Use when breaking PonyBunny work into small, ordered, verifiable tasks with explicit dependencies and acceptance criteria.
Scanned 9/11/2026
Install to Claude Code
npx -y skills add ponybunny-ai/ponybunny --skill task-decomposition --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Task Decomposition?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ponybunny-ai-task-decomposition)More formats (shields.io, HTML) on the badges page.
---
name: task-decomposition
description: Use when breaking PonyBunny work into small, ordered, verifiable tasks with explicit dependencies and acceptance criteria.
---
# Task Decomposition
## Use this skill when
- turning a plan into implementation tasks
- splitting a complex migration into phases
- preparing generator-ready work
- reducing ambiguity before coding
## Goals
- reduce scope creep
- improve sequencing
- produce clear acceptance criteria
- separate implementation from validation
## Process
1. Define the target outcome.
2. List invariants and constraints.
3. Split by dependency.
4. Separate design, implementation, and verification tasks.
5. Add acceptance criteria to each task.
6. Add handoff expectations.
## Output contract
For each task return:
- task name
- objective
- dependencies
- affected files/modules
- acceptance criteria
- risks
- required handoff notes
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.