القائمة
Deep reflection with web search — Brave/Perplexica pipeline fed into Qwen3.5-35B thinking mode for grounded, well-reasoned answers.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
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.
CSV analysis via 2-pass SOTA orchestrator (score 54/55 on 7 CSVs). Statistics, data profiling, visualizations, insights.
Multi-perspective reasoning (advocate/critic/synthesizer). Three modes - general, --code for architecture decisions, --medical for EBM clinical analysis.
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 | deepthink |
| description | Deep reflection with web search — Brave/Perplexica pipeline fed into Qwen3.5-35B thinking mode for grounded, well-reasoned answers. |
| trigger_patterns | ["réfléchis","analyse approfondie","deep think","pense longuement","explique en détail"] |
| tools_required | ["exec","search_router","llm_qwen35"] |
| examples | ["Pourquoi la fusion froide est-elle rejetée par la communauté scientifique ?","Comment fonctionne réellement la mémoire Engram dans Chimère ?","Quels sont les trade-offs de Mamba-2 vs Transformer pour l'inférence mobile ?"] |
| model | qwen3.5-35b-a3b |
| execution | {"command":"/home/remondiere/.openclaw/bin/think.sh '$args'","timeout_ms":300000,"arg_mode":"raw"} |
Pipeline : recherche web (Brave/Perplexica via search_router) → inférence Qwen3.5-35B-A3B (thinking natif).
enable_thinking=true