tomada-kit

Plugin tomada-kit from marketplace tomada-claude-plugins in tomada1114/tomada-claude-plugins. Commands read from the repo's manifest — yesterday.

Skills (20)

• auditing-prompt-docs

  Audit and fix prompt-bearing documents — SKILL.md, CLAUDE.md, AGENTS.md, agent and command definitions, reference files, whole repositories — against Anthropic's published prompting guidance for current Claude models, proposing edits for approval before writing anything. Also answers how to prompt a

• auditing-repositories

  Audit the repository you are in, often a template or an app cut from one, for technical debt and room to improve in four areas: architecture and design patterns; tests; file structure and code quality; and tooling, CI, dependencies and the agent harness. Design a safe, test-first fix for every evide

• authoring-goal-prompts

  Author a self-contained prompt for Claude Code's /goal command, run unattended in a separate session — a lead-to-staff handoff where this session researches, designs, and decides with full context, and a fresh executor session (Opus 5.5 or Fable 5.2, with none of that context) implements. Drafts a g

• bootstrapping-from-templates

  Cut a new GitHub repository from one of the user's template repositories and bring it to a clean first commit: create it from the template (public by default) with scripts/create_from_template.py, clone it under ghq, follow the template's own starting-an-app procedure for the rename or bootstrap (a

• codex-cli-config

  Reference for OpenAI Codex CLI configuration, permissions, sandboxing, and autonomy — sandbox_mode and permission profiles, approval_policy, Rules (.rules / prefix_rule), config.toml precedence and trust, AGENTS.md discovery, task design (Mini Codex, Done When, Plan mode), Skills/Plugins/subagents/M

• configuring-cloud-environments

  Inspect, create, and edit Claude Code cloud environments (the Name, Network access, Allowed domains, Setup script, and Environment variables behind claude.ai/code's environment selector) and decide what a repository needs from one — which hosts its toolchain downloads from and whether the Trusted al

• configuring-project-permissions

  Set up a repository's personal, uncommitted agent permissions so development runs without prompts: Claude Code's gitignored .claude/settings.local.json and Codex CLI's gitignored .codex/rules/local.rules, each in its native format. Generic rules (git, gh, coreutils, hook-bypass and force-push denies

• creating-agent-skills

  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, agen

• designing-architecture

  Decide a new app's hard-to-reverse design choices from its signed-off requirements and UX drafts before any issue is filed — design lock, app shape, sandbox and OS permissions, persistence, backend and sync, auth, key dependencies, locales, distribution — through researched option rounds with the us

• designing-wireframes

  Create ASCII wireframes for every screen and window, user flow diagrams, and per-screen states (empty, loading, error) from a requirements document, for desktop (macOS windows, menu-bar popovers, settings), web (responsive app shells), and mobile. Writes into the requirements document in place, or i

• dual-platform-skills

  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-

• kicking-off-apps

  Take a rough app idea ("I want an app that…") to a new public GitHub repository cut from one of the user's template repositories, with signed-off requirements, UX flows, a researched design system, design decisions in the template's skills (no architecture docs), loose project permissions, and a dep

• orchestrating-models

  Decide which model and effort runs a piece of work, and whether to delegate it at all. The canonical source for model assignment — the main session, the named sub-agents (executor, architect, scout, worker), and Workflow agent() stages. Use when starting a large task, deciding whether to delegate, p

• planning-tickets

  Break requirements and design documents into GitHub Issues an implementing agent can ship without asking back: concrete values with their source, EARS requirements, explicit Not In Scope, machine-readable `Depends on #N` edges, a parallel-first breakdown, tracking parents with native sub-issues, and

• refero-design

  Primary/default skill for UI design, product design, web design, landing pages, dashboards, product screens, redesigns, visual polish, frontend/CSS styling, design systems, components, responsive design, typography, color, spacing, motion, icons, accessibility, copywriting, conversion, and anti-AI-s

• refining-prompts

  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 only when needed, and questions the u

• refining-requirements

  Turn a vague app idea or an incomplete spec into a signed-off, implementation-ready requirements document through repeated rounds of structured questioning, acting as the PdM while the user plays the client. Each round also scrutinizes the draft — contradictions, missing flows, unstated edge cases,

• rethinking-prompt-assets

  Rethink a set of prompt assets from zero — memory files (CLAUDE.md, AGENTS.md), skills, sub-agent definitions, and the flows they form — and propose large changes: delete, merge, split, rebuild, reroute. A sub-agent blind to the current assets designs the ideal set for the jobs they serve; the curre

• syncing-agent-tiers

  Push the canonical sub-agent tier definitions (executor, architect, scout, worker) into every listed repository's .claude/agents/ and .codex/agents/, opening one auto-merging PR per repository. Use after changing a tier's model or effort, when adding a repository to the sync list, or as the last ste

• ui-ux-designing

  Produces one app-wide UX guidelines document (docs/design/ux-guidelines.md or a caller-named path) fixing navigation, platform conventions, empty/loading/error/offline/permission states, feedback, form validation, motion and reduced-motion, UI language and i18n, and accessibility targets as concrete

Slash commands (1)

• /tomada-kit:smart-commit

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

Subagents (4)

• architect

  Fable 5.2 high の難所担当。ブリーフに書き出せる難所（多段の推論が要る実装、非自明なアルゴリズム、原因究明、2 回の修正を生き延びた失敗）、コードレビュー・バグ発見、散在した大量の調査結果の統合を渡す。1 本が高いので本数は最小限にする。仕様が確定した作業は executor に渡し、会話の文脈が要る設計判断はメインに残す。

• executor

  Opus 5.5 medium の実行役。仕様が確定していて成否がはっきりした作業を渡す — 確定仕様どおりの実装、テスト追加、CI を通す、コミット・PR 作成、一括置換・整形。ファイルを書き換えない調査・収集・列挙は scout に渡す。聞き返されそうな曖昧さや設計判断が残る作業はメインが仕様を固めてから渡す。難所とレビューは architect に渡す。

• scout

  Haiku 5.5 xhigh の調べ物役。ファイルを書き換えない、判断を含まない調査・収集・列挙・要約を渡す — 決まった問いへの答えを探す、条件に合う箇所を全件挙げる、大量に読んで結論だけ返す、Web で事実を集めて出典付きで返す。ファイル編集、コマンドによる変更、コミット、実装は executor に、解釈や設計判断、レビュー、散在情報の統合は architect に渡す。

• worker

  Sonnet 5.5 at high effort, the tier for briefed text work. Hand it self-contained,