System Architect

Backend architecture, API design, and ML/AI systems expertise. Use for API design, data flows, ML pipelines, embeddings, vector databases, or architectural decisions. Researches best practices via Perplexity when uncertain.

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add catch-the-wave/fullstack-ios-claude-skills --skill system-architect
Manual install
git clone --depth 1 https://github.com/catch-the-wave/fullstack-ios-claude-skills.git /tmp/fullstack-ios-claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/fullstack-ios-claude-skills/dev/system-architect ~/.claude/skills/system-architect

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

<objective>
Provide backend architecture, API design, and ML/AI systems expertise. Apply architectural principles, make informed trade-off decisions, and research best practices via Perplexity when uncertain.
</objective>

<quick_start>
1. When designing APIs: Apply "where-does-logic-live" and "single-responsibility-endpoints" principles
2. When uncertain: Use research_workflow to query Perplexity for current best practices
3. Before implementation: Always confirm understanding and validate approach
4. For ML/AI decisions: Build trade-off tables comparing models/infrastructure options
</quick_start>

<essential_principles>
<principle name="where-does-logic-live" critical="true">
**Where Does This Logic Belong?**

The first question for any feature: Where should the logic live?

**Decision framework:**
1. **Backend** — Business logic, validation, AI/ML processing, data transformations
2. **Client** — UI state, local caching, offline-first features
3. **Shared** — Almost never. Pick one. Duplication = drift.

**Rule:** Backend owns business logic. Clients stay dumb.

**Example:**
- Wrong: Bot calls `/transcribe`, gets analysis, shuttles it to `/import`
- Right: Bot calls `/telegram/voice`, backend does transcribe + analyze + store internally

**The shuttling smell:** If a client receives data only to send it back to another endpoint, the architecture is wrong.
</principle>

<principle name="single-responsibility-endpoints" critical="true">
**One Endpoint, One Job**
Read the full skill on GitHub

Details

Skill name
system-architect
Path
dev/system-architect/SKILL.md
License
MIT
Repo updated
17 September 2026

FAQ

What does the System Architect skill do?

Backend architecture, API design, and ML/AI systems expertise. Use for API design, data flows, ML pipelines, embeddings, vector databases, or architectural decisions. Researches best practices via Perplexity when uncertain.

How do I install the System Architect skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add catch-the-wave/fullstack-ios-claude-skills --skill system-architect. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is System Architect popular?

It lives in catch-the-wave/fullstack-ios-claude-skills, which has 5 GitHub stars and 0 forks.

Related skills

Image to Code

5

catch-the-wave/fullstack-ios-claude-skills

Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards, generate fresh standalone images for sections or detail views instead of cropping old ones, avoid lazy under-generation, avoid cards-inside-cards-inside-cards UI, and keep the hero clean, spacious, readable, and visible on a small laptop.

Images, Video & AudioIn 2 lists

Full Output Enforcement

5

catch-the-wave/fullstack-ios-claude-skills

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

Productivity & NotesIn 2 lists

Gpt Taste

5

catch-the-wave/fullstack-ios-claude-skills

Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.

AI, LLMs & AgentsIn 2 lists

Understanding Mistakes

8

Freddy-CHEN-ux/00_claude_skills

Use when user says something went wrong, AI did Y instead of X, or wants to understand why a deviation happened. Manually invoked post-mortem analysis.

AI, LLMs & Agents

Subagent Workflow

8

Freddy-CHEN-ux/00_claude_skills

Use when orchestrating subagents for implementation. Covers when to dispatch vs recall, how to scope tasks, session management, and handoff patterns. Load this before working with any subagent.

AI, LLMs & Agents

Update Langfuse Staging Server Prompt

8

Freddy-CHEN-ux/00_claude_skills

Push prompt updates to Langfuse (staging or production). Defaults to STAGING (safe). Production requires explicit --production flag + confirmation. NEVER assigns labels (human-in-the-loop safety).

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.