gkt-node 3.3.0

package/assets/.agent/skills/crewai/SKILL.md

@@ -0,0 +1,243 @@
+---
+name: crewai
+description: "Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative AI agent teams. Use when: crewai, multi-agent team, agent roles, crew of agents, role-based agents."
+source: vibeship-spawner-skills (Apache 2.0)
+---
+
+# CrewAI
+
+**Role**: CrewAI Multi-Agent Architect
+
+You are an expert in designing collaborative AI agent teams with CrewAI. You think
+in terms of roles, responsibilities, and delegation. You design clear agent personas
+with specific expertise, create well-defined tasks with expected outputs, and
+orchestrate crews for optimal collaboration. You know when to use sequential vs
+hierarchical processes.
+
+## Capabilities
+
+- Agent definitions (role, goal, backstory)
+- Task design and dependencies
+- Crew orchestration
+- Process types (sequential, hierarchical)
+- Memory configuration
+- Tool integration
+- Flows for complex workflows
+
+## Requirements
+
+- Python 3.10+
+- crewai package
+- LLM API access
+
+## Patterns
+
+### Basic Crew with YAML Config
+
+Define agents and tasks in YAML (recommended)
+
+**When to use**: Any CrewAI project
+
+```python
+# config/agents.yaml
+researcher:
+  role: "Senior Research Analyst"
+  goal: "Find comprehensive, accurate information on {topic}"
+  backstory: |
+    You are an expert researcher with years of experience
+    in gathering and analyzing information. You're known
+    for your thorough and accurate research.
+  tools:
+    - SerperDevTool
+    - WebsiteSearchTool
+  verbose: true
+
+writer:
+  role: "Content Writer"
+  goal: "Create engaging, well-structured content"
+  backstory: |
+    You are a skilled writer who transforms research
+    into compelling narratives. You focus on clarity
+    and engagement.
+  verbose: true
+
+# config/tasks.yaml
+research_task:
+  description: |
+    Research the topic: {topic}
+
+    Focus on:
+    1. Key facts and statistics
+    2. Recent developments
+    3. Expert opinions
+    4. Contrarian viewpoints
+
+    Be thorough and cite sources.
+  agent: researcher
+  expected_output: |
+    A comprehensive research report with:
+    - Executive summary
+    - Key findings (bulleted)
+    - Sources cited
+
+writing_task:
+  description: |
+    Using the research provided, write an article about {topic}.
+
+    Requirements:
+    - 800-1000 words
+    - Engaging introduction
+    - Clear structure with headers
+    - Actionable conclusion
+  agent: writer
+  expected_output: "A polished article ready for publication"
+  context:
+    - research_task  # Uses output from research
+
+# crew.py
+from crewai import Agent, Task, Crew, Process
+from crewai.project import CrewBase, agent, task, crew
+
+@CrewBase
+class ContentCrew:
+    agents_config = 'config/agents.yaml'
+    tasks_config = 'config/tasks.yaml'
+
+    @agent
+    def researcher(self) -> Agent:
+        return Agent(config=self.agents_config['researcher'])
+
+    @agent
+    def writer(self) -> Agent:
+        return Agent(config=self.agents_config['writer'])
+
+    @task
+    def research_task(self) -> Task:
+        return Task(config=self.tasks_config['research_task'])
+
+    @task
+    def writing_task(self) -> Task:
+        return Task(config
+```
+
+### Hierarchical Process
+
+Manager agent delegates to workers
+
+**When to use**: Complex tasks needing coordination
+
+```python
+from crewai import Crew, Process
+
+# Define specialized agents
+researcher = Agent(
+    role="Research Specialist",
+    goal="Find accurate information",
+    backstory="Expert researcher..."
+)
+
+analyst = Agent(
+    role="Data Analyst",
+    goal="Analyze and interpret data",
+    backstory="Expert analyst..."
+)
+
+writer = Agent(
+    role="Content Writer",
+    goal="Create engaging content",
+    backstory="Expert writer..."
+)
+
+# Hierarchical crew - manager coordinates
+crew = Crew(
+    agents=[researcher, analyst, writer],
+    tasks=[research_task, analysis_task, writing_task],
+    process=Process.hierarchical,
+    manager_llm=ChatOpenAI(model="gpt-4o"),  # Manager model
+    verbose=True
+)
+
+# Manager decides:
+# - Which agent handles which task
+# - When to delegate
+# - How to combine results
+
+result = crew.kickoff()
+```
+
+### Planning Feature
+
+Generate execution plan before running
+
+**When to use**: Complex workflows needing structure
+
+```python
+from crewai import Crew, Process
+
+# Enable planning
+crew = Crew(
+    agents=[researcher, writer, reviewer],
+    tasks=[research, write, review],
+    process=Process.sequential,
+    planning=True,  # Enable planning
+    planning_llm=ChatOpenAI(model="gpt-4o")  # Planner model
+)
+
+# With planning enabled:
+# 1. CrewAI generates step-by-step plan
+# 2. Plan is injected into each task
+# 3. Agents see overall structure
+# 4. More consistent results
+
+result = crew.kickoff()
+
+# Access the plan
+print(crew.plan)
+```
+
+## Anti-Patterns
+
+### ❌ Vague Agent Roles
+
+**Why bad**: Agent doesn't know its specialty.
+Overlapping responsibilities.
+Poor task delegation.
+
+**Instead**: Be specific:
+- "Senior React Developer" not "Developer"
+- "Financial Analyst specializing in crypto" not "Analyst"
+Include specific skills in backstory.
+
+### ❌ Missing Expected Outputs
+
+**Why bad**: Agent doesn't know done criteria.
+Inconsistent outputs.
+Hard to chain tasks.
+
+**Instead**: Always specify expected_output:
+expected_output: |
+  A JSON object with:
+  - summary: string (100 words max)
+  - key_points: list of strings
+  - confidence: float 0-1
+
+### ❌ Too Many Agents
+
+**Why bad**: Coordination overhead.
+Inconsistent communication.
+Slower execution.
+
+**Instead**: 3-5 agents with clear roles.
+One agent can handle multiple related tasks.
+Use tools instead of agents for simple actions.
+
+## Limitations
+
+- Python-only
+- Best for structured workflows
+- Can be verbose for simple cases
+- Flows are newer feature
+
+## Related Skills
+
+Works well with: `langgraph`, `autonomous-agents`, `langfuse`, `structured-output`

package/assets/.agent/skills/daily-news-report/SKILL.md

@@ -0,0 +1,356 @@
+---
+name: daily-news-report
+description: Scrapes content based on a preset URL list, filters high-quality technical information, and generates daily Markdown reports.
+argument-hint: [optional: date]
+disable-model-invocation: false
+user-invocable: true
+allowed-tools: Task, WebFetch, Read, Write, Bash(mkdir*), Bash(date*), Bash(ls*), mcp__chrome-devtools__*
+---
+
+# Daily News Report v3.0
+
+> **Architecture Upgrade**: Main Agent Orchestration + SubAgent Execution + Browser Scraping + Smart Caching
+
+## Core Architecture
+
+```
+┌─────────────────────────────────────────────────────────────────────┐
+│                        Main Agent (Orchestrator)                    │
+│  Role: Scheduling, Monitoring, Evaluation, Decision, Aggregation    │
+├─────────────────────────────────────────────────────────────────────┤
+│                                                                      │
+│   ┌─────────────┐    ┌─────────────┐    ┌─────────────┐    ┌─────────────┐     │
+│   │ 1. Init     │ → │ 2. Dispatch │ → │ 3. Monitor  │ → │ 4. Evaluate │     │
+│   │ Read Config │    │ Assign Tasks│    │ Collect Res │    │ Filter/Sort │     │
+│   └─────────────┘    └─────────────┘    └─────────────┘    └─────────────┘     │
+│         │                  │                  │                  │           │
+│         ▼                  ▼                  ▼                  ▼           │
+│   ┌─────────────┐    ┌─────────────┐    ┌─────────────┐    ┌─────────────┐     │
+│   │ 5. Decision │ ← │ Enough 20?  │    │ 6. Generate │ → │ 7. Update   │     │
+│   │ Cont/Stop   │    │ Y/N         │    │ Report File │    │ Cache Stats │     │
+│   └─────────────┘    └─────────────┘    └─────────────┘    └─────────────┘     │
+│                                                                      │
+└──────────────────────────────────────────────────────────────────────┘
+         ↓ Dispatch                          ↑ Return Results
+┌─────────────────────────────────────────────────────────────────────┐
+│                        SubAgent Execution Layer                      │
+├─────────────────────────────────────────────────────────────────────┤
+│                                                                      │
+│   ┌─────────────┐   ┌─────────────┐   ┌─────────────┐              │
+│   │ Worker A    │   │ Worker B    │   │ Browser     │              │
+│   │ (WebFetch)  │   │ (WebFetch)  │   │ (Headless)  │              │
+│   │ Tier1 Batch │   │ Tier2 Batch │   │ JS Render   │              │
+│   └─────────────┘   └─────────────┘   └─────────────┘              │
+│         ↓                 ↓                 ↓                        │
+│   ┌─────────────────────────────────────────────────────────────┐   │
+│   │                    Structured Result Return                 │   │
+│   │  { status, data: [...], errors: [...], metadata: {...} }    │   │
+│   └─────────────────────────────────────────────────────────────┘   │
+│                                                                      │
+└─────────────────────────────────────────────────────────────────────┘
+```
+
+## Configuration Files
+
+This skill uses the following configuration files:
+
+| File | Purpose |
+|------|---------|
+| `sources.json` | Source configuration, priorities, scrape methods |
+| `cache.json` | Cached data, historical stats, deduplication fingerprints |
+
+## Execution Process Details
+
+### Phase 1: Initialization
+
+```yaml
+Steps:
+  1. Determine date (user argument or current date)
+  2. Read sources.json for source configurations
+  3. Read cache.json for historical data
+  4. Create output directory NewsReport/
+  5. Check if a partial report exists for today (append mode)
+```
+
+### Phase 2: Dispatch SubAgents
+
+**Strategy**: Parallel dispatch, batch execution, early stopping mechanism
+
+```yaml
+Wave 1 (Parallel):
+  - Worker A: Tier1 Batch A (HN, HuggingFace Papers)
+  - Worker B: Tier1 Batch B (OneUsefulThing, Paul Graham)
+
+Wait for results → Evaluate count
+
+If < 15 high-quality items:
+  Wave 2 (Parallel):
+    - Worker C: Tier2 Batch A (James Clear, FS Blog)
+    - Worker D: Tier2 Batch B (HackerNoon, Scott Young)
+
+If still < 20 items:
+  Wave 3 (Browser):
+    - Browser Worker: ProductHunt, Latent Space (Require JS rendering)
+```
+
+### Phase 3: SubAgent Task Format
+
+Task format received by each SubAgent:
+
+```yaml
+task: fetch_and_extract
+sources:
+  - id: hn
+    url: https://news.ycombinator.com
+    extract: top_10
+  - id: hf_papers
+    url: https://huggingface.co/papers
+    extract: top_voted
+
+output_schema:
+  items:
+    - source_id: string      # Source Identifier
+      title: string          # Title
+      summary: string        # 2-4 sentence summary
+      key_points: string[]   # Max 3 key points
+      url: string            # Original URL
+      keywords: string[]     # Keywords
+      quality_score: 1-5     # Quality Score
+
+constraints:
+  filter: "Cutting-edge Tech/Deep Tech/Productivity/Practical Info"
+  exclude: "General Science/Marketing Puff/Overly Academic/Job Posts"
+  max_items_per_source: 10
+  skip_on_error: true
+
+return_format: JSON
+```
+
+### Phase 4: Main Agent Monitoring & Feedback
+
+Main Agent Responsibilities:
+
+```yaml
+Monitoring:
+  - Check SubAgent return status (success/partial/failed)
+  - Count collected items
+  - Record success rate per source
+
+Feedback Loop:
+  - If a SubAgent fails, decide whether to retry or skip
+  - If a source fails persistently, mark as disabled
+  - Dynamically adjust source selection for subsequent batches
+
+Decision:
+  - Items >= 25 AND HighQuality >= 20 → Stop scraping
+  - Items < 15 → Continue to next batch
+  - All batches done but < 20 → Generate with available content (Quality over Quantity)
+```
+
+### Phase 5: Evaluation & Filtering
+
+```yaml
+Deduplication:
+  - Exact URL match
+  - Title similarity (>80% considered duplicate)
+  - Check cache.json to avoid history duplicates
+
+Score Calibration:
+  - Unify scoring standards across SubAgents
+  - Adjust weights based on source credibility
+  - Bonus points for manually curated high-quality sources
+
+Sorting:
+  - Descending order by quality_score
+  - Sort by source priority if scores are equal
+  - Take Top 20
+```
+
+### Phase 6: Browser Scraping (MCP Chrome DevTools)
+
+For pages requiring JS rendering, use a headless browser:
+
+```yaml
+Process:
+  1. Call mcp__chrome-devtools__new_page to open page
+  2. Call mcp__chrome-devtools__wait_for to wait for content load
+  3. Call mcp__chrome-devtools__take_snapshot to get page structure
+  4. Parse snapshot to extract required content
+  5. Call mcp__chrome-devtools__close_page to close page
+
+Applicable Scenarios:
+  - ProductHunt (403 on WebFetch)
+  - Latent Space (Substack JS rendering)
+  - Other SPA applications
+```
+
+### Phase 7: Generate Report
+
+```yaml
+Output:
+  - Directory: NewsReport/
+  - Filename: YYYY-MM-DD-news-report.md
+  - Format: Standard Markdown
+
+Content Structure:
+  - Title + Date
+  - Statistical Summary (Source count, items collected)
+  - 20 High-Quality Items (Template based)
+  - Generation Info (Version, Timestamps)
+```
+
+### Phase 8: Update Cache
+
+```yaml
+Update cache.json:
+  - last_run: Record this run info
+  - source_stats: Update stats per source
+  - url_cache: Add processed URLs
+  - content_hashes: Add content fingerprints
+  - article_history: Record included articles
+```
+
+## SubAgent Call Examples
+
+### Using general-purpose Agent
+
+Since custom agents require session restart to be discovered, use general-purpose and inject worker prompts:
+
+```
+Task Call:
+  subagent_type: general-purpose
+  model: haiku
+  prompt: |
+    You are a stateless execution unit. Only do the assigned task and return structured JSON.
+
+    Task: Scrape the following URLs and extract content
+
+    URLs:
+    - https://news.ycombinator.com (Extract Top 10)
+    - https://huggingface.co/papers (Extract top voted papers)
+
+    Output Format:
+    {
+      "status": "success" | "partial" | "failed",
+      "data": [
+        {
+          "source_id": "hn",
+          "title": "...",
+          "summary": "...",
+          "key_points": ["...", "...", "..."],
+          "url": "...",
+          "keywords": ["...", "..."],
+          "quality_score": 4
+        }
+      ],
+      "errors": [],
+      "metadata": { "processed": 2, "failed": 0 }
+    }
+
+    Filter Criteria:
+    - Keep: Cutting-edge Tech/Deep Tech/Productivity/Practical Info
+    - Exclude: General Science/Marketing Puff/Overly Academic/Job Posts
+
+    Return JSON directly, no explanation.
+```
+
+### Using worker Agent (Requires session restart)
+
+```
+Task Call:
+  subagent_type: worker
+  prompt: |
+    task: fetch_and_extract
+    input:
+      urls:
+        - https://news.ycombinator.com
+        - https://huggingface.co/papers
+    output_schema:
+      - source_id: string
+      - title: string
+      - summary: string
+      - key_points: string[]
+      - url: string
+      - keywords: string[]
+      - quality_score: 1-5
+    constraints:
+      filter: Cutting-edge Tech/Deep Tech/Productivity/Practical Info
+      exclude: General Science/Marketing Puff/Overly Academic
+```
+
+## Output Template
+
+```markdown
+# Daily News Report (YYYY-MM-DD)
+
+> Curated from N sources today, containing 20 high-quality items
+> Generation Time: X min | Version: v3.0
+>
+> **Warning**: Sub-agent 'worker' not detected. Running in generic mode (Serial Execution). Performance might be degraded.
+
+---
+
+## 1. Title
+
+- **Summary**: 2-4 lines overview
+- **Key Points**:
+  1. Point one
+  2. Point two
+  3. Point three
+- **Source**: [Link](URL)
+- **Keywords**: `keyword1` `keyword2` `keyword3`
+- **Score**: ⭐⭐⭐⭐⭐ (5/5)
+
+---
+
+## 2. Title
+...
+
+---
+
+*Generated by Daily News Report v3.0*
+*Sources: HN, HuggingFace, OneUsefulThing, ...*
+```
+
+## Constraints & Principles
+
+1.  **Quality over Quantity**: Low-quality content does not enter the report.
+2.  **Early Stop**: Stop scraping once 20 high-quality items are reached.
+3.  **Parallel First**: SubAgents in the same batch execute in parallel.
+4.  **Fault Tolerance**: Failure of a single source does not affect the whole process.
+5.  **Cache Reuse**: Avoid re-scraping the same content.
+6.  **Main Agent Control**: All decisions are made by the Main Agent.
+7.  **Fallback Awareness**: Detect sub-agent availability, gracefully degrade if unavailable.
+
+## Expected Performance
+
+| Scenario | Expected Time | Note |
+|---|---|---|
+| Optimal | ~2 mins | Tier1 sufficient, no browser needed |
+| Normal | ~3-4 mins | Requires Tier2 supplement |
+| Browser Needed | ~5-6 mins | Includes JS rendered pages |
+
+## Error Handling
+
+| Error Type | Handling |
+|---|---|
+| SubAgent Timeout | Log error, continue to next |
+| Source 403/404 | Mark disabled, update sources.json |
+| Extraction Failed | Return raw content, Main Agent decides |
+| Browser Crash | Skip source, log entry |
+
+## Compatibility & Fallback
+
+To ensure usability across different Agent environments, the following checks must be performed:
+
+1.  **Environment Check**:
+    -   In Phase 1 initialization, attempt to detect if `worker` sub-agent exists.
+    -   If not exists (or plugin not installed), automatically switch to **Serial Execution Mode**.
+
+2.  **Serial Execution Mode**:
+    -   Do not use parallel block.
+    -   Main Agent executes scraping tasks for each source sequentially.
+    -   Slower, but guarantees basic functionality.
+
+3.  **User Alert**:
+    -   MUST include a clear warning in the generated report header indicating the current degraded mode.

package/assets/.agent/skills/daily-news-report/cache.json

@@ -0,0 +1,41 @@
+{
+  "schema_version": "1.0",
+  "description": "Daily News Report 缓存文件，用于避免重复抓取和跟踪历史表现",
+
+  "last_run": {
+    "date": "2026-01-21",
+    "duration_seconds": 180,
+    "items_collected": 20,
+    "items_published": 20,
+    "sources_used": ["hn", "hf_papers", "james_clear", "fs_blog", "scotthyoung"]
+  },
+
+  "source_stats": {
+    "_comment": "记录每个源的历史表现，用于动态调整优先级",
+    "hn": {
+      "total_fetches": 0,
+      "success_count": 0,
+      "avg_items_per_fetch": 0,
+      "avg_quality_score": 0,
+      "last_fetch": null,
+      "last_success": null
+    }
+  },
+
+  "url_cache": {
+    "_comment": "已处理的 URL 缓存，避免重复收录",
+    "_ttl_hours": 168,
+    "entries": {}
+  },
+
+  "content_hashes": {
+    "_comment": "内容指纹，用于去重",
+    "_ttl_hours": 168,
+    "entries": {}
+  },
+
+  "article_history": {
+    "_comment": "已收录文章的简要记录",
+    "2026-01-21": []
+  }
+}