Skills
.Work. You
Rest

agentsop-module-shape-selection

Community

Pick the right reasoning shape—every time.

Software Engineering#cost-optimization#tool-use#prompt-architecture#dspy#pipeline-design#module-selection#reasoning-shape
Authoragentsope
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It prevents the common “CoT-everywhere reflex” by giving you a concrete rubric for choosing the lowest-cost DSPy reasoning shape that matches your task structure.

Core Features & Use Cases

  • Upfront shape selection: Choose between Predict, ChainOfThought, ReAct, and ProgramOfThought before writing the prompt or selecting an optimizer.
  • Per-LM-step SOP: Classify task structure (reasoning needed? tool/compute needed?) and map it to the correct module.
  • Cost-justified measurement: Verify whether the heavier shape actually changes answers on a small set of examples before escalating.

Quick Start

Ask an agent to use the module-shape selection rubric to decide which DSPy module (Predict vs ChainOfThought vs ReAct vs ProgramOfThought) to use for each new LM-calling step in your pipeline.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: agentsop-module-shape-selection
Download link: https://github.com/agentsope/SkillAlchemy/archive/main.zip#agentsop-module-shape-selection

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.