By a-tokyo
Install every skill in this repository as one plugin: production-grade, tailwind-v3-to-v4-migration, create-skill-autoresearch, tribunal, database-documentation, and 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.
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.
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.
Principle-engineering posture for production-grade code: reads the repo first, plans before code, matches conventions, pulls latest docs over training recall, and ships the simplest correct change that holds the bar — proper algorithms and data structures, idempotent writes, schema+queries+indexes as one artefact, typed errors, tests in the same diff. Substrate-agnostic; defers to peer skills on their lanes. Use for non-trivial planning, design, implementation, review, or refactoring; RCA and debugging; performance and optimization work; changes touching a database schema, security, infrastructure, or a public API; hardening inherited, vibe-coded, or LLM-generated code (dependency/CVE and migration audits); and over-engineering cleanup ("simplest solution," "YAGNI," "what can we delete").
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 design system from scratch, or non-Tailwind CSS.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Reusable agent skills for AI coding assistants. Compatible with Cursor, Claude Code, Codex, and 40+ agents via npx skills.
Download grabs a ready-to-upload .zip of just that skill — for Claude Desktop (Settings →
Capabilities), which has no CLI and can't run npx skills. Rebuilt whenever a skill changes on
main.
| Skill | Description | Download |
|---|---|---|
| production-grade | Principle-engineering posture for production-grade code. Plans before code, simplest-correct-solution-first, ACM-grade algorithms, EXPLAIN-first databases, idempotent-atomic writes, realtime-first, concurrent-by-default, TDD-steered E2E, runtime-coherent infrastructure, maintenance & remediation of inherited or generated code. Substrate-agnostic. | .zip |
| tailwind-v3-to-v4-migration | Migrate a project from Tailwind CSS v3 to v4 safely and completely. Codemod-first (@tailwindcss/upgrade), then the judgment it can't do: dependency/PostCSS/Vite/CLI plumbing, JS config → CSS @theme (or keep via @config), the v4 changed-defaults audit + compat shims, a residual sweep, and proving the migration is a visual no-op. Framework-agnostic; bundles the official upgrade guide. | .zip |
| create-skill-autoresearch | Factory for building production-grade agent skills: interviews you for purpose + gold standards, researches the domain, drafts the skill, autonomously improves it against an LLM-as-judge (or real-world) metric, and verifies it with an independent multi-agent panel. Extends the official single-pass skill creators. Orchestrates companion skills (autoresearch, premortem, handoff) — install those alongside it; the full batteries-included environment is the agent-skills-harness. | .zip |
| tribunal | Doer → verifier-panel → consensus delivery verification for any artifact (code slices, plans, documents, audits). An orchestrator freezes acceptance criteria before implementation, dispatches a doer, then convenes a context-walled panel of independent verifiers — including an adversary with a must-oppose mandate — for evidence-anchored review (citations grepped before consensus math) adjudicated to SHIP / SHIP_WITH_CAVEATS / ITERATE / BLOCK / ESCALATE. Principles-first: panel lenses, dimensions, and prompts derived per artifact from hard invariants. Platform-agnostic; degrades to sequential fresh-context sessions without subagents. Outcome-weighted A/B benchmarks (blind-judged, executed answer keys, honest negatives included) in its README. | .zip |
| database-documentation | Generate database documentation that reaches provable 100% parity with the real schema. Grounds every statement in the live database (system-catalog introspection) and cross-validates against ORM models, migrations, generated types, and seeds, then proves completeness with a mechanical count gate + identity-diff (re-introspect and diff until empty). Emits mermaid ERDs, per-table data dictionaries, and a machine-readable schema.json. Engine-agnostic (PostgreSQL, MySQL, SQL Server, SQLite) and ORM-agnostic (Prisma, TypeORM, Drizzle, Sequelize, Knex, Django, Rails). ≥3 context-walled adversaries (omission / hallucination / correctness) gate the result; platform-agnostic with graceful degradation. Reproducible dual-dialect benchmark with honest negatives in its README. | .zip |
npx claudepluginhub a-tokyo/agent-skills --plugin production-gradeEvidence-based agent skills compiler with progressive capability tiers (Quick/Forge/Forge+/Deep).
Editorial "Skill Author" bundle for Claude Code from Agentic Awesome Skills.
Efficient skill management system with progressive discovery — 410+ production-ready skills across 33+ domains
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,419 supported skills.
Refactor and simplify code for clarity and maintainability. Helps AI agents reduce code complexity, improve readability, and optimize code structure.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.