goal-backward-planning
CommunityPlan from outcomes with verifiable truths.
System Documentation
What problem does it solve?
This Skill helps you avoid building plans from activities by structuring work around an observable end state and the prerequisites that must be true for that goal to be considered complete.
Core Features & Use Cases
- Goal → Truths → Artifacts: translates outcomes into verifiable preconditions and the exact evidence you need to prove them.
- Waves-based parallelization: groups tasks by real dependency order so parallel work is safe and efficient.
- Checkpoint protocol: adds explicit human verification and irreversible decision gates to prevent moving forward without validation.
- Discovery levels: selects the minimum necessary investigation depth to reduce wasted context and over-researching.
A practical use case is planning a secure authentication change where you must define truths like token expiry behavior, required routes, and tests before deciding how to implement endpoints and middleware.
Quick Start
Use this skill to produce a goal-backward plan by describing your desired observable outcome, then asking it to derive verifiable truths, required artifacts, wave-based tasks, and checkpoints.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: goal-backward-planning Download link: https://github.com/paulinett1508-dev/SuperCartolaManagerv5-production/archive/main.zip#goal-backward-planning Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.