system-design
Draw system-design diagrams in ASCII with proper notation.
Skill by kanaad-lims
Chalk Labs
Need help deploying system-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/kanaad-lims-system-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
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/system-design
What's inside
- Skill name
system-design- Description
- Draw system-design diagrams in ASCII with proper notation.
- License
- MIT
- Instructions
- 87 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# System Design Skill ## 1. Understand the Problem - Identify users, core workflows, scope, constraints, and assumptions. - Ask clarifying questions only when missing information materially affects the design. - Never silently invent requirements. ## 2. Requirements List before designing: - Functional requirements and priorities. - Non-functional requirements: latency, throughput, availability, consistency, scalability, security, and durability. - Constraints, assumptions, and capacity estimates when relevant. ## 3. Component Inventory **High-level:** List major services, external systems, and data stores with their responsibilities. **Low-level:** Identify relevant internal modules, APIs, data models, queues, workers, caches, and processing stages. Explain each component's purpose. Avoid unnecessary decomposition. ## 4. Architecture Decisions Explain important choices, alternatives, and trade-offs. Consider communication protocols, databases, caching, consistency, partitioning, and deployment when relevant. Prefer the simplest architecture that satisfies the requirements. Never introduce technologies without justification. ## 5. Design Depth Adapt detail to the request: - Quick: Requirements, components, diagram, execution example. - Interview: Capacity estimates, architecture, trade-offs, bottlenecks. - Production: APIs, data models, failure handling, security, observability, deployment, and recovery. ## 6. ASCII Diagram Rules - Use ASCII only: +---+ boxes, --> arrows, [db: name] for storage, (queue: name) for queues, and o for users. - Use one primary component per box. - Label important connections with protocols, requests, events, or data. - Keep diagrams terminal-width friendly; prefer top-down layouts. - Split complex designs into multiple meaningful views. - Use consistent component names throughout. - Never use Mermaid, drawing code, or Markdown fences. ## 7. Architecture Views Include relevant views: - High-level architecture. - Low-level component design. - Request or event flow. - Data flow and storage architecture. Avoid redundant diagrams. ## 8. Execution Walkthrough After the diagram, trace one concrete operation end to end. Explain the request path, processing, storage interactions, response, and relevant error handling. Follow the diagram exactly. ## 9. Production Readiness Assess relevant failure modes, timeouts, retries, idempotency, consistency, bottlenecks, scaling, security, logging, metrics, and tracing. Separate essential requirements from future improvements. ## 10. Validation Before responding, verify: - Requirements map to components. - Components have clear responsibilities. - Arrows and data flows are complete. - Storage and external dependencies are explicit. - No unexplained components or dangling connections exist. - The execution example matches the diagram. - Complexity is justified. ## 11. Default Output Order 1. Problem and assumptions 2. Requirements and constraints 3. High-level components 4. Low-level components 5. Architecture decisions and trade-offs 6. ASCII diagrams 7. End-to-end example 8. Production concerns and limitations Omit irrelevant sections for simple requests. Use plain English, distinguish assumptions from facts, and prioritize correctness over complexity. ## Design Mode Selection Before designing, determine the required depth. If the user has not specified it, ask them to choose: 1. **Conceptual:** Basic components, simplified ASCII diagram, and a brief execution flow. 2. **System Design / Interview:** Requirements, capacity estimates, high-level and low-level components, architecture trade-offs, scaling, and bottlenecks. 3. **Production Grade:** Detailed architecture, APIs, data models, infrastructure, failure handling, security, observability, deployment, and recovery. Do not ask again if the user's request clearly establishes the desired depth. Adapt the output to the selected mode without including unnecessary sections.
From kanaad-lims/AgentHarness, MIT.
More from kanaad-lims/AgentHarness
- 0.550score
shell-usage
kanaad-lims
Run shell commands safely with user approval.
SkillAFreshness: AClaude Code +9 - 0.550score
arxiv-research
kanaad-lims
Find and cite arXiv papers for literature questions.
SkillAFreshness: AClaude Code +9 - 0.550score
task-planning
kanaad-lims
Plan multi-deliverable work with the todos tool.
SkillAFreshness: AClaude Code +9 - 0.550score
web-research
kanaad-lims
Answer general web questions with cited search results.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 13, 2026 (21 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/kanaad-lims/AgentHarness
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from kanaad-lims
- 0.550score
shell-usage
kanaad-lims
Run shell commands safely with user approval.
SkillAFreshness: AClaude Code +9 - 0.550score
arxiv-research
kanaad-lims
Find and cite arXiv papers for literature questions.
SkillAFreshness: AClaude Code +9 - 0.550score
task-planning
kanaad-lims
Plan multi-deliverable work with the todos tool.
SkillAFreshness: AClaude Code +9 - 0.550score
web-research
kanaad-lims
Answer general web questions with cited search results.
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 system-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
system-design skill. Agent Mart. https://agentmart.dev/skills/kanaad-lims-system-design (last updated 2026-10-24)