A production-grade Claude Code configuration: skills, agents, hooks, rules, and permissions working as a system, not as isolated features. Companion repo for the article: "I Turned Claude Code Into an Operating System. Here's the Blueprint."
@aedelonCRITICAL SAFETY SKILL — Verify ALL technical claims, API signatures, library methods, code behavior, and factual statements…
@aedelonMulti-agent brainstorming and strategic thinking on any complex topic. Explores the subject deeply, then spawns specialized…
@aedelonReference patterns for REST APIs, pytest/vitest testing, Docker multi-stage builds, GitHub Actions CI/CD, PostgreSQL, TypeScript…
@aedelonShip workflow: review changes, generate conventional commit messages, push, and create PRs. MUST BE USED when user says:…
@aedelonDebug errors systematically by searching first, then analyzing, then proposing verified solutions. MUST BE USED when user…
@aedelonConduct rigorous research with proper citations (DOI, arXiv, PMID) and source triangulation. MUST BE USED when user asks: "what…
@aedelonExpert finance personnelle, investissement, crypto, fiscalité belge (IPP, TOB, succession, épargne-pension, Branche 21/23). MUST…
@aedelonExpert Midjourney V7/Niji 7: prompts, parametres, references (--oref/--sref/--cref), editeur, video, moderation, styles…
@aedelonExpert prompt engineering: chain-of-thought, few-shot, system prompts, évaluation de prompts, optimisation LLM. MUST BE USED when…
@aedelonRecherche académique multi-sources: revues de littérature, synthèse cross-domain, citations DOI/arXiv/PMID. AI/ML, biologie,…
@aedelon© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic
