add-golden（添加金色）

Add to Golden Dataset

Multi-agent curation workflow with quality score explanations, bias detection, and version tracking.

Quick Start

/add-golden https://example.com/article
/add-golden https://arxiv.org/abs/2312.xxxxx

Task Management (CC 2.1.16)

# Create main curation task
TaskCreate(
  subject="Add to golden dataset: {url}",
  description="Multi-agent curation with quality explanation",
  activeForm="Curating document"
)

# Create subtasks for 9-phase process
phases = ["Fetch content", "Run quality analysis", "Explain scores",
          "Check bias", "Check diversity", "Validate", "Get approval",
          "Write to dataset", "Update version"]
for phase in phases:
    TaskCreate(subject=phase, activeForm=f"{phase}ing")

Workflow Overview

Phase 1-2: Input and Extraction

Detect content type: article, tutorial, documentation, research_paper.

Extract: title, sections, code blocks, key terms, metadata (author, date).

Phase 3: Parallel Quality Analysis (4 Agents)

Launch ALL agents in ONE message with run_in_background=True.

See Quality Scoring for detailed criteria.

Phase 4: Quality Explanation

Each dimension gets WHY explanation:

### Accuracy: [N.NN]/1.0
**Why this score:**
- [Specific reason with evidence]
**What would improve it:**
- [Specific improvement]

Phase 5: Bias Detection

See Bias Detection Guide for patterns.

Check for:

• Technology bias (favors specific tools)
• Recency bias (ignores LTS versions)
• Complexity bias (assumed knowledge)
• Vendor bias (promotes products)
• Geographic/cultural bias

Phase 6: Diversity Dashboard

Track dataset balance across:

• Domain distribution (AI/ML, Backend, Frontend, DevOps, Security)
• Difficulty distribution (trivial, easy, medium, hard, adversarial)

Impact assessment: Does new document improve or worsen diversity?

Phase 7: Validation

• URL validation (no placeholders)
• Schema validation (required fields)
• Duplicate check (>80% similarity)
• Quality gates (min sections, content length)

Phase 8: Silver-to-Gold Workflow

See Silver-Gold Promotion for criteria.

Promotion criteria: 7+ days in silver, quality >= 0.75, no negative feedback.

Phase 9: Version Tracking

{
  "version": "1.2.3",
  "change_type": "ADD|UPDATE|REMOVE|PROMOTE",
  "document_id": "doc-123",
  "quality_score": 0.82,
  "rollback_available": true
}

Quality Scoring

Formula: quality_score = accuracy*0.25 + coherence*0.20 + depth*0.25 + relevance*0.30

Key Decisions

Related Skills

• golden-dataset-validation - Validate existing datasets
• llm-evaluation - LLM output evaluation patterns
• test-data-management - Test data strategies

Version: 2.0.0 (January 2026)