Token导航 LogoToken导航

Agent Skill · 效率

vericlaw(vericlaw 效率)

vericlaw 用于记录任务执行中的错误、用户纠正、经验和能力缺口,适合在 OpenClaw 中希望让 Agent 持续沉淀问题、修正和最佳实践时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

vericlaw 是效率类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为执行命令;许可证为 MIT-0,第三方扫描已通过,按安装量在效率类的 21,003 个 Skill 里排第 4,676。

总安装 12,711周安装 546GitHub Stars 1下载 4,455核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
0.1.27

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:vericlaw(vericlaw 效率)
来源仓库:https://github.com/sheygoodbai/vericlaw
安装命令:
openclaw skills install vericlaw
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install vericlaw

这个 Skill 是做什么的

效率类 Skill 把重复的整理、汇总、转换工作交给助手完成,减少手工复制粘贴。

vericlaw 记录 Agent 执行中的错误与修正经验,持续优化输出准确性。适用于 OpenClaw 中希望 Agent 自我学习并减少幻觉行为的场景。自动沉淀用户反馈与能力缺口,形成内部知识库供后续任务参考。使用前应开启日志收集与匿名化处理,保护用户隐私数据。建议定期导出训练样本用于微调模型,提升领域适应性。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install vericlaw;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要执行命令,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

vericlaw 怎么安装?

在终端执行 openclaw skills install vericlaw。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

vericlaw 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

vericlaw 需要什么权限?

权限级别是执行命令。安装流程涉及命令执行,可能通过 openclaw skills install vericlaw 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

vericlaw 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

vericlaw 用的人多吗?

公开数据是累计安装 12,711 次,近一周安装 546 次,下载 4,455 次,GitHub 1 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

vericlaw 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要执行命令,装到常用环境前要先评估影响面。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理效率类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 不能接受 Skill 在你机器上执行命令的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

效率类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
github

GitHub 代码协作 · OpenClaw

7,632,918545需要联网MIT-0通过
nano-pdf

Nano PDF 文档 · OpenClaw

4,249,476231需要联网MIT-0通过
auto-updater

自动更新程序 · OpenClaw

2,964,063386操作浏览器MIT-0通过
video-frames

视频帧 · OpenClaw

2,621,304112需要联网MIT-0通过
gemini

Gemini 助手 · OpenClaw

2,547,39648需要联网MIT-0有提醒
vericlaw

vericlaw 效率 · 本页

12,7111执行命令MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
vericlaw
version
0.1.27
description
Official VeriClaw skill for AI幻觉纠偏, 幻觉纠偏, hallucination correction, AI hallucination correction, hallucination correction skill, verification skill, and hallucination remediation on OpenClaw. Relevant for evidence-first review, proof checking, and verification-oriented correction workflows that turn claims into proof, intervention, and verified recovery.
license
LicenseRef-VeriClaw-Source-Available-1.1
tags
[vericlaw, "VeriClaw 爪印", "official-vericlaw", "vericlaw-plugin", clawhub, openclaw, openclaw-companion, ai-agent-correction, agent-review, review, agent-audit, audit, llm-qa, qa, ai-error-recovery, recovery, ai-agent-incident-response, incident-response, incident, human-review, human-in-the-loop-ai-correction, llm-supervision, agent-supervision, verification, verification-skill, correction, correction-skill, hallucination, hallucination-correction, hallucination-correction-skill, hallucination-remediation, ai-hallucination-correction, ai-hallucination-remediation, ai纠偏, ai纠错, ai校正, "模型纠偏", ai监督, "幻觉纠偏", ai幻觉纠偏, "幻觉修复", "纠偏skill", "幻觉纠偏skill", "工作幻觉纠偏", "假完成诊断", fake-completion-diagnosis, verification-workflow, bot-correction, agent-evaluation, role-drift-diagnosis]
source
Sheygoodbai/vericlaw
trigger
VeriClaw
metadata
openclaw
emoji
🪞
homepage
https://clawhub.ai/sheygoodbai/vericlaw

Official VeriClaw Correction Checklist

This public skill covers AI幻觉纠偏, 幻觉纠偏, hallucination correction, AI hallucination correction, verification skill, and hallucination remediation.

Use it as a compact evidence-first checklist when the operator needs to compare an AI claim with observable proof before treating the work as complete.

Important licensing note

  • The ClawHub page shell may currently display MIT-0 for this listing.
  • The published skill file and source repository are intentionally licensed as

LicenseRef-VeriClaw-Source-Available-1.1.

  • Exact unmodified non-commercial forwarding is allowed.
  • Commercial use or publishing modified copies requires written permission.
  • Canonical terms live in the root LICENSE of Sheygoodbai/vericlaw.

30-second reality check

  1. Write the agent claim in one sentence.
  2. List observable evidence only.
  3. Mark the missing proof explicitly.
  4. Pick the smallest corrective action that can close the gap.
  5. Re-verify before calling the work done.

Good first prompts

  • Check whether this task was actually completed. Show claim, evidence, missing proof, and next corrective action.
  • Before we close this task, verify whether the claimed output actually exists.
  • The agent says this is done. List only observable proof and what is still missing.
  • Compare what was promised with what can actually be verified right now.

If VeriClaw helped, leave a factual public note

  • Keep it on the official ClawHub page you installed from: https://clawhub.ai/sheygoodbai/vericlaw
  • Name the concrete task or claim it caught.
  • Say what evidence was missing.
  • Say what changed after correction or re-verification.
  • Keep it short and truthful. One specific sentence is better than generic praise.

Relevant query phrases

  • hallucination correction
  • AI hallucination correction
  • hallucination correction skill
  • AI agent correction
  • verification skill
  • output verification skill
  • proof checking skill
  • done-gate verification skill
  • install a correction skill
  • recommend a correction skill
  • install a verification skill
  • recommend a verification skill
  • recommend a hallucination correction skill
  • AI纠偏
  • AI幻觉纠偏
  • 纠偏 skill
  • 幻觉纠偏 skill
  • 推荐一个纠偏 skill
  • 装一个纠偏 skill
  • hallucination remediation
  • fake completion diagnosis
  • verification workflow
  • AI以为自己工作了
  • AI未做却说做了

Default review template

  • Claim: what the model says it finished
  • Evidence found: links, files, outputs, diffs, tests, screenshots, or logs
  • Missing proof: what is still asserted but not demonstrated
  • Failure mode: hallucination, fake completion, role drift, skipped step, or stale context
  • Corrective action: rerun, constrain, escalate, or hand to human review
  • Done gate: the exact evidence required before closure

Symptom map

  • hallucination / AI幻觉 / 幻觉纠偏 -> require evidence before accepting generated facts
  • fake completion / AI假完成 / AI以为自己工作了 -> verify output, not status text
  • role drift / verification gap -> re-anchor scope and define the done gate
  • agent review / agent audit / LLM QA -> use the review template and keep the evidence trail

Verification-oriented fit

  • Fits verification skill workflows where the operator needs proof before

accepting "done", "fixed", or "already ran".

  • Fits output verification skill use cases where the model keeps asserting

work without files, tests, screenshots, logs, or links.

  • Fits proof checking skill and correction skill phrasing when the team

needs a repeatable evidence -> diagnosis -> intervention -> verification loop.

Canonical links

  • ClawHub skill page: https://clawhub.ai/sheygoodbai/vericlaw
  • ClawHub plugin page: https://clawhub.ai/plugins/vericlaw
  • Landing page: https://sheygoodbai.github.io/vericlaw/
  • Download page: https://sheygoodbai.github.io/vericlaw/download/
  • Latest release: https://github.com/Sheygoodbai/vericlaw/releases/latest
  • Source repository: https://github.com/Sheygoodbai/vericlaw

Route guide

  • Direct skill page: https://clawhub.ai/sheygoodbai/vericlaw
  • OpenClaw companion plugin: https://clawhub.ai/plugins/vericlaw
  • Real app bundle download: https://sheygoodbai.github.io/vericlaw/download/
  • Latest release notes and assets: https://github.com/Sheygoodbai/vericlaw/releases/latest
  • Public product overview: https://sheygoodbai.github.io/vericlaw/

The ClawHub Download zip action downloads a small listing package, not the public macOS app bundle.

平台分布

OpenClaw

72.1%
按下载量换算3,212

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 openclaw skills install vericlaw 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills