Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Integrate Design Into Workflow

ASecurity

Design a Uniswap integration architecture. Use when user is building a project that needs to integrate Uniswap and wants recommendations on integration method (Trading API vs SDK vs direct contract), architecture patterns, required dependencies, and security considerations.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgoreactapifrontendbackendsecurity

Works with

cliapimcp

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill integrate-design-into-workflow --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Integrate Design Into Workflow?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Integrate Design Into Workflow
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-integrate-design-into-workflow/badge)](https://www.skillsdirectory.com/skills/rondoflow-integrate-design-into-workflow)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: integrate-design-into-workflow
description: "Design a Uniswap integration architecture. Use when user is building a project that needs to integrate Uniswap and wants recommendations on integration method (Trading API vs SDK vs direct contract), architecture patterns, required dependencies, and security considerations."
category: "Finance & Crypto"
author: community
version: "0.1.0"
icon: coins
---

# Design Integration

## Overview

Designs a complete Uniswap integration architecture for any project by delegating to the `integration-architect` agent. Produces a comprehensive blueprint covering: integration method recommendation (Trading API vs Universal Router SDK vs direct contract vs V4 hooks), component architecture, dependency list with versions, security review with mitigations, and ordered implementation plan.

## When to Use

Activate when the user asks:

- "Help me integrate Uniswap"
- "Design a swap integration"
- "Architecture for a DEX aggregator"
- "How to build an arbitrage bot"
- "Uniswap integration plan"
- "How should I add swaps to my dApp?"
- "Best way to integrate Uniswap in my backend"
- "Architecture for a DeFi protocol that uses Uniswap"
- "What SDK should I use for Uniswap?"

## Parameters

| Parameter | Required | Default | Description |
| --- | --- | --- | --- |
| projectType | Yes | -- | Type of project (e.g., "DeFi dashboard", "arb bot", "wallet app", "DeFi protocol") |
| functionality | Yes | -- | Required Uniswap functionality: "swap", "LP", "both", or "custom" |
| environment | No | Auto-detect | Execution environment: "frontend", "backend", "smart contract", or "full-stack" |
| chains | No | ethereum | Target chain(s): single chain name or comma-separated list |
| scale | No | -- | Expected scale: transaction volume, concurrent users, latency requirements |

## Workflow

1. **Extract parameters** from the user's request: identify the project type, required functionality, target environment, chains, and scale requirements. If the user has an existing codebase, note it for the agent to analyze.

2. **Delegate to integration-architect**: Invoke `Task(subagent_type:integration-architect)` with the full context. The integration-architect will:
   - Understand the project context and requirements
   - Evaluate integration methods and recommend primary + fallback
   - Design the component architecture with data flow
   - Identify all dependencies (NPM packages, APIs, infrastructure)
   - Perform a security review with attack vectors and mitigations
   - Produce an ordered implementation plan with effort estimates

3. **Present the blueprint** to the user covering:
   - Integration method recommendation with clear rationale
   - Architecture overview (components, data flow, error handling)
   - Complete dependency list with versions and purposes
   - Security considerations with specific mitigations
   - Step-by-step implementation order with effort estimates
   - Overall complexity assessment

## Output Format

Present a structured integration blueprint:

```text
Integration Blueprint: DeFi Dashboard with Swap (Ethereum + Base)

  Recommended Method: Trading API (primary), Universal Router SDK (fallback)
  Rationale: Trading API provides optimized routing with minimal frontend
             complexity. Fallback to SDK for advanced use cases or API downtime.

  Architecture:
    User -> QuoteService -> ApprovalManager -> SwapExecutor -> Wallet -> Chain
    
    Components:
      QuoteService:      Fetches and caches quotes from Trading API
      ApprovalManager:   Manages Permit2 approvals and allowances
      SwapExecutor:      Constructs and submits swap transactions
      ChainManager:      Multi-chain config and RPC connections

  Dependencies:
    @uniswap/sdk-core    ^5.8.0    Token and price primitives
    viem                 ^2.21.0   Ethereum client
    wagmi                ^2.14.0   React wallet hooks
    @tanstack/react-query ^5.0.0   Data fetching and caching

  Security:
    - Stale quotes: Refresh every 15s, enforce deadline (block.timestamp + 300s)
    - Approvals: Permit2 with exact amounts and 30-min expiry
    - Key management: wagmi wallet connection only, never handle keys

  Implementation Order:
    1. Wallet connection (wagmi)           — 1 day
    2. Chain configuration                 — 0.5 days
    3. Quote fetching service              — 1 day
    4. Permit2 approval flow               — 1 day
    5. Swap execution and tracking         — 1.5 days
    6. Error handling and retry logic      — 1 day

  Complexity: Medium
```

## Important Notes

- This skill delegates entirely to the `integration-architect` agent -- it does not call MCP tools directly.
- The blueprint is tailored to the specific project type and requirements -- not a generic template.
- For existing codebases, the agent will analyze the current code and recommend integration patterns that fit the existing architecture.
- The implementation order considers dependencies between components -- follow the order for smoothest development.
- Always uses viem (not ethers.js) and Permit2 (not legacy approve) per project conventions.

## Error Handling

| Error | User-Facing Message | Suggested Action |
| --- | --- | --- |
| `VAGUE_PROJECT` | "Need more detail about your project to recommend an integration approach." | Describe project type and what Uniswap functionality is needed |
| `DEPRECATED_APPROACH` | "The requested integration method is deprecated. Recommending alternatives." | Follow the updated recommendation |
| `UNSUPPORTED_CHAIN` | "Uniswap is not deployed on the specified chain." | Choose from the 11 supported chains |
| `CONFLICTING_REQUIREMENTS` | "The requirements conflict (e.g., frontend + direct contract calls)." | Clarify the execution environment and adjust expectations |

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693161 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →