tomada1114

tomada1114/tomada-claude-plugins

Plugin Claude Code

Plugin marketplace listing 1 plugin: tomada-kit.

tomada1114/tomada-claude-plugins

Plugin Claude Code

A collection of Claude Code skills for creating skills, clarifying requirements, making wireframes, developing from issues, delegating to models, and improving prompts.

tomada1114/tomada-claude-plugins

Command

Analyze the working tree, group related changes, and create commits at a sensible granularity.

tomada1114/tomada-claude-plugins

Skill Claude CodeCodex

Author a self-contained prompt for Claude Code's /goal command, run unattended in a separate session — a lead-to-staff handoff where this (stronger) session researches, designs, and decides, and a (typically weaker) executor model implements. Drafts a goal with measurable done-criteria, transcript-verifiable checks…

tomada1114/tomada-claude-plugins

Skill Claude CodeCodex

Create or improve Agent Skills (the shared SKILL.md format read by Claude Code and OpenAI Codex CLI — SKILL.md + optional references/scripts/assets). Two playbooks: build a skill from scratch or from an existing doc; or review an existing skill through parallel specialist lenses (prose quality, agent neutrality…

tomada1114/tomada-claude-plugins

Skill Claude CodeCodex

Review code structure, complexity, and security patterns under a hard read-only guarantee — the editing tools are removed for the turn, so findings can be produced against an untrusted or production checkout without any risk of a write. Use when auditing an unfamiliar codebase, scoping a refactor, or reviewing a…

tomada1114/tomada-claude-plugins

Skill Claude CodeCodex

Write a greeting in a target language at a specified register, with the usage constraints a dictionary entry omits — time-of-day window, seniority assumptions, regional variation. Use when drafting localized welcome copy, onboarding strings, or greetings for an international audience.

tomada1114/tomada-claude-plugins

Skill Claude CodeCodex

Pick the HTTP status code an API should return for a given outcome, and settle the cases where two codes both look defensible — 401 vs 403, 400 vs 422, 404 vs 403 for hidden resources, 409 vs 422 for conflicts. Use when designing REST endpoints, reviewing an API's error handling, or debugging a client that mishandles…

tomada1114/tomada-claude-plugins

Skill Claude CodeCodex

Example multi-phase skill — reviews a pull request by spawning a security specialist and a performance specialist in parallel, each primed with a numbered checklist, then merges their findings into a deterministic workspace. Structural reference for building phased skills with sub-agents; not wired to anything, do not…

tomada1114/tomada-claude-plugins

Skill Claude CodeCodex

Check a Node project for the setup failures that surface later as confusing runtime errors — malformed package.json, uninstalled nodemodules, missing .env, uninitialized git — and scaffold the missing pieces. Use when onboarding to an unfamiliar repo, bootstrapping a new project, or diagnosing "it works on my machine".

tomada1114/tomada-claude-plugins

Agent

One template for every lens in the Improving playbook. Fill the placeholders, then hand the text to a fresh context — a parallel sub-agent where the environment supports it; otherwise work through it inline, one lens at a time, in the order SKILL.md lists them, reading the checklist before the skill each time.

tomada1114/tomada-claude-plugins

Skill Claude CodeCodex

Create ASCII wireframes, user flow diagrams, and cross-cutting specifications for UI/UX visualization (ワイヤーフレーム、画面設計、UI/UXフロー). Use PROACTIVELY when user mentions wireframe, UI design, UX flow, screen layout, screen design, user flow, or asks to visualize screens. Examples: Context: User needs screen design user…

tomada1114/tomada-claude-plugins

Skill Claude CodeCodex

Convert one existing skill (Claude Code origin or Codex origin) into a layout that works on both Claude Code and OpenAI Codex CLI. Uses Topology A: the real files live in .claude/skills/ and the Codex side symlinks them. Capabilities the running runtime may not expose (parallel delegation, skill-to-skill calls, option…

tomada1114/tomada-claude-plugins

Agent

An agent that reads converted skills from the viewpoint of a fresh, skeptical reviewer and checks whether Codex could actually run them. It does not edit files.

tomada1114/tomada-claude-plugins

Agent

An analysis agent that studies a target skill in depth and creates a plan for converting it to support two modes. The description does not define what the two modes are.

tomada1114/tomada-claude-plugins

Agent

A helper agent for rewriting a skill's instructions and its Markdown reference and template files according to a conversion plan.

tomada1114/tomada-claude-plugins

Agent

A helper agent for copying the knowledge of one dependent helper agent into a skill's reference files so two platforms can share it.

tomada1114/tomada-claude-plugins

Skill Claude CodeCodex

Playbook for choosing models and deciding what to delegate. The default posture flips with the main model: when the main model is Fable, concentrate on judgment and push execution to Opus/Sonnet/Haiku; when it is Opus, execute directly by default and delegate only independent parallel tracks, mechanical work, and…

tomada1114/tomada-claude-plugins

Skill Claude CodeCodex

Plan and create GitHub Issues with agile/scrum methodology. Analyze requirements, identify parallel work, manage dependencies, and suggest git worktree strategies. Use PROACTIVELY when creating tickets, planning sprints, breaking down features, organizing issues, identifying parallel tasks, managing dependencies, or…

tomada1114/tomada-claude-plugins

Skill Claude CodeCodex

Polish a rough instruction (often dictated by voice) into a precise prompt that can be handed straight to another agentic coding session (Claude Code, Codex CLI, etc.), and print it in the CLI as a single code block (no file is saved). Runs a light scouting pass with a Sonnet sub-agent only when needed, and questions…

tomada1114/tomada-claude-plugins

Skill Claude CodeCodex

Clarify ambiguous requirements through structured questioning and produce detailed, implementation-ready specifications. Acts as PdM to identify unclear points and resolve them through structured questioning. Use PROACTIVELY when user mentions requirements, specs, PRD, refine, detail, clarify requirements, or asks to…

tomada1114/tomada-claude-plugins

Skill Claude CodeCodex

Rank the open GitHub Issues by their priority: P0-P3 labels — backfilling a missing label from whether an issue unblocks others and how far its impact spreads — then implement the top one, review and fix it with /code-review before the PR exists, open a PR that auto-closes the issue (Closes #N), watch CI until it is…

tomada1114/tomada-claude-plugins

Agent

Filled and handed to a sonnet worker (or read and run inline where the runtime exposes no delegation) from references/delegation-templates.md's "Priority research and labeling" section — the spawn condition, the return contract, and what the caller does with each section live there. This file is only the prompt body.

tomada1114/tomada-claude-plugins

Skill Claude CodeCodex

Design UI/UX concepts for apps and web services through systematic research and questioning (UI/UXデザイン、デザインコンセプト決定、配色・カラースキーム、デザインシステム設計). Use PROACTIVELY when designing app interfaces, determining visual direction, creating design systems, choosing color schemes, or establishing UX patterns. Examples: Context: User…