Agent skill

Architect

by YougLin-dev in YougLin-dev/Aha-Loop

Designs system architecture and selects technology stack based on vision analysis.

MITAuto-check passedDatabases

Install Architect

skills CLI
$ npx skills add YougLin-dev/Aha-Loop --skill architect -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install YougLin-dev/Aha-Loop architect --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/YougLin-dev/Aha-Loop.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/architect .claude/skills/architect && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
architect
GitHub stars
181
Token cost
~2.2k tokens
SKILL.md length
389 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

Designs system architecture and selects technology stack based on vision analysis.

  • Works in 11 steps: Prefer Latest Stable Versions → Consider Long-term Maintenance → Evaluate Total Cost → …
  • : design architecture
  • SKILL.md covers Workspace Mode Note, The Job, Core Principles and Research Process, plus 7 more sections
  • Calls npm, curl and jq; reaches crates.io

What it does

Architect is an agent skill from YougLin-dev/Aha-Loop. Designs system architecture and selects technology stack based on vision analysis. Use after vision analysis for technical decisions. Triggers on: design architecture, select tech stack, choose framework.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Databases. The repository describes itself as: [MVP] Aha Loop is a fully autonomous AI development system, extended from the core ideas of Ralph. It's not just an execution engine, but a complete AI development framework with… The licence is MIT.

When your agent uses it

  • : design architecture
  • Select tech stack
  • Choose framework

Example prompts

  • “Use the architect skill to design system architecture and selects technology stack based on vision analysis”
  • “/architect”

Requirements

  • Node.js
  • Docker

Workflow steps

11 steps, taken from the step headings in SKILL.md.

  1. Prefer Latest Stable Versions
  2. Consider Long-term Maintenance
  3. Evaluate Total Cost
  4. Identify Technology Layers
  5. Research Each Layer
  6. Use Structured Comparison
  7. Check Compatibility
  8. Component Diagram
  9. Data Flow
  10. Directory Structure
  11. Key Patterns

What it can do on your machine

Read from SKILL.md and the folder at commit 8d799b2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm
    • curl
    • jq
    • cargo
    • gh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • crates.io

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Architect loads about 2.2k tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 389 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from YougLin-dev/Aha-Loop at commit 8d799b2, republished under its MIT licence (© YougLin-dev). 389 words, ~2,231 tokens.

Download SKILL.mdSave it as .claude/skills/architect/SKILL.md (or your agent's skills folder).
name
architect
description
Designs system architecture and selects technology stack based on vision analysis. Use after vision analysis for technical decisions. Triggers on: design architecture, select tech stack, choose framework.

Architect Skill

Research, evaluate, and decide on technology stack and system architecture based on project requirements.

Workspace Mode Note

When running in workspace mode, all paths are relative to .aha-loop/ directory:

  • Vision analysis: .aha-loop/project.vision-analysis.md
  • Architecture output: .aha-loop/project.architecture.md

The orchestrator will provide the actual paths in the prompt context.


The Job

  1. Read project.vision-analysis.md for requirements
  2. Research candidate technologies for each layer
  3. Evaluate and compare options
  4. Make decisions with documented rationale
  5. Design system architecture
  6. Output project.architecture.md

Core Principles

1. Prefer Latest Stable Versions

Always use the latest stable version of libraries unless there's a specific reason not to.

markdown
## Version Selection Process

1. Query official source for latest version:
   - Rust: crates.io API or `cargo search`
   - Node: npmjs.com or `npm view [pkg] version`
   - Python: pypi.org or `pip index versions`

2. Check release date and stability:
   - Released > 2 weeks ago (not bleeding edge)
   - No critical issues in GitHub issues
   - Changelog shows no breaking changes from common patterns

3. Document the version and why:
   - Record in project.architecture.md
   - Add to knowledge/project/decisions.md
2. Consider Long-term Maintenance
  • Active community and regular updates
  • Good documentation
  • Large ecosystem of plugins/extensions
  • Backed by reputable organization or strong community
3. Evaluate Total Cost
  • Learning curve for the team/AI
  • Bundle size / binary size
  • Runtime performance
  • Development velocity

Research Process

Step 1: Identify Technology Layers

Based on project type, identify which layers need decisions:

LayerExamples
LanguageRust, TypeScript, Python, Go
Frontend FrameworkReact, Vue, Svelte, SolidJS
Backend FrameworkAxum, Actix, Express, FastAPI
DatabasePostgreSQL, SQLite, MongoDB
ORM/Query BuilderDiesel, SQLx, Prisma, Drizzle
AuthenticationJWT, Sessions, OAuth providers
DeploymentDocker, Serverless, VPS
TestingBuilt-in, Jest, Pytest, Vitest
Step 2: Research Each Layer

For each layer requiring a decision:

  1. Identify 2-4 candidates - Don't over-research
  2. Fetch source code if needed for deep understanding
  3. Check latest versions - Use web search or package registry
  4. Read documentation - Understand core concepts
  5. Compare tradeoffs - Performance, DX, ecosystem
Show full SKILL.md (141 more words)Show less
Step 3: Use Structured Comparison
markdown
## [Layer Name] Decision

### Candidates

| Criterion | Option A | Option B | Option C |
|-----------|----------|----------|----------|
| Latest Version | v1.2.3 | v2.0.0 | v0.9.0 |
| Release Date | 2026-01-15 | 2026-01-20 | 2025-12-01 |
| GitHub Stars | 45k | 30k | 15k |
| Bundle Size | 50kb | 80kb | 30kb |
| Learning Curve | Medium | Low | High |
| Documentation | Excellent | Good | Fair |
| TypeScript Support | Native | Via types | Partial |
| Community Activity | Very Active | Active | Moderate |

### Decision: [Option B]

### Rationale
- [Reason 1]
- [Reason 2]
- [Reason 3]

### Tradeoffs Accepted
- [What we're giving up]
- [Mitigation strategy if any]
Step 4: Check Compatibility

Before finalizing:

  • Verify all chosen technologies work together
  • Check for known integration issues
  • Ensure versions are compatible
  • Test with a minimal proof-of-concept if uncertain

Version Research Commands

Rust (crates.io)
bash
# Get latest version
curl -s "https://crates.io/api/v1/crates/tokio" | jq '.crate.max_stable_version'

# Or use cargo
cargo search tokio --limit 1
Node.js (npm)
bash
# Get latest version
npm view react version

# Get all versions
npm view react versions --json
Check GitHub for Activity
bash
# Using gh CLI
gh api repos/tokio-rs/tokio --jq '.pushed_at, .stargazers_count'

Architecture Design

After technology decisions, design the architecture:

1. Component Diagram
markdown
## System Components

[Component A] --> [Component B] --> [Component C]
       |                               |
       v                               v
  [Database]                    [External API]
2. Data Flow

Document how data flows through the system:

  • User inputs
  • Processing steps
  • Storage points
  • Output paths
3. Directory Structure

Propose the project structure:

project/
├── src/
│   ├── main.rs
│   ├── api/
│   ├── db/
│   └── ...
├── tests/
├── Cargo.toml
└── ...
4. Key Patterns

Document architectural patterns to follow:

  • Error handling approach
  • Logging strategy
  • Configuration management
  • Testing approach

Output: project.architecture.md

markdown
# Project Architecture

**Generated:** [timestamp]
**Based on:** project.vision-analysis.md

## Technology Stack

### Core Technologies

| Layer | Technology | Version | Rationale |
|-------|------------|---------|-----------|
| Language | Rust | 1.75 | Performance, safety |
| Web Framework | Axum | 0.7.4 | Ergonomic, async |
| Database | SQLite | 3.45 | Simple, embedded |
| ORM | SQLx | 0.7.3 | Compile-time checks |

### Development Tools

| Tool | Version | Purpose |
|------|---------|---------|
| cargo-watch | 8.5.2 | Auto-rebuild |
| sqlx-cli | 0.7.3 | Migrations |

## Architecture Decisions

### ADR-001: [Decision Title]

**Context:** [Why this decision was needed]
**Decision:** [What was decided]
**Rationale:** [Why this option]
**Consequences:** [Impact of decision]

### ADR-002: ...

## System Design

### Component Overview

[Diagram or description]

### Data Flow

[How data moves through system]

### Directory Structure

[Proposed structure]


## Key Patterns

### Error Handling
[Approach]

### Configuration
[Approach]

### Testing Strategy
[Approach]

## Dependencies

### Production Dependencies

```toml
[dependencies]
axum = "0.7.4"
tokio = { version = "1.35", features = ["full"] }
sqlx = { version = "0.7.3", features = ["sqlite", "runtime-tokio"] }
Development Dependencies
toml
[dev-dependencies]

Security Considerations

  • [Security item 1]
  • [Security item 2]

Performance Considerations

  • [Performance item 1]
  • [Performance item 2]

Deployment Strategy

[How the project will be deployed]

Next Steps

  1. Initialize project structure
  2. Set up CI/CD
  3. Begin roadmap planning

---

## Integration with Orchestrator

After architecture design:

1. Save `project.architecture.md` to project root
2. Update `knowledge/project/decisions.md` with ADRs
3. Signal completion to orchestrator
4. Roadmap Skill uses architecture as input

---

## Checklist

Before completing architecture:

- [ ] All technology layers evaluated
- [ ] Latest stable versions verified for each choice
- [ ] Compatibility between choices confirmed
- [ ] Decisions documented with rationale
- [ ] Directory structure proposed
- [ ] Key patterns defined
- [ ] Dependencies listed with versions
- [ ] ADRs recorded in knowledge/project/decisions.md
- [ ] Architecture saved to `project.architecture.md`

---

## Example: Web App Architecture

**Input:** Vision analysis showing PWA finance tracker

**Output:**

```markdown
# Project Architecture

## Technology Stack

### Core Technologies

| Layer | Technology | Version | Rationale |
|-------|------------|---------|-----------|
| Language | TypeScript | 5.3.3 | Type safety, ecosystem |
| Framework | SvelteKit | 2.5.0 | Fast, simple, SSR+SPA |
| Styling | Tailwind CSS | 3.4.1 | Utility-first, fast |
| Database | IndexedDB (Dexie) | 4.0.1 | Offline-first PWA |
| Build | Vite | 5.0.12 | Fast, modern |

### PWA Stack

| Component | Technology | Version |
|-----------|------------|---------|
| Service Worker | Workbox | 7.0.0 |
| Manifest | Vite PWA Plugin | 0.17.4 |

## Architecture Decisions

### ADR-001: SvelteKit over React/Next.js

**Context:** Need a modern frontend framework for PWA
**Decision:** Use SvelteKit 2.x
**Rationale:**
- Smaller bundle size (critical for PWA)
- Built-in SSR and static generation
- Simpler mental model than React
- Excellent TypeScript support
**Consequences:** Smaller community than React, but sufficient for this project.

### ADR-002: Dexie for IndexedDB

**Context:** Need offline data storage
**Decision:** Use Dexie.js 4.x wrapper for IndexedDB
**Rationale:**
- Promise-based API
- Excellent TypeScript support
- Reactive queries
- Well-maintained
**Consequences:** Additional 30kb bundle, but worth the DX improvement.

© YougLin-dev, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/architect of YougLin-dev/Aha-Loop.

Open the folder on GitHubat commit 8d799b2

Compare with similar skills

Architect next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Architect compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Architect this skillYougLin-dev/Aha-Loop181—~2.2kAutomated safety check: PassMIT
Rustpgdogdev/pgdog5.6k—~1.9kAutomated safety check: NotesAGPL-3.0
Mail Timeveliovgroup/mail-time143—~1kAutomated safety check: PassBSD-3-Clause
Tgf Server Devthkhxm/tgf128—~1.3kAutomated safety check: NotesMIT
Pixel Perfect ReplicationYu-369/VibeCurb980—~8.7kAutomated safety check: PassMIT
Azure Storagemicrosoft/GitHub-Copilot-for-Azure2552 repos~1.3kAutomated safety check: PassMIT

Similar skills

  • Rust

    pgdogdev/pgdog

    Rust coding best practices for idiomatic, efficient, and maintainable code.

    5.6k GitHub stars~1.9k tokensUpdated today
    DatabasesAuto-check: notes
  • Mail Time

    veliovgroup/mail-time

    A skill your agent uses when building, wiring, reviewing, or debugging MailTime and ostrio:mailer email queues for horizontally scaled Node.js, Bun, or Meteor apps.

    143 GitHub stars~1k tokensUpdated 6 days ago
    DatabasesAuto-check passed
  • Tgf Server Dev

    thkhxm/tgf

    基于 tgf v2(github.com/thkhxm/tgf/v2)用确定性的 tgfctl 工作流创建、验证和维护 Go 游戏服务器项目。

    128 GitHub stars~1.3k tokensUpdated 2 mo ago
    DatabasesAuto-check: notes
  • Image-to-code replication pipeline. An agent skill from Yu-369/VibeCurb.

    980 GitHub stars~8.7k tokensUpdated 2 mo ago
    DatabasesAuto-check passed
  • Azure Storage

    microsoft/GitHub-Copilot-for-Azure

    Official

    Azure Storage Services including Blob Storage, File Shares, Queue Storage, Table Storage, and Data Lake.

    255 GitHub starsUsed in 2 repos~1.3k tokens
    DatabasesAuto-check passed
  • Configure REST Cache

    strapi-community/plugin-rest-cache

    Choose and write a Strapi REST Cache configuration for a specific use case.

    155 GitHub stars~1.1k tokensUpdated 9 days ago
    DatabasesAuto-check passed

More from YougLin-dev/Aha-Loop

All 15 skills in this repo
  • God Member

    YougLin-dev/Aha-Loop

    Defines God Committee member behavior and responsibilities with oversight authority.

    181 GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check passed
  • Doc Review

    YougLin-dev/Aha-Loop

    Reviews and cleans up outdated documentation. An agent skill from YougLin-dev/Aha-Loop.

    181 GitHub stars~1.5k tokensUpdated 8 mo ago
    Auto-check passed
  • God Consensus

    YougLin-dev/Aha-Loop

    Guides God Committee members through consensus-building for collective decisions.

    181 GitHub stars~2k tokensUpdated 8 mo ago
    Auto-check passed
  • God Intervention

    YougLin-dev/Aha-Loop

    Guides God Committee members through executing interventions.

    181 GitHub stars~2.3k tokensUpdated 8 mo ago
    Auto-check passed
  • Parallel Explore

    YougLin-dev/Aha-Loop

    Guides parallel exploration of multiple implementation approaches using git worktrees.

    181 GitHub stars~1.9k tokensUpdated 8 mo ago
    Auto-check passed
  • Plan Review

    YougLin-dev/Aha-Loop

    Reviews and adjusts PRD plans based on research findings. An agent skill from YougLin-dev/Aha-Loop.

    181 GitHub stars~1.8k tokensUpdated 8 mo ago
    Auto-check passed

Questions about Architect

What does Architect do?

Designs system architecture and selects technology stack based on vision analysis. Architect is an agent skill from YougLin-dev/Aha-Loop. Designs system architecture and selects technology stack based on vision analysis.

When should I use Architect?

Architect fits situations like: : design architecture; select tech stack; choose framework.

How do I install Architect in Claude Code?

Run `npx skills add YougLin-dev/Aha-Loop --skill architect -a claude-code`. Or copy the skill folder (.agents/skills/architect in YougLin-dev/Aha-Loop) into .claude/skills/architect in your project. Claude Code loads it when a task matches its description.

How do I install Architect in Codex?

Run `npx skills add YougLin-dev/Aha-Loop --skill architect -a codex`. Or copy the skill folder (.agents/skills/architect in YougLin-dev/Aha-Loop) into .agents/skills/architect in your project. Codex loads it when a task matches its description.

Can I use Architect in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add YougLin-dev/Aha-Loop --skill architect -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/architect, .gemini/skills/architect, .github/skills/architect and .opencode/skills/architect in your project.

What does Architect need to run?

Going by SKILL.md and its folder, Architect needs the command-line tools its instructions call (npm, curl, jq, cargo and gh). Our summary lists: Node.js; Docker.

Does Architect access the network?

SKILL.md names 1 domain. In commands or code: crates.io; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Architect safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Architect use?

Architect is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Architect use?

About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Architect?

Skills that share tags, products or a category with Architect: Rust (pgdogdev/pgdog, 5.6k stars), Mail Time (veliovgroup/mail-time, 143 stars), Tgf Server Dev (thkhxm/tgf, 128 stars) and Pixel Perfect Replication (Yu-369/VibeCurb, 980 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Architect?

YougLin-dev (a GitHub user) maintains it in YougLin-dev/Aha-Loop, which has 181 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on February 3, 2026.

Source: YougLin-dev/Aha-Loop on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.