architecture-designer

An agent skill by Jeffallan, from Jeffallan/claude-skills. Tags: design, documentation, microservices, scalability, strategy, system-design.

What it does

Use when designing new high-level system architecture, reviewing existing designs, or making architectural decisions. Invoke to create architecture diagrams, write Architecture Decision Records (ADRs), evaluate technology trade-offs, design component interactions, and plan for scalability. Use for system design, architecture review, microservices structuring, ADR authoring, scalability planning, and infrastructure pattern selection — distinct from code-level design patterns or database-only design tasks.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add Jeffallan/claude-skills --skill architecture-designer

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/Jeffallan/claude-skills
cp -r claude-skills/skills/architecture-designer ~/.claude/skills/architecture-designer

Safety box score

Grade A, minimal risk: 5 of 100 risk points, rated 2026-09-25. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is documentation-only: it helps draft architecture diagrams, ADRs, and design notes from plain markdown templates. The main risk is stylistic/instructional rather than operational; it uses strong role-play language, but it does not ship scripts, installers, or automation.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	No shell commands, code evaluation, or native scripts are present; the shipped files are plain markdown templates.
Network access	0 (none)	There are no download/fetch steps or API calls; the only outbound reference is a static documentation link in `SKILL.md`.
Filesystem reach	0 (none)	The skill does not instruct the agent to read, write, or delete paths outside the repository.
Secrets & credentials	0 (none)	No handling of tokens, keys, passwords, `.env` files, or other credentials appears in the skill files.
Privilege & persistence	0 (none)	It does not request sudo, global installs, service registration, or OS/shell configuration changes.
Instruction hijack surface	1 (low)	`SKILL.md` assigns a persona and role-play voice (`"You are a principal architect with 15+ years of experience"`), which is directive but does not instruct bypassing higher-priority rules.
Irreversible actions	0 (none)	The workflow is for drafting designs and reviewing with stakeholders; it does not post, deploy, delete, pay, or otherwise act on its own.
Transparency	0 (none)	All files are readable markdown; there are no binaries, minified blobs, or unreviewable installers.

Before installing

Read `SKILL.md` to confirm you want the role-play style and architecture workflow.
Inspect the linked external documentation separately if you plan to rely on it.
Verify future revisions stay markdown-only and do not add scripts or remote fetch steps.

Rated 2026-09-25 by an automated review of 6 files from the skill's repository.

Source

Repository: Jeffallan/claude-skills (all skills from this repository)
Path: skills/architecture-designer/SKILL.md
Branch: main
Updated: 2026-09-19

taste-design — Semantic Design System Skill for Google Stitch.
architect — Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
design-md — Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files
goal-prompt — Drafts copy-paste-ready /goal commands for goal mode in Claude Code and Codex.
guidelines-advisor — Smart contract development advisor based on Trail of Bits' best practices.
marketing-plan — When the user needs a comprehensive marketing plan for a client, a company they advise, or their own product.