text-only-nudge
CommunityForce action, stop plan-only replies.
Software Engineering#prompt-injection#llm-safety#tool-execution#text-nudge#plan-detection#iteration-control
Authorbianhaifeng789-hue
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill detects when the model describes its plan without taking action and injects a force prompt to ensure immediate tool execution, preventing stagnant planning during early iterations.
Core Features & Use Cases
- Text-only plan detection during early iterations (iteration <= 3) with no prior tool calls.
- Nudge injection that prompts the agent to run commands immediately using a predefined system prompt.
- Seamless integration into the agent loop to pause descriptive behavior and enforce execution.
Quick Start
If the model describes a plan in early iterations, trigger the nudge to start executing tools immediately.
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: text-only-nudge Download link: https://github.com/bianhaifeng789-hue/openclaw-config/archive/main.zip#text-only-nudge 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.