Menu
CSV analysis via 2-pass SOTA orchestrator (score 54/55 on 7 CSVs). Statistics, data profiling, visualizations, insights.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Code architecture design with web-informed debate between Architect and Reviewer agents — produces ASCII diagrams, justified stack, patterns (SOLID/DDD/CQRS), phased implementation plan.
Multi-turn brainstorming session with RAG, domain profiles (code/tech/btp/cyber/finance), Claude Opus or local Qwen3.5 backend.
Multi-perspective reasoning (advocate/critic/synthesizer). Three modes - general, --code for architecture decisions, --medical for EBM clinical analysis.
Deep reflection with web search — Brave/Perplexica pipeline fed into Qwen3.5-35B thinking mode for grounded, well-reasoned answers.
Threat intelligence analysis of IoCs (IPs, domains, hashes, URLs) via CyberBro (33 engines including Shodan/AbuseIPDB/VirusTotal) + Brave Search enrichment.
MCP CLI — list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.
| name | datascience |
| description | CSV analysis via 2-pass SOTA orchestrator (score 54/55 on 7 CSVs). Statistics, data profiling, visualizations, insights. |
| trigger_patterns | ["analyse csv","analyser fichier",".csv","data analysis","statistiques"] |
| tools_required | ["exec","pandas","llm_qwen35"] |
| examples | ["/chemin/vers/fichier.csv","/tmp/patients.csv","~/data/sales_2026.csv"] |
| model | qwen3.5-35b-a3b |
| execution | {"command":"/home/remondiere/.openclaw/bin/analyze_csv.sh '$args'","timeout_ms":360000,"arg_mode":"raw"} |
Dispatch direct vers analyze_csv.sh : orchestrateur 2-pass, score 54/55 sur 7 CSVs de référence.
Bypasse le modèle principal : le gateway appelle exec directement.
