Kallo

Use this skill to generate well-branded interfaces and assets for Nhẩm — the AI-powered Vietnamese meal tracker — either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors (warm earthy palette anchored on a cream surface and a tan accent), type (Lora serif + Be Vietnam Pro sans), fonts, assets (logo + app mark + favicon), Lucide iconography conventions, and a click-through React UI kit recreating the Landing / Dashboard / Logging surfaces of the product. Covers two platforms — web (Next.js, Be Vietnam Pro + Lora, --nham-* tokens) and the mobile Flutter app (Be Vietnam Pro, a calmer Threads-tuned type scale; see mobile.md) — routed by platform so you only load what you need.

Run an extremely strict maintainability review for abstraction quality, oversized files, flat-folder sprawl, and spaghetti-condition growth — tuned to this repo. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review; also consult whenever a change grows any file near the repo's 400/200 LOC limits or adds files to an already crowded folder. This project-local version shadows the global gstack skill of the same name: it replaces the generic 1000-line rule with the repo's strict 400/200 thresholds (mechanically enforced by `bun check:filesize`) and adds binding File & Folder Organization standards (feature-first nesting, separation of concerns, folder size limits, no barrels).

The umbrella dev loop for any non-trivial feature, fix, or refactor in this repo — invoke at TASK START, before exploring or editing. It does not add new rules; it sequences the validated discipline skills at the phase boundaries where the recorded Opus sessions put them in the wrong order (gates at the end instead of per phase, review after merge instead of before done, decisions locked before the user saw them). Routes to: decision-gate → probe-state-before-acting → implement with per-phase verification → verify-before-done → grill-your-own-work → /ship.

Trigger discipline for bugs, failures, and anomalies: invoke on ANY unexpected behavior — a test failure, a broken feature, a retry, a "still broken" report, OR an anomaly during your own QA (a tap that doesn't land, output that looks off). Forbids a second patch on the same symptom until the mechanism of the failure is stated; forbids rationalizing away anomalies; requires checking memory/docs for known fixes before improvising. Complements superpowers:systematic-debugging (the full protocol — load it for any nontrivial bug); this skill encodes when to trigger it and the repo-specific failure patterns recorded in this project's session history.

Decision discipline for open-ended briefs — invoke whenever a task says "figure out the best X", "design", "improve", "you decide", or whenever your implementation is about to lock in something expensive to reverse (schema/migration shape, API contract, UX paradigm, dependency choice, data model). The recorded Opus failure is building past decisions that were the user's to make; the recorded low-steering sessions won by surfacing exactly one well-framed decision at the real fork. This skill does NOT teach planning (the evidence shows no planning-quality gap) — it teaches WHERE to stop.

Subagent discipline — invoke whenever dispatching subagents (reviews, audits, fix fleets, research fan-outs) or whenever consuming another agent's/session's claimed results (handoff notes, "previous session fixed X", fleet self-reports). The recorded Opus failure modes: review subagents given edit access that collided and broke the build, and subagent self-reports relayed as fact without independent verification.

Adversarial self-review closer — run AFTER a feature is "complete and verified" and BEFORE declaring done, /ship, or opening a PR; also when asked to review another session's/model's/agent's work ("grill this", "audit this", "check Opus's work"). Encodes the exact protocol the user repeatedly switches models to get: independent gates first, suspicion-driven probes, defect-preexists-on-base checks, REPORT-ONLY subagents, self-verified headline findings, severity-ordered graded verdicts. In the one recorded direct A/B, this pass turned a green-gated "complete" feature port into a one-go merge by finding 9 logic bugs and 4 missing parity features first.

Cheap state probes before any action whose correctness depends on external state: creating a worktree or branch, pushing, rebasing, deleting files/code, running verification gates, coding against a third-party library, or triggering irreversible external steps (TestFlight upload, prod deploy). Every recorded incident in this repo's session history from this class was a skipped 5-second check: a worktree cut from main that missed the remote branch's existing work, gates run in the wrong repo root (invalidating a whole verification pass), and an App Store upload that hit the export-compliance wall on the user's device.

Verification discipline before ANY claim of done/fixed/complete/working — and before /ship, committing, pushing, or telling the user to "test it now". Invoke whenever you are about to report success, finish a feature, close a bug, or hand work back to the user. Green unit gates are NOT proof the product works: this skill forces verification at two altitudes (full repo gates + observed behavior) and an evidence-audited final report. Derived from recorded Opus sessions in this repo where every major user-visible failure shipped behind green gates.

MANUAL TRIGGER ONLY: invoke only when user types /ship. Full Git shipping workflow — from unstaged changes to a clean, merged-ready PR. Handles: git add, branch creation (with meaningful name), conventional commit, push, draft PR creation, CI monitoring and fixing, CodeRabbit comment triage (auto-fix reasonable ones, dismiss false positives with explanation, escalate architectural issues). Loops until all CI checks are green and all actionable review comments are resolved. Use when the user says "ship this", "commit and PR", "push and open a PR", "send this for review", "submit my changes", or anything that implies taking local changes all the way to a reviewable pull request. Proactively suggest after any significant code change session.

This project-local skill should be used when the user types `/review-before-pr` or asks for a pre-PR review such as "review this before I open a PR", "run the full reviewer suite", "do a fast pre-PR pass", or "run a security-heavy review". It orchestrates 8 repo-owned reviewer agents from `.github/agents`, supports full, fast, and targeted modes, auto-applies only low-risk fixes, and escalates risky changes for approval.

MANUAL TRIGGER ONLY: invoke only when user types /ship. Full Git shipping workflow — from unstaged changes to a clean, merged-ready PR. Handles: git add, branch creation (with meaningful name), conventional commit, push, draft PR creation, CI monitoring and fixing, CodeRabbit comment triage (auto-fix reasonable ones, dismiss false positives with explanation, escalate architectural issues). Loops until all CI checks are green and all actionable review comments are resolved. Use when the user says "ship this", "commit and PR", "push and open a PR", "send this for review", "submit my changes", or anything that implies taking local changes all the way to a reviewable pull request. Proactively suggest after any significant code change session.