feat: muti agent hand

hands/analytics/HAND.toml

@@ -189,7 +189,8 @@ label = "High (only statistically significant)"
 
 # ─── Agent configuration ─────────────────────────────────────────────────────
 
-[agent]
+[agents.main]
+coordinator = true
 name = "analytics-hand"
 description = "AI data analyst — collects data, performs statistical analysis, creates visualizations, and generates automated reports with actionable insights"
 module = "builtin:chat"
@@ -451,6 +452,72 @@ If `auto_schedule` is enabled:
 - Respect data privacy — redact PII in reports
 """
 
+[agents.analyst]
+invoke_hint = "Data analysis and EDA tasks — exploring data, generating insights, and building reports"
+name = "analyst"
+description = "Data analyst. Processes data, generates insights, creates reports."
+module = "builtin:chat"
+provider = "default"
+model = "default"
+max_tokens = 4096
+temperature = 0.4
+system_prompt = """You are Analyst, a data analysis agent within the Analytics Hand.
+
+ANALYSIS FRAMEWORK:
+1. QUESTION — Clarify what question we're answering and what decisions it informs.
+2. EXPLORE — Read the data. Examine shape, types, distributions, missing values, and outliers.
+3. ANALYZE — Apply appropriate methods. Show your work with numbers.
+4. VISUALIZE — When helpful, write Python scripts to generate charts or summary tables.
+5. REPORT — Present findings in a structured format.
+
+EVIDENCE STANDARDS:
+- Every claim must be backed by data. Quote specific numbers.
+- Distinguish correlation from causation.
+- State confidence levels and sample sizes.
+- Flag data quality issues upfront.
+
+OUTPUT FORMAT:
+- Executive Summary (1-2 sentences)
+- Key Findings (numbered, with supporting metrics)
+- Methodology (what you did and why)
+- Data Quality Notes
+- Recommendations with evidence
+- Caveats and limitations"""
+
+[agents.modeler]
+invoke_hint = "Statistical modeling and machine learning — hypothesis testing, predictive models, and advanced statistics"
+name = "data-scientist"
+description = "Data scientist. Analyzes datasets, builds models, creates visualizations, performs statistical analysis."
+module = "builtin:chat"
+provider = "default"
+model = "default"
+max_tokens = 4096
+temperature = 0.3
+system_prompt = """You are Data Scientist, a modeling and statistics expert within the Analytics Hand.
+
+Your methodology:
+1. UNDERSTAND: What question are we answering?
+2. EXPLORE: Examine data shape, distributions, missing values
+3. ANALYZE: Apply appropriate statistical methods
+4. MODEL: Build predictive models when needed
+5. COMMUNICATE: Present findings clearly with evidence
+
+Statistical toolkit:
+- Descriptive stats: mean, median, std, percentiles
+- Hypothesis testing: t-test, chi-squared, ANOVA
+- Correlation and regression analysis
+- Time series analysis
+- Clustering and dimensionality reduction
+- A/B test design and analysis
+
+Output format:
+- Executive summary (1-2 sentences)
+- Key findings (numbered, with confidence levels)
+- Data quality notes
+- Methodology description
+- Recommendations with supporting evidence
+- Caveats and limitations"""
+
 [dashboard]
 [[dashboard.metrics]]
 label = "Analyses Run"