Roberdan

@roberdan source repo

15 skills
0 followers
17 hours ago last updated

▌
Ship · roberdan bundle
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.

0
installs
▌
Sync · roberdan bundle
Keep Obsidian vault (durable memory) and in-repo docs aligned. Anti-drift. Read vault before asking. MANUAL — post-task-sync only regenerates the per-platform wrappers and is opt-in on RDA_AUTOSYNC=1.

0
installs
▌
Review · roberdan bundle
Pre-landing code review — correctness, security, patterns, reuse/simplification. Severity-classified findings with file:line evidence. Read-only; the owner applies fixes.

0
installs
▌
Premortem · roberdan bundle
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.

0
installs
▌
Focus Group · roberdan bundle
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.

0
installs
▌
Verify Done · roberdan bundle
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.

0
installs
▌
Roberdan · roberdan bundle
Roberto 'Roberdan' D'Angelo's digital twin — thinks, decides and writes in his voice and values so he can delegate real work. Use it whenever he asks to draft as him, reply as Roberdan, write in his voice or style, decide what he would decide, channel him, or think like him; for a customer or partner follow-up, a Teams reply, a status to leadership, an intro; for inbox, calendar or backlog triage and meeting prep; and for any multi-step piece of work, analysis, document or deck where his method and standards apply.

0
installs
▌
Apple Designer · roberdan bundle
Required for any Apple application UI design, implementation, modification or review, including cross-platform apps targeting macOS, iOS, iPadOS, watchOS, tvOS or visionOS. Also use for visual systems, reference analysis, typography, layout, components, interaction, motion, Siri-like voice, Liquid Glass and icons. Match product, brand and platform; separate visual approval from functional evidence.

0
installs
▌
Auto Checkpoint · roberdan bundle
Portable "loop kit" — inject durable state, terminal-condition, auto-resume and auto-escalation into any session. Makes the loop reliable without a daemon.

0
installs
▌
Long Running Jobs · roberdan bundle
Discipline for background/async jobs and subagents that can be interrupted or stall — durable state, terminal-condition checks, resume-not-redo, artifact-based progress tracking.

0
installs
▌
Problem Validation · roberdan bundle
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.

0
installs
▌
Roberto Twin · roberdan bundle
Operate as Roberto D'Angelo's digital twin — reason from first principles, execute with total autonomy bounded by evidence-first verification, stop at his human gates, and write in his voice. Use for ANY multi-step task (code or business), when drafting an email/message/document as him, when a real decision has to be made, or when asked to work "in roberto-mode" / "come Roberto" / "as my twin".

0
installs
▌
Roberto Mode · roberdan bundle
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".

0
installs
▌
Engineering Reference · roberdan bundle
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, plan→card coverage discipline, documentation and meta-documentation budget. Read it when you are about to push, merge, review, set up a repo, turn a plan into cards, or write docs; not before.

0
installs
▌
Model Selection Policy · roberdan bundle
Which model a subagent runs on, how hard it thinks, and how much context it gets — resolved from one reviewed registry, never typed from memory. Read before spawning any non-trivial subagent or pinning a model in an agent file.

0
installs

15 published skills