Self Consistency — Development skill for Claude Code
Self-Consistency 用多次采样投票提升准确率,Self-Refine 让模型自我打分修正——两个看似简单的技巧,效果常常比换更强的模型还显著.
How to install Self Consistency
Installs to ~/.claude/skills/yibo365-agent-camp-self-consistency/SKILL.md
mkdir -p ~/.claude/skills/yibo365-agent-camp-self-consistency && curl -fsSL https://raw.githubusercontent.com/yibo365/agent-camp/HEAD/prompt/self-consistency.md -o ~/.claude/skills/yibo365-agent-camp-self-consistency/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Self Consistency does
title: 自一致性与自我反思 description: Self-Consistency 用多次采样投票提升准确率,Self-Refine 让模型自我打分修正——两个看似简单的技巧,效果常常比换更强的模型还显著。 pageClass: prompt-self-consistency-page
Prompt 工程
Self-Consistency 与 Self-Refine
Self-Consistency 用多次采样投票,Self-Refine 让模型自我打分修正——两个简单技巧,效果常常比换更强的模型还显著。
Alternatives in Development
- GenericAgent — Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token co 6.1k ★
- Hermes Agent Self Evolution — ⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA 5.2k ★
- Microsandbox — Open-source self-hosted MicroVM sandboxes with sub-200ms startup, hardware-level isolation via libkrun 5k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Check Continuity
Validate consistency across the screenplay.
03 Repair Batch Consistency
Repair Prompt: Batch Consistency and Mirror Recovery
Validate Manifest
Validate the extension manifest for dependency order, protected extensions, and consistency
Validate Hooks
Validate hook registration, consistency, and configuration
3 Ranking Laws Cheat Sheet
Audits a website against Google's 3 Ranking Laws, sourced from Google's own patents and the May 2024 Search AP
Proto Pin
Pin tool versions in .prototools for team consistency
Related Agents
Senior Editor
Use this agent to refine, polish, and perfect any piece of text. This agent is a master of grammar, style, and
Langchain Prompt Designer
Especialista en system prompts de agentes LangChain (LLM nodes en N8N, OpenAI Agents, Anthropic, etc.). Diseña
Typesafe Calibrator
Turns invented thresholds into measured ones. Builds labelled sets, plots confidence against accuracy, measure