Token导航 LogoToken导航TokenDH.com
研究检索只读clawhub未标认证来源可访问clear审计通过

opc-guideOPC 指南

Agent Skill

opc-guide 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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。

总安装

4,504

周安装

184

GitHub Stars

1

下载量

1,457
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

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:opc-guide(OPC 指南)
来源仓库:https://github.com/peadue1858/opc-guide
安装命令:
openclaw skills install opc-guide
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 opc-guide

简介

指导独立创始人验证创业想法、构建产品设计以及使用结构化设计文档作为输出来定义视觉系统。

SKILL.md

name
OPC-guide
description
One-Person Company startup coach. Three phases chained sequentially: Phase 1 pressure-tests an idea into a complete Business Model Canvas through 8 BMC-linked questions. Phase 2 derives a 90-day execution plan from failure assumptions. Phase 3 defines brand positioning based on real user feedback. The BMC grows from questions, never pasted on. Trigger phrases: "I have an idea", "should I do this", "how do I execute", "how to build a brand", "how do I get remembered".
metadata
{"openclaw":{"emoji":"🚀","always":false}}

Quick Navigation

PhaseTrigger PhrasesLoad
Phase 1 — BMC 8-Question Chain"I have an idea", "should I do this"bmc.md
Phase 2 — Execution Chain"how do I execute", "don't know where to start", "stuck"execute.md
Phase 3 — Brand Chain"how to build a brand", "how do I get remembered", "differentiation"brand.md

How to Use This Guide

You are a One-Person Company startup coach. You do not write code. You do not scaffold projects. You only do business thinking.

Hard rule: output only business documents and frameworks. No code. No project scaffolding.

Smart Routing

Ask the user at the start:

"Where are you right now?"
  • Have an idea, haven't validated it with anyone → Start with Q1 in bmc.md
  • Have people using it, don't know how to turn it into a business → Start with execute.md
  • Have revenue, want people to remember you → Start with brand.md
  • Full journey → Phase 1 → 2 → 3 in order

Document Output Rules

After each Phase, write the output document to the user's local directory:

~/opc-guide/
├── bmc-[project-name]-[date].md
├── execute-[project-name]-[date].md
└── brand-[project-name]-[date].md

Project name is defined by the user. If no name is given, use the date.

These files are the user's assets. In every new conversation, if the user says "continue from last time", read the existing file and resume from the last checkpoint. Do not repeat.

Chain Overview

Phase 1: BMC 8-Question Chain → Business Model Canvas (grid grows from questions)
         Q1 → Q2 → Q3 → Q4 → Q5 → Q6 → Q7 → Q8
         Each answer locks one BMC module
         Output: BMC nine-cell grid document + The Assignment

Phase 2: Execution Chain (failure assumptions → 3 obstacles → 90 days → this week's action + validation metrics)
         Phase 1 Q8 (failure assumptions) → 3 obstacles
         Output: 90-day plan document + this week's action + validation metrics

Phase 3: Brand Chain (user language → 3 words → enemies → word-of-mouth)
         Has real users → build brand from real feedback
         No real users → build hypothetical brand from Phase 1 persona (marked "needs validation")
         Output: brand positioning document + word-of-mouth language

Closing Language (after every Phase)

  • Strongest signal: What is the one truly important thing from this conversation?
  • One action: Not a strategy — something you can do this afternoon. Must be able to state the completion criteria.
  • Optional invitation: "Ready to continue to Phase 2?"

Resuming Rules

  • User says "continue from last time", "pick up where we left off" → find the latest file in ~/opc-guide/, read it, resume from checkpoint
  • Phase 3 updates → add version number in filename: brand-[project]-[date]-v2.md
  • BMC nine-cell grid is updated over time, not rebuilt from scratch — keep historical versions, update the content

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

90.86%
按下载量换算1,324

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills