@hienlh/ppm 0.9.81 → 0.9.83

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

@@ -1,125 +0,0 @@
----
-description: "💡💡 Technical SEO audit - Args: ['url']"
----
-
-Perform a comprehensive technical SEO audit.
-
-<url>$ARGUMENTS</url>
-
-Activate `seo-optimization` skill.
-
-## Workflow
-
-1. **Fetch Page Data**
-   - Use `WebFetch` tool to retrieve page content
-   - If local file, use `Read` tool
-
-2. **ReviewWeb API Analysis** (if `$REVIEWWEB_API_KEY` available)
-   - Reference: `.opencode/skills/seo-optimization/references/reviewweb-api.md`
-   - **Backlink Analysis**: `POST /seo-insights/backlinks` with domain
-   - **Traffic Insights**: `POST /seo-insights/traffic` for traffic history, top pages, keywords
-   - **Page Review**: `POST /review` then `GET /review/{reviewId}` for detailed analysis
-   - **Visual Audit**: `POST /screenshot` for desktop/mobile rendering check
-
-3. **Technical Analysis**
-   - Use `seo-specialist` agent for audit
-   - Activate `seo-optimization` skill
-   - Check all SEO elements:
-     - Title tag (length, keywords)
-     - Meta description
-     - Heading structure (H1-H6)
-     - URL structure
-     - Internal/external links
-     - Image alt tags
-     - Schema markup
-     - Mobile responsiveness
-     - Page speed indicators
-
-4. **Generate Report**
-   - Merge WebFetch + ReviewWeb API findings
-   - Score each element
-   - Prioritize issues (critical/high/medium/low)
-   - Provide specific recommendations
-   - Output to `reports/seo/`
-
-## Agents Used
-- `seo-specialist` - Technical SEO expertise
-
-## Skills Used
-- `seo-optimization` - Audit frameworks + ReviewWeb API reference
-- `assets-organizing` - Standardized output paths
-
-## API Reference
-- ReviewWeb API: `.opencode/skills/seo-optimization/references/reviewweb-api.md`
-- Required env: `$REVIEWWEB_API_KEY` (optional but recommended)
-
-## Output
-- Path: `assets/seo/audits/{date}-{domain}-audit.md`
-
-### Output Requirements
-- Overall score (0-100) with letter grade
-- Executive summary (2-3 sentences)
-- Each element scored with status emoji: ✅ Pass | ⚠️ Warning | ❌ Fail
-- Issues grouped by priority (Critical → High → Medium → Low)
-- Actionable recommendations with effort estimates (Quick Win / Medium / Major)
-- Include ReviewWeb API data if available (backlinks, traffic, keywords)
-
-### Output Template
-```markdown
-# SEO Audit: {domain}
-**Date:** {date} | **Score:** {score}/100 ({grade})
-
-## Executive Summary
-{2-3 sentence overview of site health and top priorities}
-
-## Quick Stats
-| Metric | Value | Status |
-|--------|-------|--------|
-| Backlinks | {count} | {emoji} |
-| Monthly Traffic | {estimate} | {emoji} |
-| Top Keywords | {count} ranking | {emoji} |
-
-## Technical SEO Checklist
-| Element | Status | Details |
-|---------|--------|---------|
-| Title Tag | {emoji} | {length}/60 chars, {keyword status} |
-| Meta Description | {emoji} | {length}/160 chars |
-| H1 Tag | {emoji} | {count} found |
-| Heading Hierarchy | {emoji} | {structure} |
-| URL Structure | {emoji} | {notes} |
-| Image Alt Tags | {emoji} | {x}/{total} optimized |
-| Schema Markup | {emoji} | {types found or missing} |
-| Mobile Friendly | {emoji} | {notes} |
-| Page Speed | {emoji} | {indicators} |
-| Internal Links | {emoji} | {count} |
-| External Links | {emoji} | {count} |
-
-## Issues by Priority
-
-### 🔴 Critical
-{list or "None found"}
-
-### 🟠 High
-{list or "None found"}
-
-### 🟡 Medium
-{list or "None found"}
-
-### 🟢 Low
-{list or "None found"}
-
-## Recommendations
-| # | Action | Priority | Effort | Impact |
-|---|--------|----------|--------|--------|
-| 1 | {recommendation} | {priority} | {effort} | {impact} |
-
-## Data Sources
-- WebFetch analysis: {yes/no}
-- ReviewWeb API: {yes/no, endpoints used}
-```
-
-## Examples
-```
-/seo/audit https://example.com
-/seo/audit https://example.com/pricing
-```

package/.opencode/commands/ckm-seo-keywords.md

@@ -1,135 +0,0 @@
----
-description: "💡💡 Keyword research & planning - Args: ['topic']"
----
-
-Conduct keyword research for a topic or niche.
-
-<topic>$ARGUMENTS</topic>
-
-## Workflow
-
-1. **Understand Intent**
-   - Parse topic from `$ARGUMENTS`
-   - Determine search intent (informational/transactional/navigational)
-
-2. **Research Keywords via ReviewWeb API**
-   - **Keyword Ideas**: `POST /seo-insights/keyword-ideas` with topic
-   - **Keyword Difficulty**: `POST /seo-insights/keyword-difficulty` for top keywords
-   - Use `attraction-specialist` agent for expanded discovery
-   - Use `WebSearch` for competitive analysis
-   - Activate `seo-optimization` skill for keyword clustering
-
-3. **Analysis**
-   - Primary keywords (high volume, relevant)
-   - Long-tail variations
-   - Question-based keywords
-   - Related topics
-   - Competitor keywords
-   - Difficulty scores from API
-
-4. **Output Strategy**
-   - Keyword clusters by intent
-   - Content recommendations
-   - Priority ranking
-   - Output to `assets/seo/keywords/`
-
-## API Reference
-
-Uses ReviewWeb SEO Insights API:
-- Skill: `seo-optimization/references/reviewweb-api.md`
-- Endpoints: `/seo-insights/keyword-ideas`, `/seo-insights/keyword-difficulty`
-- Auth: `$REVIEWWEB_API_KEY` via X-API-Key header
-
-## Agents Used
-- `attraction-specialist` - Keyword discovery
-- `seo-specialist` - Keyword analysis
-
-## Skills Used
-- `seo-optimization` - Keyword research frameworks, ReviewWeb API
-- `assets-organizing` - Standardized output paths
-
-## Output Requirements
-
-1. **Minimum 20 keywords** across all clusters
-2. **Difficulty scores** for top 10 primary keywords (via API)
-3. **Intent classification** for each keyword cluster
-4. **Priority ranking** (High/Medium/Low) based on:
-   - Search volume potential
-   - Difficulty score (lower = higher priority)
-   - Relevance to topic
-5. **Content recommendations** per cluster
-
-## Output Template
-
-```markdown
-# Keyword Research: {topic}
-
-**Date**: {YYYY-MM-DD}
-**Topic**: {topic}
-**Search Intent**: {primary intent}
-
-## Executive Summary
-
-{2-3 sentence overview of findings}
-
-## Primary Keywords
-
-| Keyword | Difficulty | Volume Est. | Intent | Priority |
-|---------|------------|-------------|--------|----------|
-| {kw}    | {0-100}    | {High/Med/Low} | {I/T/N} | {H/M/L} |
-
-## Keyword Clusters
-
-### Cluster 1: {Theme}
-**Intent**: {Informational/Transactional/Navigational}
-**Priority**: {High/Medium/Low}
-
-- {keyword 1}
-- {keyword 2}
-- {keyword 3}
-
-**Content Recommendation**: {suggested content type/angle}
-
-### Cluster 2: {Theme}
-...
-
-## Long-tail Keywords
-
-| Long-tail Keyword | Parent Keyword | Intent |
-|-------------------|----------------|--------|
-| {long-tail kw}    | {parent}       | {I/T/N} |
-
-## Question Keywords
-
-- {question keyword 1}
-- {question keyword 2}
-
-## Competitor Keywords
-
-| Competitor | Key Terms | Gap Opportunity |
-|------------|-----------|-----------------|
-| {domain}   | {terms}   | {opportunity}   |
-
-## Recommendations
-
-1. **Quick Wins**: {low difficulty, high relevance keywords}
-2. **Strategic Targets**: {medium difficulty, high value}
-3. **Long-term Goals**: {high difficulty, brand-building}
-
-## Next Steps
-
-- [ ] Create content calendar for top clusters
-- [ ] Prioritize quick-win keywords
-- [ ] Monitor competitor movements
-```
-
-## Output Path
-
-`assets/seo/keywords/{date}-{topic-slug}-keywords.md`
-
-## Examples
-```
-/seo:keywords "AI writing tools"
-/seo:keywords "project management software"
-/seo:keywords "sustainable fashion"
-```

package/.opencode/commands/ckm-seo-pseo.md

@@ -1,66 +0,0 @@
----
-description: "💡💡 Programmatic SEO template generation - Args: ['template-type']"
----
-
-Generate programmatic SEO templates for scalable content.
-
-<template_type>$ARGUMENTS</template_type>
-
-## Template Types
-- `location` - Location-based pages (e.g., "best {service} in {city}")
-- `comparison` - Comparison pages (e.g., "{product} vs {competitor}")
-- `review` - Review pages (e.g., "{product} review")
-- `howto` - How-to guides (e.g., "how to {action} with {tool}")
-- `list` - List posts (e.g., "top 10 {category} tools")
-
-## Workflow
-
-1. **Template Selection**
-   - Parse template type from `$ARGUMENTS`
-   - If not specified, ask user via `AskUserQuestion`
-
-2. **Data Structure Design**
-   - Use `seo-specialist` agent for template architecture
-   - Define data source schema (CSV, JSON, API)
-   - Identify variable placeholders
-
-3. **Template Creation**
-   - Use `content-creator` agent for content blocks
-   - Activate `content-marketing` skill
-   - Generate:
-     - Page template with variables
-     - Meta tag templates
-     - Schema markup template
-     - Internal linking strategy
-
-4. **SEO Optimization**
-   - Apply `seo-optimization` skill
-   - Keyword insertion points
-   - Unique content ratios
-   - Prevent duplicate content
-
-5. **Sample Generation**
-   - Generate 3 sample pages
-   - Validate SEO compliance
-   - Output to `assets/attraction/pseo-templates/`
-
-## Agents Used
-- `seo-specialist` - pSEO architecture
-- `content-creator` - Content templates
-
-## Skills Used
-- `seo-optimization` - SEO best practices
-- `content-marketing` - Content strategy
-- `assets-organizing` - Standardized output paths
-
-## Output
-- Templates → `assets/attraction/pseo-templates/{template-name}.md`
-- Data schema → `assets/attraction/pseo-templates/{template-name}-schema.json`
-- Samples → `assets/attraction/pseo-templates/{template-name}-samples/`
-
-## Examples
-```
-/seo/pseo location
-/seo/pseo comparison
-/seo/pseo "best {tool} for {usecase}"
-```

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

@@ -1,67 +0,0 @@
----
-description: "💡💡 SEO audit and optimization - Args: ['action] [target']"
----
-
-SEO audit and optimization for websites and content.
-
-<args>$ARGUMENTS</args>
-
-## Actions
-- `audit [url]` - Technical SEO audit
-- `keywords [topic]` - Keyword research
-- `optimize [content]` - Content optimization
-- `schema [page]` - Generate JSON+LD schema
-
-## Workflow
-
-1. **Parse Arguments**
-   - Extract action (audit/keywords/optimize/schema)
-   - Extract target (url/topic/content/page)
-
-2. **Audit Workflow** (for `audit`)
-   - Use `seo-specialist` agent for technical analysis
-   - Activate `seo-optimization` skill
-   - Check: meta tags, structure, performance, mobile
-   - Generate audit report
-
-3. **Keywords Workflow** (for `keywords`)
-   - Use `attraction-specialist` agent for keyword research
-   - Analyze search intent and volume
-   - Identify opportunities and gaps
-   - Output keyword strategy
-
-4. **Optimize Workflow** (for `optimize`)
-   - Use `seo-specialist` agent for content analysis
-   - Check keyword density, structure, readability
-   - Generate optimization recommendations
-   - Apply changes if confirmed
-
-5. **Schema Workflow** (for `schema`)
-   - Analyze page content type
-   - Generate appropriate JSON+LD schema
-   - Validate schema structure
-   - Output ready-to-use markup
-
-## Agents Used
-- `seo-specialist` - SEO audit and optimization
-- `attraction-specialist` - Keyword research
-
-## Skills Used
-- `seo-optimization` - SEO frameworks and templates
-- `assets-organizing` - Standardized output paths
-
-## MCP Integrations
-- Search Console - Rankings and impressions
-
-## Output
-- Audit reports → `assets/seo/audits/{date}-{domain}-audit.md`
-- Keyword reports → `assets/seo/keywords/{date}-{topic}-keywords.md`
-- Schema files → `assets/seo/schemas/{page}-schema.json`
-
-## Examples
-```
-/seo:audit https://example.com
-/seo:keywords "project management software"
-/seo:optimize https://example.com/blog/post-title
-/seo:schema
-```

package/.opencode/commands/ckm-skill-add.md

@@ -1,41 +0,0 @@
----
-description: "Add new reference files or scripts to a skill - Args: ['skill-name] [reference-or-script-prompt']"
----
-
-Think harder.
-Use `skill-creator` and `claude-code` skills.
-Use `docs-seeker` skills to search for documentation if needed.
-
-## Arguments
-$1: skill name (required, default: "")
-$2: reference or script prompt (required, default: "")
-If $1 or $2 is not provided, ask the user to provide it.
-
-## Your mission
-Add new reference files or scripts to a skill at `.opencode/skills/$1` directory.
-
-## Requirements
-<reference-or-script-prompt>
-$2
-</reference-or-script-prompt>
-
-## Rules of Skill Creation:
-Base on the requirements:
-- Always keep in mind that `SKILL.md` and reference files should be token consumption efficient, so that **progressive disclosure** can be leveraged at best.
-- `SKILL.md` is always short and concise, straight to the point, treat it as a quick reference guide.
-- If you're given nothing, use `AskUserQuestion` tool for clarifications and `researcher` subagent to research about the topic.
-- If you're given an URL, it's documentation page, use `Explore` subagent to explore every internal link and report back to main agent, don't skip any link.
-- If you receive a lot of URLs, use multiple `Explore` subagents to explore them in parallel, then report back to main agent.
-- If you receive a lot of files, use multiple `Explore` subagents to explore them in parallel, then report back to main agent.
-- If you're given a Github URL, use [`repomix`](https://repomix.com/guide/usage) command to summarize ([install it](https://repomix.com/guide/installation) if needed) and spawn multiple `Explore` subagents to explore it in parallel, then report back to main agent.
-
-### Scopes
-- Project-scope: Current working project directory (e.g. `.opencode/`)
-- User-scope: Home/user directory (e.g. `~/.opencode/`)
-
-**IMPORTANT:**
-- ALWAYS make changes to skills in the project-scope directory (UNLESS you're allowed to).
-- DO NOT make any changes to skills in the user-scope directory (UNLESS you're allowed to).
-- Skills are not documentation, they are practical instructions for Claude Code to use the tools, packages, plugins or APIs to achieve the tasks.
-- Each skill teaches Claude how to perform a specific development task, not what a tool does.
-- Claude Code can activate multiple skills automatically to achieve the user's request.

package/.opencode/commands/ckm-skill-create.md

@@ -1,34 +0,0 @@
----
-description: "Create a new agent skill - Args: ['prompt-or-llms-or-github-url']"
----
-
-Ultrathink.
-Use `skill-creator` and `claude-code` skills.
-Use `docs-seeker` skills to search for documentation if needed.
-
-## Your mission
-Create a new skill in `.opencode/skills/` directory.
-
-## Requirements
-<user-prompt>$ARGUMENTS</user-prompt>
-
-## Rules of Skill Creation:
-Base on the requirements:
-- Always keep in mind that `SKILL.md` and reference files should be token consumption efficient, so that **progressive disclosure** can be leveraged at best.
-- `SKILL.md` is always short and concise, straight to the point, treat it as a quick reference guide.
-- If you're given nothing, use `AskUserQuestion` tool for clarifications and `researcher` subagent to research about the topic.
-- If you're given an URL, it's documentation page, use `Explore` subagent to explore every internal link and report back to main agent, don't skip any link.
-- If you receive a lot of URLs, use multiple `Explore` subagents to explore them in parallel, then report back to main agent.
-- If you receive a lot of files, use multiple `Explore` subagents to explore them in parallel, then report back to main agent.
-- If you're given a Github URL, use [`repomix`](https://repomix.com/guide/usage) command to summarize ([install it](https://repomix.com/guide/installation) if needed) and spawn multiple `Explore` subagents to explore it in parallel, then report back to main agent.
-
-### Scopes
-- Project-scope: Current working project directory (e.g. `.opencode/`)
-- User-scope: Home/user directory (e.g. `~/.opencode/`)
-
-**IMPORTANT:**
-- ALWAYS make changes to skills in the project-scope `.opencode/skills/` directory (UNLESS you're allowed to).
-- DO NOT make any changes to skills in the home/user-scope `~/.opencode/skills/` directory (UNLESS you're allowed to).
-- Skills are not documentation, they are practical instructions for Claude Code to use the tools, packages, plugins or APIs to achieve the tasks.
-- Each skill teaches Claude how to perform a specific development task, not what a tool does.
-- Claude Code can activate multiple skills automatically to achieve the user's request.

package/.opencode/commands/ckm-skill-fix-logs.md

@@ -1,28 +0,0 @@
----
-description: "Fix the agent skill based on `logs.txt` file. - Args: ['prompt-or-path-to-skill']"
----
-
-Think harder.
-Use `skill-creator` and `claude-code` skills.
-Use `docs-seeker` skills to search for documentation if needed.
-
-## Your mission
-Fix the agent skill based on the current `logs.txt` file (in the project root directory).
-
-## Requirements
-<user-prompt>$ARGUMENTS</user-prompt>
-
-## Rules of Skill Fixing:
-Base on the requirements:
-**IMPORTANT:**
-- ALWAYS make changes to skills in the project-scope `.opencode/skills/` directory (UNLESS you're allowed to).
-- DO NOT make any changes to skills in the home/user-scope `~/.opencode/skills/` directory (UNLESS you're allowed to).
-- If you're given nothing, use `AskUserQuestion` tool for clarifications and `researcher` subagent to research about the topic.
-- If you're given an URL, it's documentation page, use `Explorer` subagent to explore every internal link and report back to main agent, don't skip any link.
-- If you receive a lot of URLs, use multiple `Explorer` subagents to explore them in parallel, then report back to main agent.
-- If you receive a lot of files, use multiple `Explorer` subagents to explore them in parallel, then report back to main agent.
-- If you're given a Github URL, use [`repomix`](https://repomix.com/guide/usage) command to summarize ([install it](https://repomix.com/guide/installation) if needed) and spawn multiple `Explorer` subagents to explore it in parallel, then report back to main agent.
-
-### Scopes
-- Project-scope: Current working project directory (e.g. `.opencode/`)
-- User-scope: Home/user directory (e.g. `~/.opencode/`)

package/.opencode/commands/ckm-skill-optimize-auto.md

@@ -1,30 +0,0 @@
----
-description: "Optimize an existing agent skill [auto]"
----
-
-Think harder.
-Use `skill-creator` and `claude-code` skills.
-Use `docs-seeker` skills to search for documentation if needed.
-
-## Arguments
-SKILL: $1 (default: `*`)
-PROMPT: $2 (default: empty)
-
-## Your mission
-Optimize an existing skill in `.opencode/skills/${SKILL}` directory. 
-Always keep in mind that `SKILL.md` and reference files should be token consumption efficient, so that **progressive disclosure** can be leveraged at best.
-`SKILL.md` is always short and concise, straight to the point, treat it as a quick reference guide.
-
-### Scopes
-- Project-scope: Current working project directory (e.g. `.opencode/`)
-- User-scope: Home/user directory (e.g. `~/.opencode/`)
-
-**IMPORTANT:**
-- ALWAYS make changes to skills in the project-scope directory (UNLESS you're allowed to).
-- DO NOT make any changes to skills in the user-scope directory (UNLESS you're allowed to).
-- Skills are not documentation, they are practical instructions for Claude Code to use the tools, packages, plugins or APIs to achieve the tasks.
-- Each skill teaches Claude how to perform a specific development task, not what a tool does.
-- Claude Code can activate multiple skills automatically to achieve the user's request.
-
-## Additional instructions
-<additional-instructions>$PROMPT</additional-instructions>

package/.opencode/commands/ckm-skill-optimize.md

@@ -1,39 +0,0 @@
----
-description: "Optimize an existing agent skill - Args: ['skill-name] [prompt']"
----
-
-Think harder.
-Use `skill-creator` and `claude-code` skills.
-Use `docs-seeker` skills to search for documentation if needed.
-
-## Arguments
-SKILL: $1 (default: `*`)
-PROMPT: $2 (default: empty)
-
-## Your mission
-Propose a plan to optimize an existing skill in `.opencode/skills/${SKILL}` directory. 
-When you finish, ask user to review your plan:
-- If the user approve: Write down a plan follow "Output Requirements", then ask user if they want to start implementing.
-- If the user reject: Revise the plan or ask more questions to clarify more about the user's request (ask one question at the time), then repeat the review process.
-
-## Additional instructions
-<additional-instructions>$PROMPT</additional-instructions>
-
-## Output Requirements
-An output implementation plan must also follow the progressive disclosure structure:
-- Always keep in mind that `SKILL.md` and reference files should be token consumption efficient, so that **progressive disclosure** can be leveraged at best.
-- `SKILL.md` is always short and concise, straight to the point, treat it as a quick reference guide.
-- Create a directory using naming pattern from `## Naming` section.
-- Save the overview access point at `plan.md`, keep it generic, under 80 lines, and list each phase with status/progress and links.
-- For each phase, add `phase-XX-phase-name.md` files containing sections (Context links, Overview with date/priority/statuses, Key Insights, Requirements, Architecture, Related code files, Implementation Steps, Todo list, Success Criteria, Risk Assessment, Security Considerations, Next steps).
-
-### Scopes
-- Project-scope: Current working project directory (e.g. `.opencode/`)
-- User-scope: Home/user directory (e.g. `~/.opencode/`)
-
-**IMPORTANT:**
-- ALWAYS make changes to skills in the project-scope `.opencode/skills/` directory (UNLESS you're allowed to).
-- DO NOT make any changes to skills in the home/user-scope `~/.opencode/skills/` directory (UNLESS you're allowed to).
-- Skills are not documentation, they are practical instructions for Claude Code to use the tools, packages, plugins or APIs to achieve the tasks.
-- Each skill teaches Claude how to perform a specific development task, not what a tool does.
-- Claude Code can activate multiple skills automatically to achieve the user's request.

package/.opencode/commands/ckm-skill-plan.md

@@ -1,50 +0,0 @@
----
-description: "Plan to create a new agent skill - Args: ['skill-name] [prompt']"
----
-
-Think harder.
-First: Activate `skill-creator` and `claude-code` skills.
-Use `docs-seeker` skills to search for documentation if needed.
-Employ `sequential-thinking` or `problem-solving` skills for complex problem-solving that requires structured analysis
-Finally, when creating a plan, activate `planning` skill.
-
-## Arguments
-SKILL: $1 (default: `*`)
-PROMPT: $2 (default: empty)
-
-## Your mission
-Propose a plan to create a new skill in `.opencode/skills/${SKILL}` directory. 
-When you finish, ask user to review your plan:
-- If the user approve: Write down a plan follow "Output Requirements", then ask user if they want to start implementing.
-- If the user reject: Revise the plan or ask more questions to clarify more about the user's request (ask one question at the time), then repeat the review process.
-
-## Additional instructions
-<additional-instructions>$PROMPT</additional-instructions>
-
-## Your Approach
-1. **Question Everything**: Ask probing questions to fully understand the user's request, constraints, and true objectives. Don't assume - clarify until you're 100% certain.
-2. **Brutal Honesty**: Provide frank, unfiltered feedback about ideas. If something is unrealistic, over-engineered, or likely to cause problems, say so directly. Your job is to prevent costly mistakes.
-3. **Explore Alternatives**: Always consider multiple approaches. Present 2-3 viable solutions with clear pros/cons, explaining why one might be superior.
-4. **Challenge Assumptions**: Question the user's initial approach. Often the best solution is different from what was originally envisioned.
-5. **Consider All Stakeholders**: Evaluate impact on end users, developers, operations team, and business objectives.
-
-## Output Requirements
-An output implementation plan must also follow the progressive disclosure structure:
-- Always keep in mind that `SKILL.md` and reference files should be token consumption efficient, so that **progressive disclosure** can be leveraged at best.
-- `SKILL.md` is always short and concise, straight to the point, treat it as a quick reference guide.
-- Create a directory using naming pattern from `## Naming` section.
-- Save the overview access point at `plan.md`, keep it generic, under 80 lines, and list each phase with status/progress and links.
-- For each phase, add `phase-XX-phase-name.md` files containing sections (Context links, Overview with date/priority/statuses, Key Insights, Requirements, Architecture, Related code files, Implementation Steps, Todo list, Success Criteria, Risk Assessment, Security Considerations, Next steps).
-
-### Scopes
-- Project-scope: Current working project directory (e.g. `.opencode/`)
-- User-scope: Home/user directory (e.g. `~/.opencode/`)
-
-**IMPORTANT:**
-- ALWAYS make changes to skills in the project-scope `.opencode/skills/` directory (UNLESS you're allowed to).
-- DO NOT make any changes to skills in the home/user-scope `~/.opencode/skills/` directory (UNLESS you're allowed to).
-- Analyze the given task and use `AskUserQuestion` tool to ask for more details if needed.
-- Ensure token consumption efficiency while maintaining high quality.
-- Skills are not documentation, they are practical instructions for Claude Code to use the tools, packages, plugins or APIs to achieve the tasks.
-- Each skill teaches Claude how to perform a specific development task, not what a tool does.
-- Claude Code can activate multiple skills automatically to achieve the user's request.

package/.opencode/commands/ckm-skill-update.md

@@ -1,35 +0,0 @@
----
-description: "Update an existing agent skill [auto]"
----
-
-Think harder.
-Use `skill-creator` and `claude-code` skills.
-Use `docs-seeker` skills to search for documentation if needed.
-
-## Arguments
-SKILL: $1 (default: `*`)
-PROMPT: $2 (default: empty)
-
-## Your mission
-Update an existing skill or its reference files in `.opencode/skills/${SKILL}` directory based on the user's prompt. 
-Always keep in mind that `SKILL.md` and reference files should be token consumption efficient, so that **progressive disclosure** can be leveraged at best.
-`SKILL.md` is always short and concise, straight to the point, treat it as a quick reference guide.
-
-### Scopes
-- Project-scope: Current working project directory (e.g. `.opencode/`)
-- User-scope: Home/user directory (e.g. `~/.opencode/`)
-
-## IMPORTANT NOTES:
-- ALWAYS make changes to skills in the project-scope `.opencode/skills/` directory (UNLESS you're allowed to).
-- DO NOT make any changes to skills in the home/user-scope `~/.opencode/skills/` directory (UNLESS you're allowed to).
-- If you're given nothing, use `AskUserQuestion` tool for clarifications and `researcher` subagent to research about the topic.
-- If you're given an URL, it's documentation page, use `Explore` subagent to explore every internal link and report back to main agent, don't skip any link.
-- If you receive a lot of URLs, use multiple `Explore` subagents to explore them in parallel, then report back to main agent.
-- If you receive a lot of files, use multiple `Explore` subagents to explore them in parallel, then report back to main agent.
-- If you're given a Github URL, use [`repomix`](https://repomix.com/guide/usage) command to summarize ([install it](https://repomix.com/guide/installation) if needed) and spawn multiple `Explore` subagents to explore it in parallel, then report back to main agent.
-- Skills are not documentation, they are practical instructions for Claude Code to use the tools, packages, plugins or APIs to achieve the tasks.
-- Each skill teaches Claude how to perform a specific development task, not what a tool does.
-- Claude Code can activate multiple skills automatically to achieve the user's request.
-
-## Additional instructions
-<additional-instructions>$PROMPT</additional-instructions>

package/.opencode/commands/ckm-slides-create.md

@@ -1,8 +0,0 @@
----
-description: "Create strategic presentation slides with Chart.js and design tokens - Args: ['presentation goal and context']"
----
-
-Invoke `slides-design` skill to create persuasive HTML slides using design tokens, Chart.js, and the slide knowledge database.
-
-## Task
-<task>$ARGUMENTS</task>