roberdan-os

Lookup reference for executing a task already decided on — code style per language, test/mock boundaries, API conventions, the local CI sequence before push, merge discipline, how to resolve review comments, repo settings and git hooks. Read it when you are about to push, merge, review, or set up a repo; not before.

Evidence-first done-gate. Refuses to mark work complete without concrete artifacts (commit SHA, PR link, file path, test output) verified empirically. The cardinal principle.

Platform-agnostic ship workflow — local CI gate, commit per phase, push, PR with Summary + Test plan, watch CI, merge-commit only. Honors human gates on main.

Helps figure out WHICH problems are worth solving, not just how to solve them. Orchestrates: problem discovery/validation with users (focus-group) → prioritization (severity×frequency×reachability×fit) → solution stress-test (premortem). TRIGGER: 'is it worth solving X', 'vale la pena risolvere X', 'is this a real problem', 'è un problema vero', 'which problem should I attack', 'quale problema attacco', 'should I build this', 'dovrei costruire questo', 'validate before building', 'validiamo prima di costruire', 'prioritize these problems', 'prioritizza questi problemi', 'is this worth building'. YES upstream of any non-trivial build/investment.

Operate the way Roberto D'Angelo works — total autonomy scoped by evidence-first verification, artifact-per-phase discipline, human confirmation before irreversible actions, and his communication voice for drafting. Use whenever asked to operate "in roberto-mode", when starting a complex multi-step task, when drafting a document/email/reply in his voice, when reasoning through a real decision, or when asked "do you know who I am" / "are you in my context".

Portable "loop kit" — inject durable state, terminal-condition, auto-resume and auto-escalation into any session. Makes the loop reliable without a daemon.

Pre-landing code review — correctness, security, patterns, reuse/simplification. Severity-classified findings with file:line evidence. Read-only; the owner applies fixes.

Keep the 3 systems aligned — Obsidian vault (durable memory), Convergio twin plans, in-repo docs. Anti-drift. Read vault before asking; mechanized by post-task-sync hook.

Simulates a focus group / validation with real users: creates a pool of persona-agents matching the requested profile + a moderator + a consolidator. Validates problems, definitions, hypotheses, apps, features, usability, feedback. Multi-mode (focus group, 1:1 interviews, usability test, micro-survey). TRIGGER: 'validate this hypothesis/idea/feature', 'valida questa ipotesi/idea/feature', 'what do users think', 'cosa ne pensano gli utenti', 'simulate a focus group', 'simula un focus group', 'test the usability', 'testa l'usabilità', 'create an early adopter panel', 'crea un panel di early adopter', 'real user feedback on X', 'feedback da utenti reali su X'. YES when you need the user's voice before building/deciding.

Premortem on a plan/launch/product/assumption/strategy/decision. Assumes it has ALREADY failed 6 months from now and works backward to find every cause. Produces a revised plan with the blind spots exposed. MANDATORY TRIGGERS: 'premortem this/questo', 'what could kill it', 'cosa può ucciderlo', 'stress-test this plan', 'stress-test questo piano', 'what am I missing', 'cosa mi sto perdendo', 'find the blind spots', 'trova i blind spot'. STRONG TRIGGERS: 'what could go wrong', 'cosa può andare storto', 'poke holes in this plan', 'buca questo piano', 'where does it break', 'dove si rompe', 'play devil's advocate', 'fai l'avvocato del diavolo'. Do NOT activate on simple feedback, factual questions. YES when there's a plan/commitment where being wrong is costly.