# Synthesis Code Planning

> Structured approach to code generation, implementing features, and writing code. Use when asked to generate code, implement a feature, write code, or tackle a coding task. Analyzes the task, generates multiple approaches with trade-offs, selects the optimal solution, and implements it.

- **Type:** Skill
- **Install:** `agentstack add skill-synthesisengineering-synthesis-skills-synthesis-code-planning`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [synthesisengineering](https://agentstack.voostack.com/s/synthesisengineering)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [synthesisengineering](https://github.com/synthesisengineering)
- **Source:** https://github.com/synthesisengineering/synthesis-skills/tree/main/synthesis-code-planning

## Install

```sh
agentstack add skill-synthesisengineering-synthesis-skills-synthesis-code-planning
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Code Planning

A structured methodology for approaching code tasks that produces higher-quality implementations by evaluating multiple approaches before committing to one.

## Inputs

Before generating code, gather three inputs:

1. **Task description** -- what needs to be built or changed
2. **Existing code** -- the current codebase or relevant files (if any)
3. **Contextual documentation** -- relevant API docs, framework guides, coding standards, or architectural decisions

## Process

### Step 1: Analyze

Carefully analyze the task description and existing code. Consider:

- What is the actual goal (not just the literal request)?
- What constraints does the existing code impose?
- What are the performance, maintainability, and correctness requirements?
- What best practices apply to this language, framework, or domain?

### Step 2: Generate approaches

Produce at least two distinct approaches to address the task. For each approach, document:

**Approach 1:** [Brief description]
- Pros:
  - [Advantage 1]
  - [Advantage 2]
- Cons:
  - [Drawback 1]
  - [Drawback 2]

**Approach 2:** [Brief description]
- Pros:
  - [Advantage 1]
  - [Advantage 2]
- Cons:
  - [Drawback 1]
  - [Drawback 2]

Generate more approaches when the problem space is ambiguous or when the first two approaches have significant trade-offs against each other.

### Step 3: Evaluate and select

Select the optimal solution and justify the choice with specific reasoning:

- Reference the pros and cons of each approach
- Explain why the chosen approach best addresses the task requirements
- Acknowledge what is sacrificed by not choosing the alternatives
- If the decision is close, state that explicitly

### Step 4: Implement

Implement the chosen solution by modifying or creating code:

- Mark changes clearly when modifying existing code
- Follow the conventions and patterns already present in the codebase
- Optimize for performance, maintainability, and adherence to best practices
- Include necessary error handling and edge case coverage

## When to skip multi-approach evaluation

For trivial changes (typo fixes, single-line config changes, renaming a variable), skip Steps 2-3 and implement directly. The threshold: if the implementation is obvious and unambiguous, proceed without generating alternatives.

## Principles

- **Framework-first**: prefer built-in features over custom solutions
- **Convention over configuration**: follow established patterns in the codebase
- **Root cause over symptom**: fix the underlying problem, not its surface manifestation
- **Less code is better**: a one-line config change beats 50 lines of custom code

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [synthesisengineering](https://github.com/synthesisengineering)
- **Source:** [synthesisengineering/synthesis-skills](https://github.com/synthesisengineering/synthesis-skills)
- **License:** Apache-2.0

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-synthesisengineering-synthesis-skills-synthesis-code-planning
- Seller: https://agentstack.voostack.com/s/synthesisengineering
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.