Skip to content
Agentmart
Submit a tool

architecture-planning

Produce a concise architecture plan with boundaries, alternatives, delivery steps and verification.

Skill by atstaeff

IndexedMIT★ 3
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/atstaeff-architecture-planning

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Produce a concise architecture plan with boundaries, alternatives, delivery steps and verification.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/architecture-planning

What's inside

Skill name
architecture-planning
Description
Produce a concise architecture plan with boundaries, alternatives, delivery steps and verification.
License
MIT
Instructions
30 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • architecture-planning.md · references/

SKILL.md (first lines)

# Architecture Planning

## Workflow

1. Read the actual assignment, use cases, current architecture, data flow/lifecycle,
   relevant decisions and affected consumers. Establish scale and operational constraints.
   Distinguish intended behavior, implemented behavior and unresolved assumptions.
2. Identify the outcome and the few quality attributes that determine the choice. Use
   stimulus/response/measure scenarios instead of unsupported claims such as scalable or clean.
3. Compare the current design and the simplest viable alternative. Include data meaning,
   dependency direction, trust boundaries, compatibility, operating/change cost and recovery.
4. Make abstractions earn their indirection. Propose a replaceable boundary for real
   variation; do not add speculative frameworks or service splits by default.
5. Sequence small complete increments with checks derived from criteria and contracts.
   Name consequential uncertainties and the owner who can decide them.
6. Preserve the plan in its existing home. Draft significant rationale at the designated
   decision home while alternatives are known. An accepted ADR and its replacement status
   constrain dependent work; a proposal does not silently revoke them.

## Focused references

Choose a specific boundary skill directly when no system-level plan is needed: API design,
security, performance, domain modeling or cloud deployment. Do not chain umbrella skills.


- [Detailed examples](references/architecture-planning.md): load only the section relevant to the task.
- [Quality standard](../../../toolkit/QUALITY-STANDARD.md) and
  [architecture review](../../../templates/architecture/architecture-review.md): use for the affected quality and decision boundary.

From atstaeff/ai-agents, MIT.

More from atstaeff/ai-agents

Signals

Stars
3
Forks
0
Open issues
0
Last commit (this folder)
Oct 23, 2026 (6 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from atstaeff

Cite this page

architecture-planning skill. Agent Mart. https://agentmart.dev/skills/atstaeff-architecture-planning (last updated 2026-10-24)