arch-design
Design or revise a software architecture from the actual project context, constraints, and user journey.
Skill by AnikRifat
Chalk Labs
Need help deploying arch-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.
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/anikrifat-arch-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.
About
Use cases: design, data
Reviews
Write a reviewNo 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/arch-design
What's inside
- Skill name
arch-design- Description
- Design or revise a software architecture from the actual project context, constraints, and user journey. Use for material boundaries, data flow, integration, or scale decisions; do not implement unrelated features.
- License
- unknown
- Instructions
- 9 lines in SKILL.md · view on GitHub
Files (4)
- SKILL.md
- openai.yaml · agents/
- architecture.md · references/
- selection.md · references/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from AnikRifat/full-stack-coding-setup
- 0.565score
loop-delivery
AnikRifat
Run Anik's idea-to-MVP or software delivery as an interactive, goal-driven loop with connected micro-skills and bounded sub-agents.
SkillAFreshness: AClaude Code +9 - 0.565score
project-init
AnikRifat
Establish a working project in any folder — scaffold a blank one with native tools, or adopt an existing codebase by learning its real stack, conventions, and…
SkillAFreshness: AClaude Code +9 - 0.561score
loop-code-audit
AnikRifat
Autonomously audit, prioritize, repair, verify, and re-audit code through bounded sub-agents.
SkillAFreshness: AClaude Code +9 - 0.559score
machine-init
AnikRifat
Inspect, prepare, and health-check Anik's PC-level Codex or Claude environment, reusable workspace guidance, and local agent tooling.
SkillAFreshness: AClaude Code +9 - 0.556score
loop-interface-audit
AnikRifat
Autonomously audit, prioritize, fix, and verify UI and UX issues through a context-aware, sub-agent-driven loop.
SkillAFreshness: AClaude Code +9 - 0.556score
loop-product-reforge
AnikRifat
Diagnose, redesign, rebuild, and continuously improve products.
SkillAFreshness: AClaude Code +9 - 0.521score
update-setup
AnikRifat
Inspect Anik's full-stack coding setup repository for git updates, pull new releases or commits, and erase stale copies to refresh skills, rules, and…
SkillBFreshness: BClaude Code +9 - 0.516score
bug-investigate
AnikRifat
Investigate and repair a reproducible software failure using evidence from the project, runtime, and tests.
SkillBFreshness: BClaude Code +9 - 0.516score
flow-design
AnikRifat
Analyze or improve user journeys, task flows, interaction logic, and usability from the product goal and actual audience.
SkillBFreshness: BClaude Code +9 - 0.516score
delivery-plan
AnikRifat
Turn a goal or feature outcome into a goal-driven delivery plan with executable increments, dependencies, acceptance criteria, and meaningful checks.
SkillBFreshness: BClaude Code +9 - 0.516score
code-implement
AnikRifat
Implement an agreed software change using the repository's stack, conventions, and relevant checks.
SkillBFreshness: BClaude Code +9 - 0.516score
behavior-verify
AnikRifat
Verify requested software behavior with the most meaningful checks available in the current project.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 17, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from AnikRifat
- 0.565score
loop-delivery
AnikRifat
Run Anik's idea-to-MVP or software delivery as an interactive, goal-driven loop with connected micro-skills and bounded sub-agents.
SkillAFreshness: AClaude Code +9 - 0.565score
project-init
AnikRifat
Establish a working project in any folder — scaffold a blank one with native tools, or adopt an existing codebase by learning its real stack, conventions, and…
SkillAFreshness: AClaude Code +9 - 0.561score
loop-code-audit
AnikRifat
Autonomously audit, prioritize, repair, verify, and re-audit code through bounded sub-agents.
SkillAFreshness: AClaude Code +9 - 0.559score
machine-init
AnikRifat
Inspect, prepare, and health-check Anik's PC-level Codex or Claude environment, reusable workspace guidance, and local agent tooling.
SkillAFreshness: AClaude Code +9 - 0.556score
loop-product-reforge
AnikRifat
Diagnose, redesign, rebuild, and continuously improve products.
SkillAFreshness: AClaude Code +9 - 0.556score
loop-interface-audit
AnikRifat
Autonomously audit, prioritize, fix, and verify UI and UX issues through a context-aware, sub-agent-driven loop.
SkillAFreshness: AClaude Code +9
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 arch-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.
Cite this page
arch-design skill. Agent Mart. https://agentmart.dev/skills/anikrifat-arch-design (last updated 2026-10-24)