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 user, and write each decision in the present tense, with its reasoning, into the repository skill that owns the subject (its SKILL.md or references/), or AGENTS.md's Architecture section for a layer rule. Creates no architecture overview, roadmap, decision record, or ADR; a subject with no owning skil
Install
/plugin marketplace add tomada1114/tomada-claude-pluginsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add tomada1114/tomada-claude-plugins --skill designing-architecturegit clone --depth 1 https://github.com/tomada1114/tomada-claude-plugins.git /tmp/tomada-claude-plugins
mkdir -p ~/.claude/skills
cp -r /tmp/tomada-claude-plugins/tomada-kit/skills/designing-architecture ~/.claude/skills/designing-architecturePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Designing Architecture Issues are cheap and change weekly; the reasoning they depend on should not. This skill settles what the app will stay — its shape and each choice that is expensive to reverse — so every issue can cite a skill instead of re-deciding it in a thread. Without it, the first implementer settles persistence or app shape by accident. **Design lives in the skills — the owner's standing rule.** A decision is written once, in the skill an agent loads when it touches that subject: what the app does and why, in the present tense. A document no skill points an agent at is never read when it matters, and a second copy drifts. So this skill writes no architecture overview, no roadmap, and no decision record (ADR): git holds what a decision used to say, and changing a decision means rewriting its sentences in the owning skill, in the same change as the code. Direction — what comes next — is the Product section and the open issues, not a document. ## Contract **Input:** a repository whose `docs/product/requirements.md` is signed off and whose `AGENTS.md` Product section is written; `docs/product/ux-flows.md`, `docs/design/ux-guidelines.md`, and `docs/design/design-direction.md` when they exist. **Output:** each decision written into its home, found in this order: 1. The repository skill whose **Owns** line covers the subject (read every skill's frontmatter and Owns / Does-not-own lines first). A short rule goes in its body; a
Details
- Skill name
designing-architecture- Repository
- tomada1114/tomada-claude-plugins
- Path
tomada-kit/skills/designing-architecture/SKILL.md- Repo updated
- 12 November 2026
FAQ
What does the Designing Architecture skill do?
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 user, and write each decision in the present tense, with its reasoning, into the repository skill that owns the subject (its SKILL.md or references/), or AGENTS.md's Architecture section for a layer rule. Creates no architecture overview, roadmap, decision record, or ADR; a subject with no owning skil
How do I install the Designing Architecture skill?
Claude Code plugin: /plugin marketplace add tomada1114/tomada-claude-plugins. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Designing Architecture popular?
It lives in tomada1114/tomada-claude-plugins, which has 5 GitHub stars and 0 forks.
Related skills
Auditing Prompt Docs
5tomada1114/tomada-claude-plugins
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 specific model: holds the per- model guidance for Claude Fable 5.2, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 alongside the cross-model practices. Use when reviewing or slimming an instruction file, when instructions are ignored or fire too often, when migrating a prompt to a newer m
Auditing Repositories
5tomada1114/tomada-claude-plugins
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 evidenced finding, and file the findings as GitHub issues that follow the repository's own issue conventions (triaging-issues, issue forms, past issues). A finding inherited from the template is also filed in the template repository. Cheap read-only sub-agents collect the evidence and high-effort analyst
Authoring Goal Prompts
5tomada1114/tomada-claude-plugins
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 goal with measurable done-criteria, transcript-verifiable checks, scope + anti-cheat constraints, and stop rules; packages design intent, code examples, research findings, checklists, and pre-answered decisions as support files in a per-goal state directory whenever the executor would otherwise re-de
Discord Bot Architect
5Dreydrey9000/claude-skills
Specialized skill for building production-ready Discord bots. Covers Discord.js (JavaScript) and Pycord (Python), gateway intents, slash commands, interactive components, rate limiting, and sharding.
Commit
5Magnus-Gille/claude-skills
Create or amend a Git commit with author verification, diff review, and a conventional message. Use only when the user explicitly invokes $commit or asks to commit or amend changes.
Eli5
5Magnus-Gille/claude-skills
Explain the previous answer, a selected topic, a technical concept, tool result, document, error, decision, or workflow in very simple language. Use when the user asks for ELI5, "förklara superenkelt", "som för en femåring", "på vanlig svenska", "make it simple", or wants a plain-language explanation of what was just explained.
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.