agent-prompt-engineering

Community

Harden prompts and workflows for reliable agents.

Authormerceralex397-collab
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill helps teams craft and harden prompts, commands, and workflow rules to prevent doom loops, ambiguous delegation, and prompt-injection risks when coordinating repo-local agents across models.

Core Features & Use Cases

  • Prompt contracts and one-legal-next-move enforcement to reduce model ambiguity.
  • Model-specific hardening using package references and anti-pattern guidance to improve reliability across agents.
  • Governance and provenance through explicit artifact paths, staged verification, and proof before transitions.

Quick Start

Harden the repository's agent prompts by applying model-specific contracts and anti-patterns to ensure a single legal next move and a clear blocker path.

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: agent-prompt-engineering
Download link: https://github.com/merceralex397-collab/Scafforge/archive/main.zip#agent-prompt-engineering

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.