@justin_666/square-couplets-master-skills 1.0.5 → 1.0.6

package/bin/doufang-init.js

@@ -155,8 +155,18 @@ You are a Doufang assistant. When the user uses the \`/doufang\` command or asks
 
 ## Execution Guidelines
 
-- **Direct CLI Execution**: When user requests Doufang functionality, directly execute the appropriate CLI command using terminal, do NOT create .js files
-- **Read API Key**: Automatically read GEMINI_API_KEY from .env or .env.local file
+- **CRITICAL: Direct CLI Execution Only**: 
+  - When user requests Doufang functionality, you MUST directly execute the CLI command in the terminal
+  - **NEVER create temporary .js, .ts, or any script files**
+  - **NEVER write code to files** - just execute the command directly
+  - Use the terminal/command execution tool to run: \`doufang-prompt\`, \`doufang-image\`, or \`doufang-optimize\`
+  
+- **Command Execution Examples**:
+  - User: "生成財富主題的 prompt" → Execute: \`doufang-prompt "財富"\`
+  - User: "用上述 prompt 生成 2K 圖片" → Execute: \`doufang-image "<prompt>" gemini-3-pro-image-preview 2K\`
+  - User: "優化這個 prompt" → Execute: \`doufang-optimize "<prompt>"\`
+
+- **Read API Key**: Automatically read GEMINI_API_KEY from .env or .env.local file (CLI commands handle this automatically)
 - **Ask for Details**: If user doesn't provide required parameters (like keyword or prompt), ask for clarification
 - **Error Handling**: If API key is missing, guide user to set GEMINI_API_KEY in .env file
 - **Output Format**: For prompt generation, output JSON format. For image generation, save to output/ directory and provide file path
@@ -164,19 +174,27 @@ You are a Doufang assistant. When the user uses the \`/doufang\` command or asks
 ## Common Workflows
 
 ### Generate Image from Keyword
-1. Generate prompt: \`doufang-prompt "財富"\`
+1. Execute: \`doufang-prompt "財富"\` (directly in terminal, no script creation)
 2. Extract imagePrompt from JSON output
-3. Generate image: \`doufang-image "<imagePrompt>" gemini-3-pro-image-preview 2K\`
+3. Execute: \`doufang-image "<imagePrompt>" gemini-3-pro-image-preview 2K\` (directly in terminal, no script creation)
 
 ### Generate Image with Reference
-1. Generate prompt with reference: \`doufang-prompt "健康" images/reference.png\`
+1. Execute: \`doufang-prompt "健康" images/reference.png\` (directly in terminal)
 2. Extract imagePrompt from JSON output
-3. Generate image: \`doufang-image "<imagePrompt>" gemini-3-pro-image-preview 2K images/reference.png\`
+3. Execute: \`doufang-image "<imagePrompt>" gemini-3-pro-image-preview 2K images/reference.png\` (directly in terminal)
 
 ### Optimize and Generate
-1. Generate prompt: \`doufang-prompt "財富"\`
-2. Optimize prompt: \`doufang-optimize "<imagePrompt>"\`
-3. Generate image with optimized prompt: \`doufang-image "<optimizedPrompt>" gemini-3-pro-image-preview 2K\`
+1. Execute: \`doufang-prompt "財富"\` (directly in terminal)
+2. Execute: \`doufang-optimize "<imagePrompt>"\` (directly in terminal)
+3. Execute: \`doufang-image "<optimizedPrompt>" gemini-3-pro-image-preview 2K\` (directly in terminal)
+
+## IMPORTANT REMINDERS
+
+- **DO NOT** create any .js, .ts, .mjs, or script files
+- **DO NOT** write code to files
+- **DO** execute CLI commands directly using terminal/command execution
+- The CLI commands (\`doufang-prompt\`, \`doufang-image\`, \`doufang-optimize\`) are already installed and ready to use
+- Just run the commands - they handle everything automatically
 
 ## Skills Location
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@justin_666/square-couplets-master-skills",
-  "version": "1.0.5",
+  "version": "1.0.6",
   "description": "Claude Agent Skills for generating Chinese New Year Doufang (diamond-shaped couplet) artwork using Google Gemini AI",
   "type": "module",
   "main": "bin/doufang-skills.js",

package/skills/generate-doufang-image/SKILL.md

@@ -151,6 +151,12 @@ Error: Network connection error. Please check your internet connection and try a
 
 ## Implementation Notes
 
+- **CRITICAL: Use CLI Command Directly**
+  - Execute: `doufang-image <prompt> [model] [size] [reference-image] [output-path]`
+  - **DO NOT create temporary .js, .ts, or any script files**
+  - **DO NOT write code** - just execute the CLI command directly
+  - The CLI command handles all API calls, error handling, and file operations automatically
+
 - Use retry mechanism for transient errors (500, 503, network errors)
 - Compress reference images if they exceed 500KB
 - Validate image formats (JPEG, PNG supported)

package/skills/generate-doufang-prompt/SKILL.md

@@ -106,3 +106,11 @@ When user provides a keyword or wish phrase, generate a professional Doufang art
 - User already has a complete prompt
 - User wants to modify an existing prompt (use `optimize-doufang-prompt` instead)
 - User wants to generate the actual image (use `generate-doufang-image` instead)
+
+## Implementation Notes
+
+- **CRITICAL: Use CLI Command Directly**
+  - Execute: `doufang-prompt <keyword> [reference-image]`
+  - **DO NOT create temporary .js, .ts, or any script files**
+  - **DO NOT write code** - just execute the CLI command directly
+  - The CLI command handles all API calls and returns JSON output automatically

package/skills/optimize-doufang-prompt/SKILL.md

@@ -152,3 +152,11 @@ This skill works best when:
 ## Output Format
 
 Return the optimized prompt as a string, maintaining all other aspects of the original prompt while only modifying the composition and margin-related instructions.
+
+## Implementation Notes
+
+- **CRITICAL: Use CLI Command Directly**
+  - Execute: `doufang-optimize <prompt>`
+  - **DO NOT create temporary .js, .ts, or any script files**
+  - **DO NOT write code** - just execute the CLI command directly
+  - The CLI command handles prompt optimization and returns the optimized prompt automatically