all-skills
πPlugina-tokyo/agent-skills
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.
Part of
a-tokyo/agent-skills
Installation
/plugin marketplace add a-tokyo/agent-skills/plugin install all-skills@a-tokyo-skillsMore from this repository10
An engineering posture skill that enforces production-grade coding principles including plan-before-code, simplest-correct-solution-first, ACM-grade algorithms, EXPLAIN-first databases, idempotent-atomic writes, and TDD-steered end-to-end testing.
Skill
Skill
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 and identity-diff. Emits mermaid ERDs, per-table data dictionaries, and a machine-readable schema.json. Engine-agnostic and ORM-agnostic.
Doer to verifier-panel to 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 β including an adversary with a must-oppose mandate β for evidence-anchored review adjudicated to SHIP / SHIP_WITH_CAVEATS / ITERATE / BLOCK / ESCALATE. Platform-agnostic; degrades to sequential fresh-context sessions without subagents.
π§ AI Agent skills for LLMs and AI Agents - Claude, Codex, Cursor etc.
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 and remediation of inherited or generated code. Substrate-agnostic.
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, pre-commit hooks, hardened CI, supply-chain pinning, and an agent-ready AGENTS.md. Native adapters for Next.js, NestJS, Django, Go, Rust, and Spring Boot. Greenfield only (v1).
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 to CSS @theme (or keep via @config), the v4 changed-defaults audit and compat shims, a residual sweep, and proving the migration is a visual no-op. Framework-agnostic; bundles the official upgrade guide.
Factory for building production-grade agent skills: interviews you for purpose and 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) β install those alongside it; the full batteries-included environment is the agent-skills-harness.