Token导航 LogoToken导航TokenDH.com
研究检索操作浏览器clawhub未标认证来源可访问clear审计提醒

plan-flow计划流程

Agent Skill

plan-flow 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

11,421

周安装

462

GitHub Stars

公开资料未说明

下载量

3,585
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:plan-flow(计划流程)
来源仓库:https://github.com/brunoscardoso/plan-flow
安装命令:
openclaw skills install plan-flow
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 plan-flow

简介

plan-flow 用于结构化人工智能辅助开发工作流程,涵盖发现、规划、执行、代码审查和测试阶段。

  • 它支持自然语言驱动的 task 拆解与资源调度,适用于复杂项目开发场景。
  • 通过 clawhub 安装后即可调用工作流引擎。
  • 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。
  • plan-flow 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

name
plan-flow
version
1.0.8
description
Structured AI-assisted development workflows - discovery, planning, execution, code reviews, and testing
metadata
{"openclaw":{"requires":{"bins":["git","gh"]}},"clawhub":{"requires":{"bins":["git","gh"]},"emoji":"🗺️","homepage":"https://github.com/brunoscardoso/plan-flow"}}
homepage
https://github.com/brunoscardoso/plan-flow
user-invocable
true

Plan-Flow: Structured AI-Assisted Development

A comprehensive skill set for AI-assisted software development with structured workflows and persistent project memory.

Available Commands

CommandDescription
/setupAnalyze project and generate pattern files
/discoveryCreate discovery document for requirements gathering
/create-planCreate implementation plan with phases and complexity scores
/execute-planExecute plan phases with verification
/create-contractCreate integration contract from API docs
/review-codeReview local uncommitted changes
/review-prReview a Pull Request
/write-testsWrite tests to achieve coverage target
/flowToggle autopilot mode (auto-chains the full workflow)

Always-Active Features

FeatureDescription
Project LedgerPersistent learning journal at flow/ledger.md - silently captures mistakes, corrections, and project-specific knowledge across sessions

Recommended Workflow

Automated - runs without asking permission:

1. /setup           → Index project patterns (run once)
2. /discovery       → Gather requirements for a feature
3. /create-plan     → Create structured implementation plan (auto-runs after discovery)
4. /execute-plan    → Execute the plan phase by phase (auto-runs after plan)
5. /review-code     → Review changes before committing
6. Archive          → Move discovery + plan to flow/archive/

Only stop to ask the user when:

  • Missing critical information (device type, browser, etc.)
  • Need to reproduce an issue
  • Ambiguous requirements
  • Need approval for destructive actions

Never ask "Ready to create plan?" or "Proceed with execution?" - just do it.

Core Concepts

Complexity Scoring

Every plan phase has a complexity score (0-10):

ScoreLevelDescription
0-2TrivialSimple, mechanical changes
3-4LowStraightforward implementation
5-6MediumModerate complexity, some decisions
7-8HighComplex, multiple considerations
9-10Very HighSignificant complexity/risk

Flow Directory Structure

All artifacts are stored in flow/:

flow/
├── archive/           # Completed/abandoned plans
├── contracts/         # Integration contracts
├── discovery/         # Discovery documents
├── plans/             # Active implementation plans
├── references/        # Reference materials
├── reviewed-code/     # Code review documents
├── reviewed-pr/       # PR review documents
└── ledger.md          # Persistent project learning journal

Critical Rules

  1. Automated Workflow: Run discovery → plan → execute automatically. Only stop to ask when you need information from the user.
  2. Discovery First (Hard Block): /discovery is required before /create-plan. Plans cannot be created without a discovery document. No exceptions. If no discovery exists, run discovery first.
  3. Tests Last: Tests are always the last phase of any implementation plan.
  4. Build at End Only: Run build verification only after ALL phases complete.
  5. Archive When Done: Move completed discovery and plans to flow/archive/.

Configuration

Create .plan-flow.yml in your project root:

ai:
  provider: claude
  anthropic_api_key: sk-ant-api03-your-key-here

Requirements

  • git - For version control operations
  • gh - GitHub CLI for PR reviews

Installation

clawhub install plan-flow

Or add to your workspace skills folder:

git clone https://github.com/brunoscardoso/plan-flow.git ~/.openclaw/skills/plan-flow

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

76.58%
按下载量换算2,745

安全审计

VirusTotal

可疑

ClawScan

可疑

Static analysis

未展示

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。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