Token导航 LogoToken导航

Agent Skill · 研究检索

template-selector(模板选择器)

template-selector 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。

template-selector 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 73,675 个 Skill 里排第 38,093。

总安装 1,616周安装 68GitHub Stars 171下载 566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:template-selector(模板选择器)
来源仓库:https://github.com/jamditis/claude-skills-journalism
仓库路径:skills/template-selector
安装命令:
npx skills add https://github.com/jamditis/claude-skills-journalism --skill template-selector
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 template-selector

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。

template-selector 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。适用于内容筛选、模板匹配和信息优先级排序场景。可根据条件过滤候选结果,提升信息检索的准确性和效率。

安装命令:npx skills add https://github.com/jamditis/claude-skills-journalism --skill template-selector。使用前需确认权限范围、维护状态及是否触发联网或文件读写操作。

来源仓库内路径:skills/template-selector

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 temp…;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

template-selector 怎么安装?

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

template-selector 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。

template-selector 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。

template-selector 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。

template-selector 用的人多吗?

公开数据是累计安装 1,616 次,近一周安装 68 次,下载 566 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。

template-selector 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。
  • 标注为只读权限,试用阶段不容易误改本地文件。

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。
  • 只想先试试效果、不希望它改动本地文件的人。

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
template-selector

模板选择器 · 本页

1,616171只读未明确通过

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

Template selector

Match projects to the correct template category. Don't guess—use the decision tree.

Quick reference

Project typeTemplate category
Newsroom AI tool, fact-checkereditorial-tool
Conference, summit, workshopevent-website
Newsletter, podcast, blogpublication
Investigation, data journalismresearch-project
CMS workflow, syndicationcontent-pipeline
Historical collection, archivedigital-archive

Decision tree

Is it for journalism/publishing?
├── Yes →
│   ├── Has specific end date/event? → event-website
│   ├── Ongoing content series? → publication
│   ├── Historical/preservation? → digital-archive
│   ├── Newsroom tool/AI? → editorial-tool
│   ├── CMS/automation? → content-pipeline
│   └── Investigation with scope? → research-project
│
└── No (general software) →
    Use general template or another collection

Detailed category descriptions

editorial-tool

Use when: Building newsroom tools, writing assistants, fact-checkers, AI-powered research tools, moderation systems, workflow automation for journalists

Not for: Generic productivity tools, non-journalism software

Signs it's an editorial tool:

  • Primary users are journalists, editors, or producers
  • Helps with a specific editorial workflow step
  • Requires accuracy/trust for publication decisions

event-website

Use when: Building sites for conferences, summits, workshops, or events with specific dates

Not for: Ongoing content, organization websites without events, event management software (that's editorial-tool)

Signs it's an event website:

  • Has a specific event date (or date range)
  • Registration/attendance is involved
  • Content includes speakers, schedule, venue info

publication

Use when: Building newsletters, podcasts, blogs, magazines, or ongoing content series with regular publishing schedule

Not for: One-off articles, static content sites, CMSes that power publications (that's editorial-tool)

Signs it's a publication:

  • Regular publishing cadence (daily, weekly, monthly)
  • Growing subscriber/reader base
  • Consistent voice and format

research-project

Use when: Building investigative journalism projects, data journalism, analysis with defined scope and end date

Not for: Ongoing research operations, general data analysis, tools that support research (that's editorial-tool)

Signs it's a research project:

  • Answers a specific question or hypothesis
  • Has a defined end point (publication date)
  • Involves data collection, analysis, and findings

content-pipeline

Use when: Building CMS workflows, publishing automation, content syndication systems, feed aggregators, cross-posting tools

Not for: Manual publishing workflows, single-site content management, publications themselves

Signs it's a content pipeline:

  • Automates content movement between systems
  • Transforms content formats
  • Handles scheduling and distribution

digital-archive

Use when: Building historical collections, preservation projects, research databases, document repositories

Not for: Active news sites, CMS platforms, search engines

Signs it's a digital archive:

  • Primary focus is preservation
  • Collection has defined scope (time period, topic)
  • Users are researchers, historians, or the public seeking historical content

Common mistakes

ProjectWrong choiceRight choiceWhy
Newsletter dashboardeditorial-toolpublicationIt's about the publication, not the tech
AI fact-checkerresearch-projecteditorial-toolIt's a tool, not a one-off investigation
Event registration systemevent-websiteeditorial-toolIt's a tool that serves events
Podcast websitecontent-pipelinepublicationIt's a publication, not automation
Document search tooldigital-archiveeditorial-toolIt's a tool, not the archive itself
FOIA tracking systemresearch-projecteditorial-toolIt's a tool that supports research

The litmus test

If you're still unsure, ask:

  1. Is this a tool that helps journalists do X, or is this X itself?

- Tool → editorial-tool - The thing itself → other categories

  1. Does it have a specific end date?

- Yes, event dates → event-website - Yes, publication date → research-project - No, ongoing → publication, content-pipeline, or digital-archive

  1. Is preservation the primary goal?

- Yes → digital-archive - No → other categories

Using templates

For project memory (CLAUDE.md)

  1. Identify project category using decision tree above
  2. Copy appropriate template from project-memory/templates/
  3. Fill in bracketed placeholders with your specifics
  4. Delete sections that don't apply
  5. Add project-specific gotchas as you discover them

For retrospectives (LESSONS.md)

  1. Identify project category
  2. Copy appropriate template from project-retrospective/templates/
  3. Fill in as the project progresses or at completion
  4. Be specific about failures—that's the valuable part

Template locations

claude-skills-journalism/
├── project-memory/templates/
│   ├── editorial-tool.md
│   ├── event-website.md
│   ├── publication.md
│   ├── research-project.md
│   ├── content-pipeline.md
│   └── digital-archive.md
│
└── project-retrospective/templates/
    ├── editorial-tool.md
    ├── event.md
    ├── publication.md
    └── research-project.md

*Pick the specific template that fits. "General" is a last resort.*

平台分布

Codex

35.55%
按下载量换算201

Claude

31.06%
按下载量换算176

Cursor

18.87%
按下载量换算107

Gemini CLI

10.03%
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

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。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