Sub-skill of improve: Decision Logic (Scoring).
Scanned 9/9/2026
Install to Claude Code
npx -y skills add vamseeachanta/workspace-hub --skill decision-logic-scoring --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Decision Logic Scoring?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/vamseeachanta-decision-logic-scoring-workspace-hub)More formats (shields.io, HTML) on the badges page.
---
name: improve-decision-logic-scoring
description: 'Sub-skill of improve: Decision Logic (Scoring).'
version: 1.4.0
category: workspace-hub
type: reference
scripts_exempt: true
---
# Decision Logic (Scoring)
## Decision Logic (Scoring)
| Factor | Weight | Criteria |
|---|---|---|
| Recurrence | 40% | Same pattern N times (1x=0.2, 2x=0.5, 3+=0.8) |
| Severity | 30% | Blocked work (1.0), warning (0.5), info (0.2) |
| Freshness | 15% | This session (1.0), last 7 days (0.7), older (0.3) |
| Specificity | 15% | Actionable (1.0), vague (0.3) |
**Thresholds**:
- Score >= 0.6: Apply immediately
- Score 0.3–0.59: Stage for accumulation (may trigger next session)
- Score < 0.3: Discard
**Exceptions** (bypass scoring):
- Direct user statements ("remember this", "always do X") → apply immediately
- Skill deprecation → requires 90-day inactivity evidence regardless of score
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!
Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.