How do I install the Plan Implementation skill?

Run npx skillmds@latest add uniswap/plan-implementation in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Plan Implementation safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Plan Implementation?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Plan Implementation free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Plan Implementation?

uniswap (@uniswap) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Plan Implementation by uniswap — Agent Skill

Name: Plan Implementation
Author: uniswap

Plan Implementation

Create implementation plans for features and changes. Use when user says "plan how to implement user authentication", "how should I add dark mode to the app", "what's the best way to refactor the database layer", "create a plan for migrating to the new API", or "I need to implement [feature] - help me plan it out".

uniswap 2cb2b7b 2 files · 9.2 KB Updated Sep 17, 2026

File contents

Implementation Planner

Create clear, actionable implementation plans through collaborative multi-agent discussion and refinement.

When to Activate

User wants to implement a new feature
User asks "how should I implement X?"
User wants to add functionality
User needs to refactor or migrate code
Complex bug fixes requiring planning
Architectural changes or design decisions
Any task that benefits from structured planning

Quick Process

Analyze Context: Understand the task, leverage any prior exploration
Select Agents: Choose specialists for the dimensions the task actually raises, up to 10
Collaborative Discussion: Multi-agent refinement, up to the round ceiling in the table below
Synthesize Plan: Generate comprehensive implementation plan
Output File: Write plan to .claude-output/plan-[timestamp].md

Complexity-Based Planning

Agent and round counts are ceilings, not quotas. Staff only the dimensions the task actually raises, and do not spawn an agent for analysis that would finish in a handful of direct tool calls - plan the simple case yourself.

Task Type	Agents (max)	Rounds (max)	Plan Length
Simple (bug fix, minor feature)	up to 2	1	~100-200 lines
Medium (features, refactors)	up to 5	2	~200-400 lines
Complex (architecture, major features)	up to 10	3	~400-600 lines

Plan Structure

Generated plans include:

Overview - High-level summary
Scope - What will/won't be implemented
Current State - Relevant architecture and files
API Design (optional) - Interfaces and data structures
Implementation Steps - Clear sequential steps (5-7 typical)
Files Summary - Files to create/modify
Critical Challenges (optional) - Risks and mitigations
Agent Collaboration Summary - Consensus and trade-offs

Workflow Integration

This is Step 2 of the implementation workflow:

Explore → 2. Plan (this) → 3. Review → 4. Execute

Automatically uses context from prior exploration
Output plan can be reviewed with /review-plan
Approved plans execute with execute-plan skill

Detailed Reference

For agent selection, discussion protocols, and output formats, see planning-guide.md.

---name: plan-implementationdescription: Create implementation plans for features and changes. Use when user says "plan how to implement user authentication", "how should I add dark mode to the app", "what's the best way to refactor the database layer", "create a plan for migrating to the new API", or "I need to implement [feature] - help me plan it out".---# Implementation PlannerCreate clear, actionable implementation plans through collaborative multi-agent discussion and refinement.## When to Activate- User wants to implement a new feature- User asks "how should I implement X?"- User wants to add functionality- User needs to refactor or migrate code- Complex bug fixes requiring planning- Architectural changes or design decisions- Any task that benefits from structured planning## Quick Process1. **Analyze Context**: Understand the task, leverage any prior exploration2. **Select Agents**: Choose specialists for the dimensions the task actually raises, up to 103. **Collaborative Discussion**: Multi-agent refinement, up to the round ceiling in the table below4. **Synthesize Plan**: Generate comprehensive implementation plan5. **Output File**: Write plan to `.claude-output/plan-[timestamp].md`## Complexity-Based PlanningAgent and round counts are **ceilings, not quotas**. Staff only the dimensions the task actually raises, and do not spawn an agent for analysis that would finish in a handful of direct tool calls - plan the simple case yourself.| Task Type | Agents (max) | Rounds (max) | Plan Length || -------------------------------------- | ------------ | ------------ | -------------- || Simple (bug fix, minor feature) | up to 2 | 1 | ~100-200 lines || Medium (features, refactors) | up to 5 | 2 | ~200-400 lines || Complex (architecture, major features) | up to 10 | 3 | ~400-600 lines |## Plan StructureGenerated plans include:1. **Overview** - High-level summary2. **Scope** - What will/won't be implemented3. **Current State** - Relevant architecture and files4. **API Design** (optional) - Interfaces and data structures5. **Implementation Steps** - Clear sequential steps (5-7 typical)6. **Files Summary** - Files to create/modify7. **Critical Challenges** (optional) - Risks and mitigations8. **Agent Collaboration Summary** - Consensus and trade-offs## Workflow IntegrationThis is **Step 2** of the implementation workflow:1. Explore → 2. **Plan** (this) → 3. Review → 4. Execute- Automatically uses context from prior exploration- Output plan can be reviewed with `/review-plan`- Approved plans execute with `execute-plan` skill## Detailed ReferenceFor agent selection, discussion protocols, and output formats, see [planning-guide.md](planning-guide.md).

Frequently asked questions