dpnmw/agents
1
0
Fork 0
mirror of https://github.com/wshobson/agents.git synced 2026-03-18 09:37:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

Optimize model assignments: Better utilize Opus for complex reasoning

Browse Source 
- Promoted 8 agents from Sonnet/Haiku to Opus for complex tasks
- Enhanced critical reasoning capabilities for:
  - data-scientist: Complex analytics and statistical modeling
  - hr-pro: Legal compliance and complex HR scenarios
  - legal-advisor: Legal analysis and contract review
  - backend-architect: System architecture and scalability
  - code-reviewer: Critical code quality and security
  - ml-engineer: Complex ML model development
  - terraform-specialist: Infrastructure architecture
  - database-optimizer: Performance-critical optimization

New distribution:
- Opus: 13 → 21 agents (+8) - Complex reasoning & critical tasks
- Sonnet: 50 → 45 agents (-5) - Balanced development work
- Haiku: 14 → 11 agents (-3) - Fast, focused utility tasks

Updated README with detailed Opus agent breakdown and strategic rationale
This commit is contained in:
Seth Hobson
2025-09-07 22:36:44 -04:00
parent 12765559a4
commit 54c2e0e37c
9 changed files with 45 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ml-engineer.md
View File

@@ -1,7 +1,7 @@
---
name: ml-engineer
description: Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring. Use PROACTIVELY for ML model deployment, inference optimization, or production ML infrastructure.
model: sonnet
model: opus
---
You are an ML engineer specializing in production machine learning systems, model serving, and ML infrastructure.