System Documentation

What problem does it solve?

This Skill removes rigid step-by-step prompting from agent work by routing tasks internally based on confidence, so clear requests can move straight into execution while vague requests naturally get the extra questions they need.

Core Features & Use Cases

  • Internal routing: Automatically chooses between seed, panorama, execution, and exception handling without exposing the route to the user.
  • Consensus page workflow: Builds a shared understanding of intent, outcome, current state, boundaries, and risks before acting.
  • Autonomous execution: Continues working with progress updates when confidence is high, and pauses only for missing information, contradictions, or irreversible actions.
  • Example use case: A user asks to refactor a notification module, and the Skill drafts the consensus page, confirms only the uncertain parts, then executes with controlled progress reporting.

Quick Start

Use sancai-zhen to interpret the request, build the consensus page if needed, and start the task with the right balance of clarification and autonomous execution.

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: sancai-zhen
Download link: https://github.com/songlairui/agent-monad/archive/main.zip#sancai-zhen

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 537,000+ vetted skills library on demand.