Token导航 LogoToken导航

Agent Skill · 研究检索

project-planning(项目策划)

project-planning 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 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。

project-planning 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证为 MIT,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 41,004。

总安装 1,224周安装 51GitHub Stars 52下载 408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

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:project-planning(项目策划)
来源仓库:https://github.com/zenobi-us/dotfiles
仓库路径:skills/project-planning
安装命令:
npx skills add https://github.com/zenobi-us/dotfiles --skill project-planning
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/zenobi-us/dotfiles --skill project-planning

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

project-planning 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 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。适用于需求拆解、资源估算或里程碑设定等项目管理前期准备工作。

通过 npx skills add 命令从指定仓库安装,调用时输入项目目标即可获得任务分解建议。安装前需确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。建议结合来源仓库和原始 README 核验是否支持甘特图生成或与 Jira 等工具集成。

来源仓库内路径:skills/project-planning

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 Codex、Claude、Cursor、Gemini CLI;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 npx skills add https://github.com/zenobi-us/dotfiles --skill project-planning;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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

project-planning 怎么安装?

在终端执行 npx skills add https://github.com/zenobi-us/dotfiles --skill project-planning。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

project-planning 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。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。

project-planning 需要什么权限?

权限级别是只读。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。

project-planning 是免费的吗?

来源标注的许可证是 MIT。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。

project-planning 用的人多吗?

公开数据是累计安装 1,224 次,近一周安装 51 次,下载 408 次,GitHub 52 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。

project-planning 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

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,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

  • 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 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、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

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
project-planning

项目策划 · 本页

1,22452只读MIT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

What are [Planning Artifact] Types?

Throughout the project-planning instructions you will see often refernces to types in the form of [Epic], [Spec], [Story], [Task], [Research], and [Decision].

This is to reinforce to you the reader or agent that these are distinct artifact types with specific roles.

  • [PRD]: Product Requirements Document, A high-level statement of what the product should achieve. They capture the needs and expectations of stakeholders. A [PRD] informs managers in the creation of one or more [Epic].
  • [Epic]: A large body of work that is described by Stories. An [Epic] is always accompanied by a [Spec], they have a 1:1 relationship.
  • [Spec]: A detailed description of the project's requirements and objectives. It leads to creation of one or more [Story].
  • [Research]: Information gathering and analysis conducted to inform project decisions. Primary phase: Planning/Initiation (during PRD/Epic/Spec creation). Secondary phase: ad-hoc during Execution when implementation raises unknowns. [Research] informs [Spec], [Decision], and project direction. Linked to [PRD], [Epic], [Spec], [Decision], [Story], or [Task].
  • [Decision]: A conclusion reached after evaluating options, often based on [Research]. [Decision] can influence [Spec] and project direction. Created during Initiation/Planning (for strategic decisions) or during Execution (for implementation decisions). Status must be "Decided" or "Unresolved". All [Decision] artifacts with status "Unresolved" MUST be linked to the [Retrospective] during the Closing phase.
  • [Story]: A scenario or use case, manageable piece of work derived from an [Epic]. [Story] always contain "user stories". [Story] are always implemented by [Task].
  • [Task]: A specific piece of work that needs to be completed as part of a [Story]. They are always linked to both a [Story] and an [Epic]. They can also be linked to other [Task] in interesting ways (e.g., blocking, dependent on, related to).
  • [Retrospective]: A reflective artifact created at the end of an epic or project phase to capture lessons learned, successes, and areas for improvement. It summarizes insights from the team and stakeholders to inform future projects. Each [Retrospective] is linked to its corresponding [Epic] and any unresolved [Decision] artifacts.

Workflow Phases

Projects flow through five distinct phases. Understanding where artifacts belong is critical for agents executing this skill.

Agents make tactical decisions autonomously (which artifact to create, when to move statuses, validating content) but escalate strategic decisions to Q (scope changes, timeline shifts, technical refactoring, resource constraints).

Phase Overview

  1. Planning — Create artifacts defining the work (PRD → Epic → Spec → Stories → Tasks)

- → See: skill_reference(references/workflow/planning-phase.md) for detailed artifact creation sequence and validation gates

  1. Execution — Move work to completion through status transitions

- → See: skill_reference(references/workflow/execution-phase.md) for execution guidance

  1. Closing — Archive completed work and formally close Epic/Project

- → See: skill_reference(references/workflow/closing-phase.md) for closing procedures

  1. Retrospective — Capture learnings (can follow Epic or Project completion)

- → See: skill_reference(references/workflow/retrospective-phase.md) for retrospective guidance

Escalation Matrix

Pause and escalate to Q when encountering:

  • Scope changes — Feature additions/removals mid-Epic or mid-Planning
  • Timeline shifts — Projected delivery date moves >1 week
  • Technical refactoring — Discovered design changes during work
  • Resource constraints — Task/Story complexity exceeds capacity

→ See: skill_reference(references/workflow/overview.md) for complete escalation matrix, artifact relationship diagram, and agent decision model.

Estimation

When estimation is required, read the resources:

  • → See: skill_reference(references/estimation.md) for detailed estimation techniques and best practices.

Relationships

Artifacts maintain clear relationships to ensure traceability and context throughout the project lifecycle.

  • → See: skill_reference(references/relationships.md) for detailed relationship types and usage guidelines for all artifact types (PRD, Epic, Research, Story, Task, Retrospective, Decision).

Artifact Status Transitions

Each artifact type has valid status progressions that guide state management throughout the project lifecycle.

  • → See: skill_reference(references/status-flow.md for detailed status flow diagrams and descriptions for all artifact types (PRD, Epic, Research, Story, Task, Retrospective, Decision).

Artifact Schemas and Content Structure

All artifacts follow consistent schema patterns for organization and linking. Each artifact type has specific frontmatter requirements and content sections.

→ Use the linked skill resources for detailed schema definitions, artifact content structure, and link type definitions for all artifact types (PRD, Epic, Research, Story, Task, Retrospective, Decision).

See below for specific artifact schemas:

  • → PRD skill_reference(schema/01-artifact-prd.md)
  • → Epic skill_reference(schema/02-artifact-epic.md)
  • → Spec skill_reference(schema/03-artifact-spec.md)
  • → Research skill_reference(schema/04-artifact-research.md)
  • → Decision skill_reference(schema/05-artifact-decision.md)
  • → Story skill_reference(schema/06-artifact-story.md)
  • → Task skill_reference(schema/07-artifact-task.md)
  • → Retrospective skill_reference(schema/08-artifact-retrospective.md)

平台分布

OpenCode

30.93%
按下载量换算126

Claude Code

23.49%
按下载量换算96

Antigravity

15.45%
按下载量换算63

Gemini CLI

13.4%
按下载量换算55

moltbot

7.1%
按下载量换算29

windsurf

3.06%
按下载量换算12

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

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。

继续浏览同类 Skills