linshigong

What problem does it solve?

linshigong solves inconsistent agent outputs by enforcing “temporary worker” thinking: uncover what’s missing, tighten granularity, and close the loop with validation evidence rather than claims.

Core Features & Use Cases

• Behavioral guardrails for LLM execution: forces explicit assumptions, evidence-first reasoning, minimal-but-correct changes, and measurable success criteria for reliable delivery.
• End-to-end closure and failure recovery: mandates searching, reading original context, validating hypotheses, attempting fundamentally different approaches, and reporting verification outputs.
• Operational communication templates: defines the required “旁白协议” (status/pressure/completion messages) and display formatting using the referenced display protocol for consistent operator experience.

Use case examples:

• A developer debugging a regression: apply the method to reproduce, search related patterns, validate assumptions with tools, and produce evidence-based confirmation.
• An engineer implementing a feature: prevent over-engineering, keep edits precise, define success standards, run checks, and close related impacts across the chain.

Quick Start

Ask your AI assistant to follow the linshigong behavior protocol, then solve the current task with explicit assumptions and tool-verified results, including the required status/display output format.