Token导航 LogoToken导航

Agent Skill · 研究检索

project-memory(项目记忆)

project-memory 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-memory 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,权限为需要联网;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,674 个 Skill 里排第 37,787。

总安装 1,670周安装 71GitHub Stars 171下载 585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
unknown

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-memory(项目记忆)
来源仓库:https://github.com/jamditis/claude-skills-journalism
仓库路径:skills/project-memory
安装命令:
npx skills add https://github.com/jamditis/claude-skills-journalism --skill project-memory
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 npx skills 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。

skills.shnpx skills
npx skills add https://github.com/jamditis/claude-skills-journalism --skill project-memory

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-memory 用于查找、检索和筛选相关信息。适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词或任务场景快速定位候选结果。可结合来源仓库和原始 README 继续核验具体用法。

安装命令:npx skills add https://github.com/jamditis/claude-skills-journalism --skill project-memory 注意:安装前建议确认权限范围、维护状态及是否触发联网或文件操作。

来源仓库内路径:skills/project-memory

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/jamditis/claude-skills-journalism --skill proj…;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

    它需要需要联网,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

project-memory 怎么安装?

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

project-memory 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-memory 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

project-memory 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

project-memory 用的人多吗?

公开数据是累计安装 1,670 次,近一周安装 71 次,下载 585 次,GitHub 171 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-memory 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。
  • 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

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 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。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 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-memory

项目记忆 · 本页

1,670171需要联网未明确通过

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

Project memory generator

Create CLAUDE.md files that transfer tribal knowledge, not obvious information. Think like a senior journalist onboarding a competent colleague—you don't explain how journalism works, you explain YOUR project's quirks.

What belongs in CLAUDE.md

IncludeDon't include
Project-specific quirksHow journalism works generally
YOUR naming conventionsStandard file organization
Commands with YOUR flagsGeneric commands like "npm install"
Non-obvious architectureFramework documentation
Common mistakes in THIS projectGeneral best practices
External service configurationsInformation already in comments
Source handling requirementsBasic ethics everyone knows

The deletion test

For every line you write, ask: "Would an experienced journalist already know this?"

  • If yes → Delete it
  • If no → Keep it

Basic template structure

# CLAUDE.md

## Project overview
[1-2 sentences maximum. What this does + who uses it.]

## Commands
[Only project-specific commands. Not generic ones.]

## Architecture
[Only non-obvious decisions. Where does X live? Why?]

## Patterns
[Only patterns unique to this project]

## Things to avoid
[Project-specific anti-patterns and gotchas]

## External dependencies
[APIs, services, credential locations]

What to cut ruthlessly

Generic commands everyone knows:

<!-- DELETE THIS -->
git add .      # Stage changes
npm install    # Install dependencies

Obvious journalism patterns:

<!-- DELETE THIS -->
We verify facts before publishing. All quotes must be
attributed. Follow AP Style...

Framework explanations:

<!-- DELETE THIS -->
React components live in /components. We use hooks
for state management...

What to keep

Project-specific quirks:

<!-- KEEP THIS -->
Source names in the spreadsheet use LAST, FIRST format
but the CMS expects FIRST LAST. The import script handles
this, but manual entries need flipping.

Non-obvious architecture:

<!-- KEEP THIS -->
Embargo dates are stored in the CMS as NYC time but
displayed in the reader's local time. Server-side renders
use UTC. Check timezone handling before changing date code.

Gotchas that burned you:

<!-- KEEP THIS -->
The AP feed disconnects silently after 4 hours. Cron job
at :00 checks connection and restarts if stale.

Voice guidelines

  • Direct and terse
  • Like notes you'd leave for yourself
  • No marketing language
  • No "Welcome to..." introductions
  • No "This project is..." padding

Example: Good vs bad

Bad (too verbose, obvious):

# CLAUDE.md

## Overview
Welcome to our newsroom's story tracking system! This is a
web application built with React and Node.js that helps
editors and reporters collaborate on stories.

## Getting started
First, make sure you have Node.js installed. Then:
npm install
npm start

Good (tribal knowledge only):

# CLAUDE.md

## Overview
Story tracker for metro desk. React + Supabase.

## Gotchas
- Story slugs must be unique across ALL desks, not just metro
- "Hold" status doesn't stop the autopublish cron—use "Kill"
- Reporter dropdown caches for 1 hour; new hires won't appear

## Commands
npm run sync-ap  # Pull latest from AP, runs automatically at :15

## Credentials
Supabase key in 1Password "Metro Desk" vault, not .env

Length guideline

A good CLAUDE.md is 50-150 lines. If it's longer, you're explaining too much. If it's shorter, you might be missing critical quirks.

Journalism-specific templates

Templates are in the templates/ directory:

TemplateUse for
editorial-tool.mdNewsroom tools, fact-checkers, AI assistants
event-website.mdConferences, workshops, campaign sites
publication.mdNewsletters, podcasts, ongoing content series
research-project.mdInvestigations, data journalism with defined scope
content-pipeline.mdCMS workflows, publishing automation
digital-archive.mdHistorical collections, document repositories

Template selection guide

What are you building?
├── Tool for the newsroom → editorial-tool.md
├── Site for an event → event-website.md
├── Recurring content series → publication.md
├── One-time investigation → research-project.md
├── Publishing automation → content-pipeline.md
└── Archive/preservation → digital-archive.md

How to use templates

  1. Copy the appropriate template to your project root as CLAUDE.md
  2. Fill in the bracketed placeholders with YOUR specifics
  3. Delete any sections that don't apply
  4. Add project-specific gotchas as you discover them
  5. Keep it updated—stale CLAUDE.md files cause confusion

*The best CLAUDE.md files are written by people who've been burned by the quirks they're documenting.*

平台分布

Codex

35.9%
按下载量换算210

Claude

29.05%
按下载量换算170

Cursor

17.06%
按下载量换算100

Gemini CLI

9.66%
按下载量换算57

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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