myaidev-method 0.3.3 → 0.3.5

package/skills/content-writer/SKILL.md

@@ -1,285 +0,0 @@
----
-name: content-writer
-description: Orchestrates professional content creation through a multi-agent pipeline covering research, planning, writing, SEO optimization, and editorial review. Use when creating articles, blog posts, technical tutorials, or any written content.
-argument-hint: "<topic> [--word-count=1500] [--tone=professional] [--type=blog-post]"
-allowed-tools: [Read, Write, WebSearch, WebFetch, Task, Bash, Glob, Grep, AskUserQuestion]
-context: fork
----
-
-# Content Writer — Orchestrator
-
-You are the **Content Production Orchestrator**. You parse arguments, dispatch specialized subagents via the Task tool, and assemble their outputs into a final article. All intermediate state flows through `.content-session/` scratchpad files.
-
-## Subagent Registry
-
-Each subagent is a real Claude Code subagent defined in `agents/` with its own tools and model:
-
-| Phase | Subagent Name | Model | Tools |
-|-------|--------------|-------|-------|
-| Research | `content-research-agent` | inherit | WebSearch, WebFetch, Read, Write |
-| Planning | `content-planner-agent` | sonnet | Read, Write |
-| Writing | `content-writer-agent` | inherit | Read, Write, WebSearch |
-| SEO | `content-seo-agent` | haiku | Read, Write, WebSearch |
-| Editor | `content-editor-agent` | sonnet | Read, Write |
-
-## Execution Phases
-
-### Phase 0: Initialize
-- Parse `$ARGUMENTS` for topic, flags, and parameters
-- Load `content-rules.md` if present (check: `./content-rules.md`, `./.claude/content-rules.md`, `./docs/content-rules.md`)
-- Determine content type template and constraints
-- Create scratchpad directory: `.content-session/` (ephemeral, gitignored)
-
-### Phase 1: Research
-
-Spawn the research subagent:
-
-```
-Task(subagent_type: "content-research-agent", prompt: "
-  Research the topic '{topic}' for a {type} article.
-  Target audience: {audience}. Tone: {tone}.
-  {content_rules_section}
-  Write your findings to .content-session/research.md
-")
-```
-
-Skip if `--no-research` flag is set.
-
-### Phase 2: Plan
-
-Read `.content-session/research.md`, then spawn the planner:
-
-```
-Task(subagent_type: "content-planner-agent", prompt: "
-  Create a detailed article plan for: '{topic}'
-  Content type: {type} | Word count: {word_count} | Tone: {tone}
-  Audience: {audience} | Keywords: {keywords}
-
-  Research summary (from Phase 1):
-  {brief research summary - key findings, angle, gaps}
-
-  {content_rules_section}
-  Write the plan to .content-session/plan.md
-")
-```
-
-### Phase 3: Write (main workload)
-
-Read `.content-session/plan.md` and `.content-session/research.md`, then spawn the writer:
-
-```
-Task(subagent_type: "content-writer-agent", prompt: "
-  Write the full article based on the plan and research.
-  Read the plan from: .content-session/plan.md
-  Read the research from: .content-session/research.md
-  {content_rules_section}
-  Write the complete draft to .content-session/draft.md
-")
-```
-
-### Phase 4: Optimize (Parallel)
-
-Spawn SEO and editorial subagents **in parallel**:
-
-```
-Task(subagent_type: "content-seo-agent", prompt: "
-  Analyze the article draft for SEO optimization.
-  Read the draft from: .content-session/draft.md
-  Keywords: {keywords}. Content type: {type}.
-  Write your SEO report to .content-session/seo-report.md
-")
-
-Task(subagent_type: "content-editor-agent", prompt: "
-  Review the article draft for quality and publication readiness.
-  Read the draft from: .content-session/draft.md
-  Target tone: {tone}. Target audience: {audience}.
-  {content_rules_section}
-  Write your editorial report to .content-session/edit-notes.md
-")
-```
-
-### Phase 5: Assemble & Finalize
-
-The orchestrator (this skill):
-- Reads all scratchpad files (.content-session/draft.md, seo-report.md, edit-notes.md)
-- Applies SEO recommendations to the draft
-- Incorporates editorial improvements
-- Produces final article with proper frontmatter
-- Saves to `./content-output/{slug}.md`
-- Cleans up `.content-session/` directory
-
-## Parameters
-
-| Parameter | Description | Default |
-|-----------|-------------|---------|
-| `topic` | Main subject matter | Required |
-| `--word-count` | Target article length | 1500 |
-| `--tone` | Voice: professional, casual, technical, conversational, academic | professional |
-| `--type` | Template: blog-post, technical-tutorial, how-to-guide, listicle, comparison-guide, case-study, api-documentation, architecture-guide | blog-post |
-| `--audience` | Target reader demographic | general |
-| `--keywords` | Comma-separated primary,secondary keywords | auto-detected |
-| `--publish` | Publish to platform: wordpress, payloadcms, docusaurus, mintlify, astro | none |
-| `--output-dir` | Output directory for final article | ./content-output |
-| `--no-research` | Skip research phase (use for topics you provide context for) | false |
-| `--verbose` | Show detailed progress from each phase | false |
-
-## Content Rules Integration
-
-The orchestrator automatically discovers and loads content rules. Rules are passed to every subagent via the Task prompt to ensure consistent brand voice.
-
-**Discovery order:**
-1. `./content-rules.md`
-2. `./.claude/content-rules.md`
-3. `./docs/content-rules.md`
-
-If no rules file exists, suggest running the content-rules-setup skill.
-
-**Rules are injected into Task prompts as:**
-```
-## Brand & Style Guidelines (from content-rules.md)
-{content of rules file}
-```
-
-## State Management (Scratchpad Pattern)
-
-All intermediate work is written to `.content-session/` directory:
-
-```
-.content-session/
-├── config.json          # Parsed arguments and settings
-├── content-rules.md     # Loaded content rules (if found)
-├── research.md          # Research agent output
-├── plan.md              # Article plan
-├── draft.md             # Writer agent output
-├── seo-report.md        # SEO optimization suggestions
-├── edit-notes.md        # Editorial feedback
-└── final-meta.json      # Assembled frontmatter data
-```
-
-## Execution Flow
-
-```
-1. INIT        -> Parse args, load rules, create session dir
-2. RESEARCH    -> Task(content-research-agent) — skip if --no-research
-3. PLAN        -> Task(content-planner-agent) with research summary
-4. WRITE       -> Task(content-writer-agent) with plan + research
-5. OPTIMIZE    -> Task(content-seo-agent) + Task(content-editor-agent) IN PARALLEL
-6. ASSEMBLE    -> Read all outputs, produce final article
-7. OUTPUT      -> Save to output-dir, optionally publish
-8. CLEANUP     -> Remove .content-session/ directory
-```
-
-## Error Handling
-
-- If a subagent fails, log the error and continue with what's available
-- Research failure -> proceed with plan (user-provided context may suffice)
-- SEO/Editor failure -> use draft as-is with basic frontmatter
-- Never block the entire pipeline on a single failure
-
-## Pipeline Checklist
-
-Copy and track progress through each phase:
-
-```
-Pipeline Progress:
-- [ ] Phase 0: Parse arguments, load content-rules, create .content-session/
-- [ ] Phase 1: Research (content-research-agent) — skip if --no-research
-- [ ] Phase 2: Plan (content-planner-agent) with research summary
-- [ ] Phase 3: Write (content-writer-agent) with plan + research
-- [ ] Phase 4: Optimize — SEO + Editor agents IN PARALLEL
-- [ ] Phase 5: Assemble final article from all outputs
-- [ ] Phase 6: Save to output-dir, publish if requested
-- [ ] Phase 7: Clean up .content-session/
-```
-
-## Context Management
-
-### Context Regurgitation
-Before dispatching each subagent, restate in the Task prompt:
-- Current phase number and what's been completed
-- Key decisions made (chosen angle, title direction, tone calibration)
-- What this subagent needs to accomplish and how its output feeds the next phase
-
-### Dynamic Plan Updates
-If a subagent returns indicating the plan needs revision (e.g., writer discovers research gaps, SEO agent finds the angle is unsearchable):
-1. Parse the update request from the subagent's output
-2. Re-run the affected earlier phase with the new context
-3. Resume the pipeline from the current phase
-4. Maximum **2 plan revisions per session** to prevent infinite loops
-
-### File Buffering
-When constructing Task prompts for subsequent phases, read only the specific sections needed from `.content-session/` files. Summarize key points and reference the scratchpad file path so the subagent can read details itself.
-
-## Progress Reporting
-
-At each phase transition, report to the user:
-
-```
--> Phase 1/5: Researching "{topic}"...
-  Done: Found 6 sources, identified 3 unique angles
--> Phase 2/5: Planning article structure...
-  Done: Outline ready: 5 sections, ~{word_count} words target
--> Phase 3/5: Writing article...
-  Done: Draft complete: {actual_word_count} words
--> Phase 4/5: Optimizing (SEO + Editorial review)...
-  Done: SEO score: 8.5/10 | Editorial score: 8/10
--> Phase 5/5: Assembling final article...
-  Done: Saved to ./content-output/{slug}.md
-
-Summary:
-  Words: {count} | Reading Time: {time}
-  SEO Score: {score}/10 | Quality: {score}/10
-```
-
-## Output Format
-
-Final article is saved with full frontmatter:
-
-```markdown
----
-title: [SEO-optimized title]
-meta_description: [150-160 chars]
-slug: [url-friendly]
-tags: [relevant, tags]
-keywords:
-  primary: [main keyword]
-  secondary: [supporting, keywords]
-word_count: [actual count]
-reading_time: [X minutes]
-content_type: [type used]
-generated_at: [ISO timestamp]
----
-
-# [Title]
-
-[Full article content]
-```
-
-## Publishing Integration
-
-If `--publish` is specified, after saving the article locally:
-
-1. Determine target platform from flag value
-2. Use the appropriate publishing approach:
-   - WordPress: use the wp MCP tools directly
-   - Other platforms: use platform-specific skills if available
-3. Report published URL to user
-
-## Example Usage
-
-```bash
-# Basic article
-/myaidev-method:content-writer "Kubernetes Best Practices for Production"
-
-# Technical tutorial with custom length
-/myaidev-method:content-writer "Building a RAG Pipeline" --word-count=2500 --type=technical-tutorial --tone=technical
-
-# With publishing
-/myaidev-method:content-writer "Getting Started with Docker" --publish=wordpress --tone=conversational
-
-# Skip research (you provide context)
-/myaidev-method:content-writer "Our Q4 Product Launch" --no-research --type=case-study
-
-# Custom output location
-/myaidev-method:content-writer "API Design Patterns" --output-dir=./blog/posts --keywords="api design,rest best practices"
-```

package/skills/visual-generator/SKILL.md

@@ -1,140 +0,0 @@
----
-name: visual-generator
-description: Generates high-quality images and videos using AI APIs (Gemini, Imagen, DALL-E, FLUX, Veo). Use when creating hero images, diagrams, infographics, or video content for articles and projects.
-argument-hint: [prompt] [--type=hero] [--service=gemini]
-allowed-tools: [Read, Write, Bash, Task]
----
-
-# Visual Generator Skill
-
-Generate high-quality images and videos for content creation using AI generation APIs (Google Gemini Flash, Imagen 3, DALL-E 3, FLUX 2 Pro, Veo 3).
-
-## Capabilities
-
-- Hero images for articles and landing pages
-- Technical diagrams and architecture illustrations
-- Infographics (data, process, comparison, timeline)
-- Screenshots and UI mockups
-- Video content for demos and tutorials
-
-## Supported Services
-
-| Service | Type | Cost | Best For |
-|---------|------|------|----------|
-| Gemini 2.5 Flash | Image | $0.02 | Fast, diagrams, general use |
-| Imagen 3 | Image | $0.03 | Premium quality heroes |
-| DALL-E 3 | Image | $0.04-0.12 | Creative, artistic |
-| GPT Image 1.5 | Image | $0.02 | Text-heavy visuals |
-| FLUX 2 Pro | Image | $0.03 | Detailed illustrations |
-| Veo 3 | Video | $0.10 | Product demos, tutorials |
-
-## Image Types
-
-| Type | Description | Recommended Service |
-|------|-------------|---------------------|
-| `hero` | Article header, main theme | FLUX 2 Pro / Imagen |
-| `illustration` | Abstract concepts, metaphors | FLUX 2 Pro |
-| `diagram` | Technical workflows, architecture | Gemini |
-| `screenshot` | UI mockups, interface designs | GPT Image 1.5 |
-| `infographic-data` | Statistics, metrics, charts | GPT Image 1.5 |
-| `infographic-process` | Step flows, workflows | FLUX 2 Pro |
-| `infographic-comparison` | Side-by-side comparisons | GPT Image 1.5 |
-| `infographic-timeline` | Chronological events | FLUX 2 Pro |
-| `architecture-diagram` | System design, tech stacks | Gemini |
-| `flowchart` | Decision trees, processes | Gemini |
-| `sequence-diagram` | API/service interactions | Gemini |
-| `video` | Product demos, tutorials | Veo 3 |
-
-## Prerequisites
-
-- At least one API key configured:
-  - `GOOGLE_API_KEY` (for Gemini, Imagen, Veo)
-  - `OPENAI_API_KEY` (for DALL-E, GPT Image)
-  - `FAL_KEY` (for FLUX 2 Pro)
-
-Run `/myai-configure visual` to set up API keys.
-
-## Process
-
-1. **Configuration Check**: Verify API keys are configured
-2. **Requirements Gathering**: Collect prompt, type, and preferences
-3. **Cost Estimation**: Show estimated cost and check budget
-4. **Generation**: Generate image/video using selected service
-5. **Asset Management**: Save to organized directory structure
-6. **Markdown Reference**: Return embed code for content
-
-## File Organization
-
-```
-content-assets/
-  ├── images/
-  │   └── YYYY-MM-DD/
-  │       └── {type}-{description}-{id}.png
-  └── videos/
-      └── YYYY-MM-DD/
-          └── video-{description}-{id}.mp4
-```
-
-## Parameters
-
-| Parameter | Description | Default |
-|-----------|-------------|---------|
-| `prompt` | What the image/video should depict | Required |
-| `--type` | Image type (see table above) | hero |
-| `--service` | Preferred generation service | auto |
-| `--quality` | low, medium, high | medium |
-| `--size` | 1024x1024, 1792x1024, 1024x1792 | 1024x1024 |
-| `--description` | Short description for filename | auto |
-
-## Budget Management
-
-The skill tracks daily and monthly spending:
-- Default daily budget: $5.00
-- Default monthly budget: $50.00
-
-Configure limits in `.env`:
-```
-VISUAL_DAILY_BUDGET=10.00
-VISUAL_MONTHLY_BUDGET=100.00
-```
-
-## HTML Conversion Alternative
-
-For data-driven visuals requiring pixel-perfect accuracy, use HTML conversion instead of AI generation:
-
-| Use Case | Tool |
-|----------|------|
-| Exact numbers/data | HTML Conversion |
-| Precise text labels | HTML/D2 Conversion |
-| Charts and graphs | HTML Conversion |
-| Creative/artistic | AI Generation |
-
-## Example Usage
-
-```bash
-# Basic hero image
-/myaidev-method:generate-visual "Modern developer workspace" --type=hero
-
-# Technical diagram
-/myaidev-method:generate-visual "Microservices architecture with API gateway" --type=architecture-diagram --service=gemini
-
-# Data infographic
-/myaidev-method:generate-visual "5 Key API Metrics: Latency <50ms, Uptime 99.99%" --type=infographic-data --service=gpt-image-1.5
-
-# Video content
-/myaidev-method:generate-visual "Product demo showing login flow" --type=video --service=veo3
-```
-
-## Integration
-
-- Works with `/myaidev-method:content-writer` via `--with-images` flag
-- Automatic asset organization and cost tracking
-- Markdown reference generation for easy embedding
-
-## Error Handling
-
-- Rate limiting: Wait 60 seconds and retry, or switch service
-- Budget exceeded: Shows usage and suggests increasing limits
-- API errors: Provides helpful guidance and alternatives
-
-Always prioritize user experience, cost transparency, and quality results.