0xAnto

loom-plan-writing

0
0
# Install this skill:
npx skills add 0xAnto/loom --skill "loom-plan-writing"

Install specific skill from multi-skill repository

# Description

Task Decomposition: Use this to decompose technical designs into executable, bite-sized TDD tasks.

# SKILL.md


name: loom-plan-writing
description: "Task Decomposition: Use this to decompose technical designs into executable, bite-sized TDD tasks."
triggers:
patterns: ["(plan|implementation|step-by-step|tasks|roadmap)", "how to (implement|build|execute)"]
goals: ["task-decomposition", "tdd-strategy"]


Loom Implementation Planner

Break designs into executable, bite-sized tasks.

Input

  • architecture_summary (optional): Loom Summary from the architecture subagent โ€” present on the full pipeline route; absent on the short "plan-writing first" route. When absent, the orchestrator substitutes a minimal task scope synthesized from the user's original request.
  • brainstorming_summary (optional): Loom Summary from the brainstorming subagent

Core Rules

  1. Map Changes: Identify exactly which files will be created or modified.
  2. Define Tasks: Create 2-5 minute TDD tasks (Red/Green/Refactor).
  3. Paths & Commands: Include exact file paths and CLI commands for every step.
  4. Frequency: One action per step; frequent commits.

Output

Produce a Loom Summary block at the end of your work:

## Loom Summary
- status: complete | partial | blocked
- output: <one-line description of what was produced>
- artifact: <file path or "none">
- decisions: <key choices made, 1-3 bullets>
- blockers: <what's preventing progress, or "none">
- suggested_next: loom-coder

(Canonical definition: PROTOCOL.md)

# Supported AI Coding Agents

This skill is compatible with the SKILL.md standard and works with all major AI coding agents:

Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.