pragya
CommunitySeek corrections, don't assume.
Software Engineering#decision making#uncertainty#user feedback#ai safety#agent protocol#strategy evolution
Authordhruvinrsoni
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill ensures AI agents don't make costly assumptions by implementing a protocol for seeking user direction and corrections before taking uncertain or irreversible actions.
Core Features & Use Cases
- Uncertainty Detection: Assesses confidence and identifies multiple viable paths.
- Direction Checkpoint: Pauses execution to present options, pros, cons, and recommendations to the user.
- Strategy Evolution: Tracks and adapts the agent's strategy based on new discoveries and user feedback.
- Use Case: When an AI is deciding between two architectural approaches for a new feature, Pragya will present the trade-offs of each and ask the user to make the final decision.
Quick Start
Use the pragya skill to assess the confidence of the next action and determine if a checkpoint is needed.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 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: pragya Download link: https://github.com/dhruvinrsoni/agentskills-garden/archive/main.zip#pragya Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.