# Validate Leaves

> Quality check on leaf nodes of the GoalTree. Verify each leaf is specific enough, actionable, and that the set of leaves fully covers the top goal. Flag issues for further decomposition.

- Skill: `yogsoth-ai/validate-leaves` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add yogsoth-ai/validate-leaves`
- Raw SKILL.md: https://api.skillmd.com/api/skills/yogsoth-ai/validate-leaves/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: yogsoth-ai (https://skillmd.com/u/yogsoth-ai)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/yogsoth-ai/validate-leaves

---


# Validate Leaves

Ensure GoalTree leaf nodes are high quality.

## Execution

Subagent — spawned via `subagent-spawning/spawn-agent` skill.

## Input

- GoalTree (full structure)
- Top goal statement

## Checks

- Is each leaf specific enough to act on?
- Is each leaf verifiable (can you tell when it's done)?
- Does the complete set of leaves cover the top goal?

## Output

Validation report — which leaves pass, which need further decomposition, coverage gaps.

<!-- BEGIN available-tables (generated) -->

## Available SOPs

Optional, no fixed order; the final leaf is always a sop.

| SOP | When to use |
| --- | --- |
| spawn-agent | Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent. |

<!-- END available-tables (generated) -->