rootnode-reasoning-blockslisted
Install: claude install-skill drayline/rootnode-skills
# Reasoning Approach Selection for Claude Prompts
> **Calibration:** Tier 1 (Model-compatible) - runs cleanly on the current dual-primary tier (Opus 5, Sonnet 5) as well as Haiku 4.5 with extended thinking. Structured retrieval, rule evaluation, or template lookup - output shape does not depend on model class. Correct-shape output also on Opus 4.8 (fallback-graceful) and Sonnet 4.6 (legacy-graceful). See repository README for model compatibility.
Select the reasoning approach that matches how the task requires Claude to think. The reasoning layer is the highest-leverage component in a prompt — the difference between shallow and deep output almost always traces back to reasoning quality.
## How to Use This Skill
1. Identify the dominant thinking mode the task requires (see the selection guide below).
2. Read the corresponding reference file for that category to find the specific variant that fits.
3. Copy and adapt the reasoning instructions into your prompt.
4. If the task spans categories, see "Combining Reasoning Approaches" below.
## Selection Guide
### Analytical / Evaluative
**Choose when the task requires evaluating, diagnosing, or assessing something that exists.**
| Approach | Best For | Key Differentiator |
|---|---|---|
| General Analysis | Broad evaluation of a situation, opportunity, or problem | Works forward from evidence to conclusions |
| Root Cause Diagnosis | Something is failing or underperforming — find out why | Works backward from symptoms to cau