Menú
SkillsMP ha recopilado 12 skills de AIdevsmartdata/chimere-odo. Abre una skill para revisar su origen y sus detalles.
Mostrando 12 de 12 skills recopiladas.
Code architecture design with web-informed debate between Architect and Reviewer agents — produces ASCII diagrams, justified stack, patterns (SOLID/DDD/CQRS), phased implementation plan.
Idioma del texto original: Varios idiomas
Multi-turn brainstorming session with RAG, domain profiles (code/tech/btp/cyber/finance), Claude Opus or local Qwen3.5 backend.
Idioma del texto original: Sin determinar
CSV analysis via 2-pass SOTA orchestrator (score 54/55 on 7 CSVs). Statistics, data profiling, visualizations, insights.
Idioma del texto original: francés
Multi-perspective reasoning (advocate/critic/synthesizer). Three modes - general, --code for architecture decisions, --medical for EBM clinical analysis.
Idioma del texto original: francés
Deep reflection with web search — Brave/Perplexica pipeline fed into Qwen3.5-35B thinking mode for grounded, well-reasoned answers.
Idioma del texto original: francés
Threat intelligence analysis of IoCs (IPs, domains, hashes, URLs) via CyberBro (33 engines including Shodan/AbuseIPDB/VirusTotal) + Brave Search enrichment.
Idioma del texto original: inglés
MCP CLI — list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.
Idioma del texto original: francés
Launch, monitor, and manage ML training jobs on GPU — safe process handling, DataLoader-aware kill logic, VRAM/NaN/alpha alerts, QuickChart visualizations.
Idioma del texto original: inglés
Unified project management — workspace creation, file ops, code execution, git, phase workflow (analyse→design→code→test→done). Smart routing via Qwen3.5 for free-form requests.
Idioma del texto original: Sin determinar
Deep web research with structured report — from quick 30s summary to ultra-exhaustive 50min analysis. SearXNG + Brave + ChromaDB + academic sources.
Idioma del texto original: inglés
Intelligent code review agent — security (OWASP Top 10), best practices, test coverage, consistency. Auto-detects stack (Django/FastAPI/Node/Rust) and adapts checklists.
Idioma del texto original: Varios idiomas
Self-consistency voting (N=3 samples) to reduce Qwen3.5 hallucinations. ~46% hallucination reduction per ACL 2025 research.
Idioma del texto original: francés