Skip to content
Agentmart
Submit a tool

clean-design

Turn requirements into use cases, stable policy boundaries, delivery and data boundaries, dependency direction, acceptance examples, and repository-owned…

Skill by shashank-sn

IndexedMIT
Write a review

Chalk Labs

Need help deploying clean-design?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

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/shashank-sn-clean-design

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

Turn requirements into use cases, stable policy boundaries, delivery and data boundaries, dependency direction, acceptance examples, and repository-owned architecture constraints. Use before implementing a feature, when splitting components, when a change crosses framework or vendor boundaries, or when architecture drift needs an explicit policy and graph check.

Use cases: design, data

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. Checked Oct 25, 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/clean-design

What's inside

Skill name
clean-design
Description
Turn requirements into use cases, stable policy boundaries, delivery and data boundaries, dependency direction, acceptance examples, and repository-owned architecture constraints. Use before implementing a feature, when splitting components, when a change crosses framework or vendor boundaries, or when architecture drift needs an explicit policy and graph check.
License
MIT
Instructions
34 lines in SKILL.md · view on GitHub

Files (3)

  • SKILL.md
  • agent.json
  • openai.yaml · agents/

SKILL.md (first lines)

# Clean Design

Define enough design intent to guide implementation and deterministic checks.

## Workflow

1. Write the actor, desired outcome, failure behavior, and boundary cases in implementation-neutral language.
2. Identify the business rules that should remain stable when UI, framework, database, vendor, or transport choices change.
3. Name components from repository concepts and assign each one or more repository-relative paths.
4. Declare permitted dependency directions and public surfaces. Record exclusions and temporary exceptions with concrete reasons.
5. Ask the repository's language or build tool to produce a dependency graph in the shared JSON format.
6. Run `clean-code architecture --policy <policy.json> --graph <graph.json>` and treat every reported path as mechanical evidence.
7. Keep semantic design questions for review: responsibility placement, use-case cohesion, volatility, and whether the declared components represent useful concepts.

## Decisions

- Keep inner policy independent of UI, persistence, frameworks, vendors, and delivery mechanisms.
- Pass dependencies through explicit arguments, interfaces, factories, or returned values.
- Put behavior near the data and policy it interprets, unless that would pull presentation or vendor details inward.
- Split components by change pressure and release responsibility. Avoid folders created solely to resemble an architecture diagram.
- Keep architecture policy repository-owned. Discovery may propose boundaries, while a person approves them.

## Evidence limits

The graph checker proves only the supplied file edges against the supplied policy. It cannot prove that the graph producer found every dependency, that a component owns the right responsibility, or that passing structure makes the product correct. Report those limits with the mechanical result.

## Safety

- Reject absolute, escaping, ambiguous, and undeclared paths.
- Require a reason for every exception.
- Keep generated-code and test exceptions narrow and visible.
- Report an exact cycle path instead of a generic cycle count.

From shashank-sn/clean-code, MIT.

More from shashank-sn/clean-code

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 21, 2026 (2 months ago)
Last release
Sep 17, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from shashank-sn

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get clean-design running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying clean-design?

CallGet help
Cite this page

clean-design skill. Agent Mart. https://agentmart.dev/skills/shashank-sn-clean-design (last updated 2026-10-24)