Instructions file
Instructions for swDomass/AI_orchestrator, covering claude.md, obsidian-projektdoku, project, commands and run all tests (1800 tests, 95 s).
5 15d ago C 6,500 tokens
original MIT
brainstorm
02Skill Claude CodeCodex
Multi-persona Round-Table mit domain-aware Personas (LLM wählt 4–6 themenspezifische Rollen); iterative Cross-Pollination bis TF-IDF-Konvergenz; Synthesizer ranked Top-N mit Pro/Contra.
5 15d ago A 53 tokens
original MIT
Skill Claude CodeCodex
Radical-honesty architectural review — questions code, methodology, design, and operational fitness.
5 15d ago A 21 tokens
original MIT
Skill Claude CodeCodex
Multi-agent deep security audit — 6 expert personas (pentester, architect, code auditor, supply chain, data privacy, forensics) + CISO synthesis + optional fix implementation.
5 15d ago A 41 tokens
original MIT
dev-loop
05Skill Claude CodeCodex
Research → Execute → Dual-Review Loop (Code Quality + Issue Resolution) bis beide Reviews bestanden.
5 15d ago A 22 tokens
original MIT
Skill Claude CodeCodex
Cross-Domain Know-How-Transfer — findet kreative Anwendungen von Vault-Expertise in anderen Branchen.
5 15d ago A 23 tokens
original MIT
research-qa
07Skill Claude CodeCodex
Deep Research + Fragen-Katalog vor Implementierungsbeginn.
5 15d ago A 14 tokens
original MIT
review-loop
08Skill Claude CodeCodex
Iterative code review — fix all P1/P2/P3 findings until clean.
5 15d ago A 19 tokens
original MIT
Skill Claude CodeCodex
Security audit + fix — scans for hardcoded secrets, injection vectors, path traversal, input validation gaps, then implements all fixes.
5 15d ago A 29 tokens
original MIT
test-loop
10Skill Claude CodeCodex
Run tests, fix failures, re-run until all tests pass.
5 15d ago A 15 tokens
original MIT