Can I update an existing plan with this skill?

Yes, it features a dedicated 'Update a Plan' workflow that identifies deltas in requirements or exploration results and ensures the plan remains internally consistent.

What is the 'Confidence Gate' feature?

The Confidence Gate is a mandatory self-assessment step where Claude must confirm it has enough information to proceed. If not, it must ask the user questions or explore the codebase before planning.

Does it support visual architecture changes?

Yes, the skill includes specific templates for illustrating 'Before and After' states of project structures, tech stacks, and system architectures using box-drawing characters.

Why should I use the write-plan skill in Claude Code?

It ensures Claude follows a rigorous planning phase before writing code, which reduces errors, prevents guessing, and ensures that all changes are backed by a solid testing strategy.

How does this skill handle bug fixes?

It mandates a 'Regression-First' approach, requiring a failing reproducer test to be planned and executed before any implementation tasks for the fix are allowed.

Amplify Systematic Planning

Name: Amplify Systematic Planning
Author: WeZZard

byWeZZard

•

生产力与工作流

Enforces a rigorous, template-driven planning workflow for Claude Code sessions to ensure architectural consistency and comprehensive test coverage.

The write-plan skill provides a standardized framework for Claude to follow before executing any code changes. It mandates a multi-step process: assessing component readiness, identifying knowledge gaps through a 'confidence gate', and drafting detailed plans using specialized templates for project structure, tech stack, and architecture. By requiring explicit testing strategies—including unit, integration, and E2E tests—and prioritizing regression-first bug fixes, it ensures that AI-generated work is grounded in evidence, documented thoroughly, and verified against specific requirements.

主要功能

01Mandatory confidence-gate assessment to eliminate AI guessing

02Comprehensive testing strategy enforcement including regression-first bug fixes

03Hypothesis tracking and human-verification gate identification

04Automated task dependency mapping and verification specifications

059 GitHub stars

06Standardized templates for visualizing project structure and architecture

使用场景

01Refactoring legacy codebases requiring detailed architectural documentation

02Architecting new features with complex component and file dependencies

03Implementing bug fixes with a mandatory 'reproducer-first' regression approach

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add wezzard/skills write-plan

For use in Claude.ai and ChatGPT