0)
-2. `/write/publish` → Auto-fix if score <8.0
-3. Present final version with score
-
-## Examples
-```
-/write/blog "best project management tools for startups"
-/write/blog "AI marketing automation guide"
-/write/blog "remote team productivity tips"
-```

package/.opencode/commands/ckm-write-cro.md

@@ -1,42 +0,0 @@
----
-description: "Analyze the current content and optimize for conversion - Args: ['issues']"
----
-
-You are an expert in conversion optimization. Analyze the content based on reported issues:
-<issues>$ARGUMENTS</issues>
-
-## Conversion Optimization Framework
-
-1. Headline 4-U Formula: Useful, Unique, Urgent, Ultra-specific (80% won't read past this)
-2. Above-Fold Value Proposition: Customer problem focus, no company story, zero scroll required
-3. CTA First-Person Psychology: "Get MY Guide" vs "Get YOUR Guide" (90% more clicks)
-4. 5-Field Form Maximum: Every field kills conversions, progressive profiling for the rest
-5. Message Match Precision: Ad copy, landing page headline, broken promises = bounce
-6. Social Proof Near CTAs: Testimonials with faces/names, results, placed at decision points
-7. Cognitive Bias Stack: Loss aversion (fear), social proof (FOMO), anchoring (pricing)
-8. PAS Copy Framework: Problem > Agitate > Solve, emotion before logic
-9. Genuine Urgency Only: Real deadlines, actual limits, fake timers destroy trust forever
-10. Price Anchoring Display: Show expensive option first, make real price feel like relief
-11. Trust Signal Clustering: Security badges, guarantees, policies all visible together
-12. Visual Hierarchy F-Pattern: Eyes scan F-shape, put conversions in the path
-13. Lead Magnet Hierarchy: Templates > Checklists > Guides (instant > delayed gratification)
-14. Objection Preemption: Address top 3 concerns before they think them, FAQ near CTA
-15. Mobile Thumb Zone: CTAs where thumbs naturally rest, not stretching required
-16. One-Variable Testing: Change one thing, measure impact, compound wins over time
-17. Post-Conversion Momentum: Thank you page sells next step while excitement peaks
-18. Cart Recovery Sequence: Email in 1 hour, retarget in 4 hours, incentive at 24 hours
-19. Reading Level Grade 6: Smart people prefer simple, 11-word sentences, short paragraphs
-20. TOFU/MOFU/BOFU Logic: Awareness content ≠ decision content, match intent precisely
-21. White Space = Focus: Empty space makes CTAs impossible to miss, crowded = confused
-22. Benefit-First Language: Features tell, benefits sell, transformations compel
-23. Micro-Commitment Ladder: Small yes leads to big yes, start with email only
-24. Performance Tracking Stack: Heatmaps show problems, recordings show why, events show what
-25. Weekly Optimization Ritual: Review metrics Monday, test Tuesday, iterate or scale
-
-## Workflow
-
-- If the user provides screenshots, use `ai-multimodal` skill to analyze and describe conversion optimization issues in detail.
-- If the user provides videos, use `ai-multimodal` (`video-analysis`) skill to analyze video content and identify conversion bottlenecks.
-- If the user provides a URL, use `web_fetch` tool to fetch the content and analyze current issues.
-- Use `/scout:ext` (preferred) or `/scout` (fallback) slash command to search the codebase for files needed to complete the task
-- Use `copywriter` agent to write the enhanced copy into the code files, then report back to main agent.

package/.opencode/commands/ckm-write-enhance.md

@@ -1,13 +0,0 @@
----
-description: "Analyze the current copy issues and enhance it - Args: ['issues']"
----
-
-Enhance the copy based on reported issues:
-<issues>$ARGUMENTS</issues>
-
-## Workflow
-
-- If the user provides screenshots, use `ai-multimodal` skill to analyze and describe the issues in detail, ensuring the copywriter understands the context.
-- If the user provides videos, use `ai-multimodal` (`video-analysis`) skill to analyze video content and extract relevant copy issues.
-- Use `/scout:ext` (preferred) or `/scout` (fallback) slash command to search the codebase for files needed to complete the task
-- Use `copywriter` agent to write the enhanced copy into the code files, then report back to main agent.

package/.opencode/commands/ckm-write-fast.md

@@ -1,12 +0,0 @@
----
-description: "Write creative & smart copy [FAST]"
----
-
-Write creative & smart copy for this user request:
-<user_request>$ARGUMENTS</user_request>
-
-## Workflow
-
-- If the user provides screenshots, use `ai-multimodal` skill to analyze and describe the context.
-- If the user provides videos, use `ai-multimodal` (`video-analysis`) skill to analyze video content.
-- Use `copywriter` agent to write the copy, then report back to main agent.

package/.opencode/commands/ckm-write-formula.md

@@ -1,116 +0,0 @@
----
-description: "Generate copy using proven copywriting formulas (AIDA, PAS, BAB, etc.) - Args: <formula> \"<topic>\""
----
-
-# Copy Formula Generator
-
-Generate persuasive copy using proven copywriting frameworks with brand context.
-
-<formula>$ARGUMENTS</formula>
-
-## Available Formulas
-
-| Formula | Best For |
-|---------|----------|
-| **AIDA** | Landing pages, ads, sales emails |
-| **PAS** | Email, sales pages, problem-focused |
-| **BAB** | Testimonials, case studies, transformations |
-| **4Ps** | Sales letters, long-form |
-| **ACCA** | Awareness campaigns |
-| **FAB** | Product descriptions, features |
-
-## Workflow
-
-### Step 1: Parse Arguments
-
-Extract formula and topic from input:
-- If only topic provided, default to AIDA
-- Supported: AIDA, PAS, BAB, 4Ps, ACCA, FAB
-
-### Step 2: Inject Brand Context
-
-```bash
-node .opencode/skills/brand-guidelines/scripts/inject-brand-context.cjs --json
-```
-
-Use brand voice, prohibited words, and tone.
-
-### Step 3: Load Formula Reference
-
-Activate `copywriting` skill and read:
-- `.opencode/skills/copywriting/references/copy-formulas.md`
-- `.opencode/skills/copywriting/references/power-words.md`
-
-### Step 4: Generate Copy
-
-Apply the formula structure to the topic:
-
-**AIDA Structure:**
-```
-ATTENTION: Bold hook using brand voice
-INTEREST: Why this matters (pain/gain)
-DESIRE: Transformation picture
-ACTION: CTA with brand tone
-```
-
-**PAS Structure:**
-```
-PROBLEM: Specific pain point
-AGITATE: Consequences, frustration
-SOLUTION: Your offer as the answer
-```
-
-**BAB Structure:**
-```
-BEFORE: Current painful state
-AFTER: Desired transformed state
-BRIDGE: How your solution gets them there
-```
-
-### Step 5: Output Variants
-
-Generate 3 variants:
-1. **Short** - Social/ad length (~50 words)
-2. **Medium** - Email/landing section (~150 words)
-3. **Long** - Full sales copy (~300 words)
-
-### Step 6: Save Output
-
-Save to: `assets/copy/{date}-{formula}-{slug}.md`
-
-## Examples
-
-```bash
-/copy:formula AIDA "SaaS product launch"
-/copy:formula PAS "email deliverability problems"
-/copy:formula BAB "fitness transformation program"
-/copy:formula "marketing automation tool"  # defaults to AIDA
-```
-
-## Output Format
-
-```markdown
-# {Topic} - {Formula} Copy
-
-## Brand Context
-- Voice: {extracted voice}
-- Tone: {extracted tone}
-
-## Short Version (Social/Ad)
-{50-word copy}
-
-## Medium Version (Email/Landing)
-{150-word copy}
-
-## Long Version (Sales Page)
-{300-word copy}
-
----
-Generated: {date}
-Formula: {formula}
-```
-
-## Skills Used
-
-- `copywriting` - Formulas, power words, templates
-- `brand-guidelines` - Voice, tone, prohibited words

package/.opencode/commands/ckm-write-good.md

@@ -1,16 +0,0 @@
----
-description: "Write good creative & smart copy [GOOD]"
----
-
-Write good creative & smart copy for this user request:
-<user_request>$ARGUMENTS</user_request>
-
-## Workflow
-
-- If the user provides screenshots, use `ai-multimodal` skill to analyze and describe the context in detail.
-- If the user provides videos, use `ai-multimodal` (`video-analysis`) skill to analyze video content.
-- Activate `creativity` skill for creative direction - style selection, color psychology, tone guidance.
-- Use multiple `researcher` agents in parallel to search for relevant information, then report back to main agent.
-- Use `/scout:ext` (preferred) or `/scout` (fallback) slash command to search the codebase for files needed to complete the task
-- Use `planner` agent to plan the copy, make sure it can satisfy the user request.
-- Use `copywriter` agent to write the copy based on the plan, then report back to main agent.