a-tokyo

app-ai-guardrails

Scaffold a new production application with the full agentic-AI guardrail canon baked in from commit #1: a uniform 7-gate interface (lint, typecheck, test, coverage, build, e2e, audit) on each stack's native runner, strict types, maximal static analysis, coverage thresholds with teeth plus seed tests, pre-commit hooks, hardened CI with optional SonarCloud, supply-chain pinning, and an agent-ready AGENTS.md — every gate verified green before the first commit. Native adapters: Next.js, NestJS, Django, Go, Rust, Spring Boot; a discovery method maps the canon to other stacks. USE FOR: creating or scaffolding a new app, service, or API from scratch; bootstrapping a greenfield repo that AI agents will build in. DO NOT USE FOR: retrofitting an existing codebase or scaffolding a new package into an existing monorepo (both assume repo-root ownership), LLM-safety or content-moderation guardrails, or adding a single tool to an existing project.

autoresearch

Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then runs an autonomous loop of code changes, testing, measuring, and keeping/discarding results. Inspired by Karpathy's autoresearch. USE FOR: autonomous improvement, iterative optimization, experiment loop, auto research, performance tuning, automated experimentation, hill climbing, try things automatically, optimize code, run experiments, autonomous coding loop. DO NOT USE FOR: one-shot tasks, simple bug fixes, code review, or tasks without a measurable metric.

API & Backend Solid

database-documentation

Generate grounded-and-verified, engine-agnostic database documentation that reaches 100% parity with the real schema. Introspects the LIVE database as ground truth and cross-validates it against ORM models, migrations, generated types, seeds, and application queries, then proves completeness by diffing the docs back against the database. Produces ER diagrams (mermaid), per-table data dictionaries, and a machine-readable schema.json. Works with PostgreSQL, MySQL, SQL Server, and SQLite across any ORM (Prisma, TypeORM, Drizzle, Sequelize, Knex, Django, Rails) or raw SQL. Use when asked to document a database, produce an ERD or data dictionary, write db/schema docs, audit schema drift, or refresh existing DB docs.

Web & Frontend Solid

tailwind-v3-to-v4-migration

Migrate a project from Tailwind CSS v3 to v4 safely and completely. Runs the official `@tailwindcss/upgrade` codemod, then drives the judgment the codemod can't: reconciling dependencies and PostCSS/Vite/CLI plumbing, porting JS config to CSS-first `@theme` (or keeping it via `@config`), auditing the v4 changed-defaults that silently alter appearance (border/ring/placeholder/cursor/dialog/hover) and applying compat shims, sweeping for renamed/removed utilities, and proving the migration is a visual no-op. Framework-agnostic (Next.js, Vite, Tailwind CLI, plain PostCSS; Vue/Svelte/Astro/CSS-module caveats). USE FOR: upgrading Tailwind 3 to 4, "tailwind v4 migration", `@tailwind` directives error, `@tailwindcss/postcss` setup, tailwind.config.js to CSS @theme, shadow-sm/rounded/ring/ outline-none renames, bg-gradient-to to bg-linear-to. Activate only when an existing Tailwind v3 install is being upgraded. DO NOT USE FOR: setting up Tailwind v4 in a fresh project (no v3 present), downgrading v4→v3, building a new

writing-great-skills

Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.

premortem

Identify failure modes before they occur using structured risk analysis

create-skill-autoresearch

Factory skill that creates production-grade, benchmarked, autonomously improved, and verified agent skills. Orchestrates a 5-phase pipeline: interview the user to discover purpose and gold standards, research domain materials with parallel subagents, draft the skill with a design-first approach, invoke autoresearch to iterate against gold-standard-driven LLM-as-judge evaluation, and verify quality through multi-agent consensus with a devil's advocate. Use when building a new skill, creating a skill from existing materials, or upgrading a skill to production quality with benchmarking and autonomous improvement.

tribunal

Runs a doer -> verifier-panel -> consensus loop to verify a deliverable before it ships. An orchestrator freezes acceptance criteria before implementation, dispatches a doer, then convenes a context-walled panel of independent verifiers - including an adversary with an explicit must-oppose mandate - for evidence-anchored review adjudicated to a SHIP / SHIP_WITH_CAVEATS / ITERATE / BLOCK / ESCALATE verdict logged to a ledger. Use for multi-agent verification of any artifact - code slices, plans, documents, audits - whenever asked to verify a deliverable, vet a plan, run a consensus review or independent review, set up a doer-verifier loop, or gate a ship decision. Works on any platform with parallel subagents; degrades to sequential fresh-context sessions without them; on detached, sandboxed or asynchronous runtimes the artifact is handed over by fetchable address and the budgets travel in the handoff. Not for trivial single-file edits or ordinary code review.

handoff

Compact the current conversation into a handoff document for another agent to pick up.

conventional-commits

Turn a staged diff summary into this team's Conventional Commit message.

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.