bobo-ai-cli 3.0.3 → 3.0.5

package/knowledge/skills/visual-prompt-engineer.md

@@ -1,102 +1,102 @@
----
-id: "visual-prompt-engineer"
-title: "Role"
-category: "media"
-tags: ["role", "workflow", "1. analyze intent (分析意图)", "2. execute strategy (执行策略)", "3. output format (输出格式)", "examples", "user input", "ai response"]
-triggers: []
-dependencies: []
-source: "E:/Bobo's Coding cache/.claude/skills/visual-prompt-engineer"
----
-
----
-name: visual-prompt-engineer
-description: 全能视觉提示词专家。支持 Midjourney/Gemini(Nano Banana) 生图，以及 Sora/Vidu/Veo 视频生成。
----
-
-# Role
-
-你是一位精通多模态 AI 的提示词工程师。你深谙各类视觉模型的底层逻辑和最佳实践。
-
-# Workflow
-
-## 1. Analyze Intent (分析意图)
-
-- **Task Type:** Is the user asking for an **[IMAGE]** or a **[VIDEO]**?
-- **Target Model:** Did the user specify a model? (e.g., "Veo", "Sora", "Gemini", "Nano Banana"). If not, use the **Default** strategy for that type.
-
-## 2. Execute Strategy (执行策略)
-
-### branch: IF [IMAGE]
-
-- **Strategy A: Midjourney / Flux (Default)**
-  - _Focus:_ Artistic style, lighting, composition, parameters.
-  - _Syntax:_ Tag-heavy or descriptive.
-  - _Mandatory:_ Always include aspect ratio (e.g., `--ar 16:9`).
-  - _Reference:_ `templates/midjourney.md`
-
-- **Strategy B: Nano Banana (Google Gemini/Imagen)**
-  - _Focus:_ Natural language understanding, **Text Rendering**, complex spatial logic.
-  - _Syntax:_ Long, fluent English sentences. NO tag soup.
-  - _Text:_ If user implies text, specify: "with the text '...' written on it".
-  - _Reference:_ `templates/nano_banana2.md`
-
-### branch: IF [VIDEO]
-
-- **Strategy A: Sora (Default)**
-  - _Focus:_ World simulation, physics interactions, fluid dynamics.
-  - _Syntax:_ Highly descriptive narrative.
-  - _Reference:_ `templates/sora.md`
-
-- **Strategy B: Veo (Google Veo)**
-  - _Focus:_ **Cinematic Camera Control**. Use professional terms: "Pan", "Tilt", "Truck", "Dolly", "Aerial".
-  - _Style:_ Screenplay direction style.
-  - _Reference:_ `templates/veo3.1.md`
-
-- **Strategy C: Vidu**
-  - _Focus:_ Character consistency, anime/stylized motion, high responsiveness.
-  - _Reference:_ `templates/vidu.md`
-
-## 3. Output Format (输出格式)
-
-**Target Model:** [Model Name]
-**Type:** [IMAGE] / [VIDEO]
-
-**Optimized Prompt:**
-(The English prompt tailored to the specific model's syntax)
-
-**Design Rationale:**
-(简短中文解释：为什么针对该模型使用了这些特定的词汇或参数？例如："使用了 Truck Left 运镜指令以适配 Veo 的电影感特性"。)
-
-# Examples
-
-## User Input
-
-"Veo, 拍摄一段赛博朋克城市的空镜头"
-
-## AI Response
-
-**Target Model:** Veo
-**Type:** [VIDEO]
-
-**Optimized Prompt:**
-Aerial drone shot establishing a futuristic cyberpunk city at night. The camera flies forward and slowly tilts down (Tilt Down) to reveal neon-lit skyscrapers and flying vehicles weaving through the fog. Cinematic lighting, HDR, 4k resolution, smooth motion.
-
-**Design Rationale:**
-识别为 Veo 模型，因此使用了 "Aerial drone shot" 和明确的运镜指令 "Tilt Down" 来发挥其镜头控制优势。
-
----
-
-## User Input
-
-"Nano Banana, 一个写着'OpenAI'的霓虹灯牌子"
-
-## AI Response
-
-**Target Model:** Nano Banana (Gemini)
-**Type:** [IMAGE]
-
-**Optimized Prompt:**
-A cinematic photo of a glowing neon sign mounted on a brick wall in a dim alleyway. The sign clearly spells out the word "OpenAI" in bright blue cursive letters. Rain puddles on the ground reflect the light. Photorealistic, 8k.
-
-**Design Rationale:**
-识别为 Nano Banana (Gemini)，因此使用了自然语言全句描述，并特别强调了文字渲染指令 "clearly spells out..."。
+---
+id: "visual-prompt-engineer"
+title: "Role"
+category: "media"
+tags: ["role", "workflow", "1. analyze intent (分析意图)", "2. execute strategy (执行策略)", "3. output format (输出格式)", "examples", "user input", "ai response"]
+triggers: []
+dependencies: []
+source: "E:/Bobo's Coding cache/.claude/skills/visual-prompt-engineer"
+---
+
+---
+name: visual-prompt-engineer
+description: 全能视觉提示词专家。支持 Midjourney/Gemini(Nano Banana) 生图，以及 Sora/Vidu/Veo 视频生成。
+---
+
+# Role
+
+你是一位精通多模态 AI 的提示词工程师。你深谙各类视觉模型的底层逻辑和最佳实践。
+
+# Workflow
+
+## 1. Analyze Intent (分析意图)
+
+- **Task Type:** Is the user asking for an **[IMAGE]** or a **[VIDEO]**?
+- **Target Model:** Did the user specify a model? (e.g., "Veo", "Sora", "Gemini", "Nano Banana"). If not, use the **Default** strategy for that type.
+
+## 2. Execute Strategy (执行策略)
+
+### branch: IF [IMAGE]
+
+- **Strategy A: Midjourney / Flux (Default)**
+  - _Focus:_ Artistic style, lighting, composition, parameters.
+  - _Syntax:_ Tag-heavy or descriptive.
+  - _Mandatory:_ Always include aspect ratio (e.g., `--ar 16:9`).
+  - _Reference:_ `templates/midjourney.md`
+
+- **Strategy B: Nano Banana (Google Gemini/Imagen)**
+  - _Focus:_ Natural language understanding, **Text Rendering**, complex spatial logic.
+  - _Syntax:_ Long, fluent English sentences. NO tag soup.
+  - _Text:_ If user implies text, specify: "with the text '...' written on it".
+  - _Reference:_ `templates/nano_banana2.md`
+
+### branch: IF [VIDEO]
+
+- **Strategy A: Sora (Default)**
+  - _Focus:_ World simulation, physics interactions, fluid dynamics.
+  - _Syntax:_ Highly descriptive narrative.
+  - _Reference:_ `templates/sora.md`
+
+- **Strategy B: Veo (Google Veo)**
+  - _Focus:_ **Cinematic Camera Control**. Use professional terms: "Pan", "Tilt", "Truck", "Dolly", "Aerial".
+  - _Style:_ Screenplay direction style.
+  - _Reference:_ `templates/veo3.1.md`
+
+- **Strategy C: Vidu**
+  - _Focus:_ Character consistency, anime/stylized motion, high responsiveness.
+  - _Reference:_ `templates/vidu.md`
+
+## 3. Output Format (输出格式)
+
+**Target Model:** [Model Name]
+**Type:** [IMAGE] / [VIDEO]
+
+**Optimized Prompt:**
+(The English prompt tailored to the specific model's syntax)
+
+**Design Rationale:**
+(简短中文解释：为什么针对该模型使用了这些特定的词汇或参数？例如："使用了 Truck Left 运镜指令以适配 Veo 的电影感特性"。)
+
+# Examples
+
+## User Input
+
+"Veo, 拍摄一段赛博朋克城市的空镜头"
+
+## AI Response
+
+**Target Model:** Veo
+**Type:** [VIDEO]
+
+**Optimized Prompt:**
+Aerial drone shot establishing a futuristic cyberpunk city at night. The camera flies forward and slowly tilts down (Tilt Down) to reveal neon-lit skyscrapers and flying vehicles weaving through the fog. Cinematic lighting, HDR, 4k resolution, smooth motion.
+
+**Design Rationale:**
+识别为 Veo 模型，因此使用了 "Aerial drone shot" 和明确的运镜指令 "Tilt Down" 来发挥其镜头控制优势。
+
+---
+
+## User Input
+
+"Nano Banana, 一个写着'OpenAI'的霓虹灯牌子"
+
+## AI Response
+
+**Target Model:** Nano Banana (Gemini)
+**Type:** [IMAGE]
+
+**Optimized Prompt:**
+A cinematic photo of a glowing neon sign mounted on a brick wall in a dim alleyway. The sign clearly spells out the word "OpenAI" in bright blue cursive letters. Rain puddles on the ground reflect the light. Photorealistic, 8k.
+
+**Design Rationale:**
+识别为 Nano Banana (Gemini)，因此使用了自然语言全句描述，并特别强调了文字渲染指令 "clearly spells out..."。

package/knowledge/skills/webapp-testing.md

@@ -1,111 +1,111 @@
----
-id: "webapp-testing"
-title: "Web Application Testing"
-category: "dev-tools"
-tags: ["web application testing", "common pitfall", "best practices", "reference files"]
-triggers: []
-dependencies: []
-source: "E:/Bobo's Coding cache/.claude/skills/webapp-testing"
----
-
----
-name: webapp-testing
-description: Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
-license: Complete terms in LICENSE.txt
----
-
-# Web Application Testing
-
-To test local web applications, write native Python Playwright scripts.
-
-**Helper Scripts Available**:
-
-- `scripts/with_server.py` - Manages server lifecycle (supports multiple servers)
-
-**Always run scripts with `--help` first** to see usage. DO NOT read the source until you try running the script first and find that a customized solution is abslutely necessary. These scripts can be very large and thus pollute your context window. They exist to be called directly as black-box scripts rather than ingested into your context window.
-
-## Decision Tree: Choosing Your Approach
-
-```
-User task → Is it static HTML?
-    ├─ Yes → Read HTML file directly to identify selectors
-    │         ├─ Success → Write Playwright script using selectors
-    │         └─ Fails/Incomplete → Treat as dynamic (below)
-    │
-    └─ No (dynamic webapp) → Is the server already running?
-        ├─ No → Run: python scripts/with_server.py --help
-        │        Then use the helper + write simplified Playwright script
-        │
-        └─ Yes → Reconnaissance-then-action:
-            1. Navigate and wait for networkidle
-            2. Take screenshot or inspect DOM
-            3. Identify selectors from rendered state
-            4. Execute actions with discovered selectors
-```
-
-## Example: Using with_server.py
-
-To start a server, run `--help` first, then use the helper:
-
-**Single server:**
-
-```bash
-python scripts/with_server.py --server "npm run dev" --port 5173 -- python your_automation.py
-```
-
-**Multiple servers (e.g., backend + frontend):**
-
-```bash
-python scripts/with_server.py \
-  --server "cd backend && python server.py" --port 3000 \
-  --server "cd frontend && npm run dev" --port 5173 \
-  -- python your_automation.py
-```
-
-To create an automation script, include only Playwright logic (servers are managed automatically):
-
-```python
-from playwright.sync_api import sync_playwright
-
-with sync_playwright() as p:
-    browser = p.chromium.launch(headless=True) # Always launch chromium in headless mode
-    page = browser.new_page()
-    page.goto('http://localhost:5173') # Server already running and ready
-    page.wait_for_load_state('networkidle') # CRITICAL: Wait for JS to execute
-    # ... your automation logic
-    browser.close()
-```
-
-## Reconnaissance-Then-Action Pattern
-
-1. **Inspect rendered DOM**:
-
-   ```python
-   page.screenshot(path='/tmp/inspect.png', full_page=True)
-   content = page.content()
-   page.locator('button').all()
-   ```
-
-2. **Identify selectors** from inspection results
-
-3. **Execute actions** using discovered selectors
-
-## Common Pitfall
-
-❌ **Don't** inspect the DOM before waiting for `networkidle` on dynamic apps
-✅ **Do** wait for `page.wait_for_load_state('networkidle')` before inspection
-
-## Best Practices
-
-- **Use bundled scripts as black boxes** - To accomplish a task, consider whether one of the scripts available in `scripts/` can help. These scripts handle common, complex workflows reliably without cluttering the context window. Use `--help` to see usage, then invoke directly.
-- Use `sync_playwright()` for synchronous scripts
-- Always close the browser when done
-- Use descriptive selectors: `text=`, `role=`, CSS selectors, or IDs
-- Add appropriate waits: `page.wait_for_selector()` or `page.wait_for_timeout()`
-
-## Reference Files
-
-- **examples/** - Examples showing common patterns:
-  - `element_discovery.py` - Discovering buttons, links, and inputs on a page
-  - `static_html_automation.py` - Using file:// URLs for local HTML
-  - `console_logging.py` - Capturing console logs during automation
+---
+id: "webapp-testing"
+title: "Web Application Testing"
+category: "dev-tools"
+tags: ["web application testing", "common pitfall", "best practices", "reference files"]
+triggers: []
+dependencies: []
+source: "E:/Bobo's Coding cache/.claude/skills/webapp-testing"
+---
+
+---
+name: webapp-testing
+description: Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
+license: Complete terms in LICENSE.txt
+---
+
+# Web Application Testing
+
+To test local web applications, write native Python Playwright scripts.
+
+**Helper Scripts Available**:
+
+- `scripts/with_server.py` - Manages server lifecycle (supports multiple servers)
+
+**Always run scripts with `--help` first** to see usage. DO NOT read the source until you try running the script first and find that a customized solution is abslutely necessary. These scripts can be very large and thus pollute your context window. They exist to be called directly as black-box scripts rather than ingested into your context window.
+
+## Decision Tree: Choosing Your Approach
+
+```
+User task → Is it static HTML?
+    ├─ Yes → Read HTML file directly to identify selectors
+    │         ├─ Success → Write Playwright script using selectors
+    │         └─ Fails/Incomplete → Treat as dynamic (below)
+    │
+    └─ No (dynamic webapp) → Is the server already running?
+        ├─ No → Run: python scripts/with_server.py --help
+        │        Then use the helper + write simplified Playwright script
+        │
+        └─ Yes → Reconnaissance-then-action:
+            1. Navigate and wait for networkidle
+            2. Take screenshot or inspect DOM
+            3. Identify selectors from rendered state
+            4. Execute actions with discovered selectors
+```
+
+## Example: Using with_server.py
+
+To start a server, run `--help` first, then use the helper:
+
+**Single server:**
+
+```bash
+python scripts/with_server.py --server "npm run dev" --port 5173 -- python your_automation.py
+```
+
+**Multiple servers (e.g., backend + frontend):**
+
+```bash
+python scripts/with_server.py \
+  --server "cd backend && python server.py" --port 3000 \
+  --server "cd frontend && npm run dev" --port 5173 \
+  -- python your_automation.py
+```
+
+To create an automation script, include only Playwright logic (servers are managed automatically):
+
+```python
+from playwright.sync_api import sync_playwright
+
+with sync_playwright() as p:
+    browser = p.chromium.launch(headless=True) # Always launch chromium in headless mode
+    page = browser.new_page()
+    page.goto('http://localhost:5173') # Server already running and ready
+    page.wait_for_load_state('networkidle') # CRITICAL: Wait for JS to execute
+    # ... your automation logic
+    browser.close()
+```
+
+## Reconnaissance-Then-Action Pattern
+
+1. **Inspect rendered DOM**:
+
+   ```python
+   page.screenshot(path='/tmp/inspect.png', full_page=True)
+   content = page.content()
+   page.locator('button').all()
+   ```
+
+2. **Identify selectors** from inspection results
+
+3. **Execute actions** using discovered selectors
+
+## Common Pitfall
+
+❌ **Don't** inspect the DOM before waiting for `networkidle` on dynamic apps
+✅ **Do** wait for `page.wait_for_load_state('networkidle')` before inspection
+
+## Best Practices
+
+- **Use bundled scripts as black boxes** - To accomplish a task, consider whether one of the scripts available in `scripts/` can help. These scripts handle common, complex workflows reliably without cluttering the context window. Use `--help` to see usage, then invoke directly.
+- Use `sync_playwright()` for synchronous scripts
+- Always close the browser when done
+- Use descriptive selectors: `text=`, `role=`, CSS selectors, or IDs
+- Add appropriate waits: `page.wait_for_selector()` or `page.wait_for_timeout()`
+
+## Reference Files
+
+- **examples/** - Examples showing common patterns:
+  - `element_discovery.py` - Discovering buttons, links, and inputs on a page
+  - `static_html_automation.py` - Using file:// URLs for local HTML
+  - `console_logging.py` - Capturing console logs during automation