メニュー
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.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
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.
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.
| name | ship |
| description | 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. |
| providers | ["claude","copilot","codex"] |
| disable-model-invocation | true |
Platform-independent ship workflow. No bypasses, no shortcuts.
cargo fmt --check / prettier --check / ruff format --checkcargo clippy -- -D warnings / eslint / ruff checkcargo check / npx tsc --noEmitcargo test / npm test / pytest (output shown)cargo build / npm run buildIf a step fails: fix and re-run all checks. Never push with known failures.
main).git push the branch.gh pr checks <n> — all SUCCESS before proceeding.main, report the merge commit SHA.main impacting branch-protection / security / license / release-infra (#1)main (#2) — always forbidden without explicit confirmationEvery comment (human or bot) must be analyzed, understood, and resolved well — never
silent-resolve, never a "fix" that only touches the quoted line while ignoring the substance.
Reply on the thread with what you did and why, then resolve. See skills/review.