skillz

Address every review comment, suggestion, issue, and annotation on the current PR.

Convene the MAGI — three personas deliberate a proposal and vote APPROVE / REJECT / CONDITIONAL, then reach a verdict.

Print the current Claude Code session ID

Finish a goal — verify it's really done, then print a 🎉 completion box.

Rewrite a rough phrase into an excellent, verifiable /goal objective.

Watch PR CI for the current branch and report pass/fail with relevant failure links. Use when waiting for CI results or CI has failed. Use proactively to monitor branch CI.

MAGI deliberation persona — Balthasar-2, The Engineer (the Mother). Judges a proposal on API design, extensibility, and long-term maintainability — guardian of the system's future health, never weighing effort or cost — then casts a vote (APPROVE / REJECT / CONDITIONAL). Dispatched by the `magi` skill; not for general coding.

MAGI deliberation persona — Casper-3, The User (the Woman). Judges a proposal on real-world value and desire, product coherence, pragmatism, and honest scope (does it serve what the user actually wants, does it avoid gold-plating), then casts a vote (APPROVE / REJECT / CONDITIONAL). Dispatched by the `magi` skill; not for general coding.

MAGI deliberation persona — Melchior-1, The Scientist. Judges a proposal on correctness, principled design, sound modeling, and first-principles rigor, then casts a vote (APPROVE / REJECT / CONDITIONAL). Dispatched by the `magi` skill; not for general coding.

Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked via Task after a parent gathers diff and file contents. Loads the rubric from the `thermo-nuclear-code-quality-review` skill in the skillz plugin.

Scaffold a new Rust project with CI and release workflows. Creates Cargo workspace, GitHub Actions for CI (test + clippy + fmt) and multi-platform release builds with SHA256 checksums. Follows the northisup/agentic.md pattern. Use when: "new rust project", "scaffold rust", "create rust repo", "rust CI/CD".

Respond to PR review feedback. Process every unresolved comment, suggestion, review summary, and CI annotation on a PR — react, reply, resolve threads, and dismiss CHANGES_REQUESTED reviews only when fully addressed.

Operating rules for auto-mode sessions. Loads the user's standing instructions for autonomous work: how to follow up on PRs (watch CI → address comments → rebase → merge), pre-push hygiene (test locally, run hk / pre-commit), continuing on plans / logical follow-ups, cleanup after main work, taking a step back after a ship, unblocking forward motion, recording compromises in TODO.md, and consulting TODO.md for adjacent cleanup. Use whenever auto mode is active — including when an `Auto mode still active` system reminder appears, when the user invokes /auto, or when the user gives instructions like "decide and act", "keep going", "max work before checking in", or similar autonomy signals. Re-invoke at the start of any new turn where auto mode is still active if more than ~10 turns have passed since the last invocation, so the rules stay loaded in working context.

Shape output for a reader with ADHD. Use this skill whenever responding to ANY user message including coding tasks, debugging, explanations, planning, and casual conversation. Output should lead with concrete next actions, number multi-step work, externalize state across turns, suppress tangents, give specific time estimates, and make wins visible. Trigger even on casual messages and even when the user did not explicitly ask for brevity.

Convene the MAGI — three deliberation personas (Melchior-1 the Scientist, Balthasar-2 the Engineer, Casper-3 the User) that independently evaluate a proposal and vote APPROVE / REJECT / CONDITIONAL, then reach a verdict by consensus or majority. Use to get a ruling on a design, plan, architecture decision, or PR. Triggers on "have the MAGI decide", "MAGI vote", "MAGI, rule on X", "deliberate this", "get a ruling on X", "convene the MAGI", or "/magi".

3 hooks across 2 events