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.
Plugin all-skills from marketplace a-tokyo-skills in a-tokyo/agent-skills. Commands read from the repo's manifest — 5 days ago.
skill-creatorCreate 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 t
writing-great-skillsReference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
autoresearchAutonomous 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: auto
handoffCompact the current conversation into a handoff document for another agent to pick up.
premortemIdentify failure modes before they occur using structured risk analysis
app-ai-guardrailsScaffold 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
create-skill-autoresearchFactory 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, inv
database-documentationGenerate 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 diff
production-gradePrinciple-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 a
tailwind-v3-to-v4-migrationMigrate a project from Tailwind CSS v3 to v4 safely and completely. Runs the official `@tailwindcss/upgrade` codemod, then drives the judgment it can't: reconciling dependencies and PostCSS/Vite/CLI plumbing, porting JS config to CSS-first `@theme` (or keeping it via `@config`), auditing the v4 chan
tribunalRuns 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 -
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.
11 skills
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 — delegating to tribunal when installed. Ships a same-model-uplift benchmark standard (bare vs skill vs skill+panel, scored by execution, honest negatives required) and a publish checklist, and stops the improvement loop on a plateau inside judge variance instead of iterating toward an unreachable target. 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.
11 skills
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.
11 skills
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.
11 skills
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.
11 skills
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 — including an adversary with a must-oppose mandate — for evidence-anchored review adjudicated to SHIP / SHIP_WITH_CAVEATS / ITERATE / BLOCK / ESCALATE. Platform-agnostic; degrades to sequential fresh-context sessions without subagents.
11 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.