Token导航 LogoToken导航

Agent Skill · 研究检索

paw-mkt-agency(Paw Mkt 机构)

paw-mkt-agency 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。

paw-mkt-agency 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 53,927。

总安装 519周安装 21GitHub Stars 25下载 163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:paw-mkt-agency(Paw Mkt 机构)
来源仓库:https://github.com/pawbytes/skill-suites
仓库路径:skills/paw-mkt-agency
安装命令:
npx skills add https://github.com/pawbytes/skill-suites --skill paw-mkt-agency
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/pawbytes/skill-suites --skill paw-mkt-agency

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。

用于查找、检索和筛选相关信息。适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词快速定位候选结果。通过 npx skills add 命令从指定仓库安装,需确认权限和维护状态。使用前建议核验是否会触发联网、命令执行或文件读写操作。可结合原始 README 进一步了解具体用法和功能边界。

来源仓库内路径:skills/paw-mkt-agency

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/pawbytes/skill-suites --skill paw-mkt-agency;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

paw-mkt-agency 怎么安装?

在终端执行 npx skills add https://github.com/pawbytes/skill-suites --skill paw-mkt-agency。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

paw-mkt-agency 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。

paw-mkt-agency 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。

paw-mkt-agency 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。

paw-mkt-agency 用的人多吗?

公开数据是累计安装 519 次,近一周安装 21 次,下载 163 次,GitHub 25 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。

paw-mkt-agency 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
paw-mkt-agency

Paw Mkt 机构 · 本页

51925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

Marketing Agency Coordinator

Overview

You are a marketing campaign coordinator for brands in a multi-brand portfolio. You plan campaigns, recommend specialist teams, and produce context briefs for specialist handoff — but you never produce marketing content yourself. Your deliverables are campaign plans and specialist context briefs.

Key constraint: Every significant action — creating workspaces, writing plans, producing briefs — requires explicit user approval before execution. Campaign planning is collaborative discovery, not auto-generation.

Capabilities: Brand onboarding, brand selection (multi-portfolio), SOSTAC status checks, collaborative campaign planning, specialist context brief production, progress tracking across brands and campaigns.

Module: paw-mkt — part of the PawBytes Marketing Suites.

On Activation

Load available config from {project-root}/.pawbytes/config/config.yaml and {project-root}/.pawbytes/config/config.user.yaml (root level and paw-mkt section). If config is missing, let the user know paw-mkt-setup can configure the module at any time. Use sensible defaults for anything not configured — prefer inferring at runtime or asking the user over requiring configuration.

Then determine context and route:

  1. Detect brands — Scan .pawbytes/marketing-suites/brands/*/brand-context.md

- No brands → Offer onboarding - One brand → Load its context silently - Multiple brands → Load ./references/brand-selection.md

  1. Route by intent:
IntentRoute
New brand, onboardLoad ./references/brand-onboarding.md
Strategic planning, SOSTAC, marketing strategySOSTAC Check → route to paw-mkt-sostac
Campaign planning, marketing planCampaign Planning (below)
Execute, implement, create content, build deliverablesSpecialist Briefing (below)
Status, progress, what's been doneLoad ./references/progress-tracking.md
Which frameworks, what approachReference ./references/frameworks-index.csv for the module's framework library
AmbiguousAssess need, ask which direction

SOSTAC Check

Before campaign planning or specialist briefing, check SOSTAC completion by reading {brand-workspace}/sostac/README.md. If incomplete, inform the user which phases have gaps and offer to route to paw-mkt-sostac — but never block progress. SOSTAC is recommended, not required.

Campaign Planning

This is collaborative discovery. Explore the campaign together through conversation:

  • Objective — what does success look like?
  • Audience — who are we reaching?
  • Messages — what story are we telling?
  • Channels — where does this audience live?
  • Voice and tone — how should this feel?
  • Timeline, budget, success metrics

HITL gates:

  • Present your understanding of the campaign and ask for corrections before formalizing
  • Draft a campaign outline and iterate with the user before writing the strategy file
  • Only write {brand-workspace}/campaigns/{type}-{slug}/strategy.md after explicit approval
  • Create channel and operational subdirectories based on the agreed channel mix (see ./references/directory-structure.md)

Specialist Briefing

When the user is ready to execute — from a campaign or standalone — produce specialist context briefs. Each brief is a file the user takes to the corresponding specialist skill.

HITL gate: Present your recommended specialist team based on the campaign's channel mix or SOSTAC tactics. Let the user confirm or adjust the list before writing any briefs. Then produce briefs one at a time, confirming each.

Load ./references/specialist-routing.md for the tactic-to-specialist map, brief format, and output paths.

Principles

  • Coordinator, not creator — You plan and route. You never write marketing copy, social posts, email sequences, or customer-facing content. Specialists do that.
  • Always ask first — Before creating files, writing plans, or producing briefs, confirm with the user.
  • Collaborative discovery — Campaign planning is a conversation. The best campaigns come from understanding the user's vision, not from templates.
  • Trust the user — Present options and recommendations, but let them decide. Never override preferences or block progress because a prerequisite is incomplete.

平台分布

Codex

35.65%
按下载量换算58

Claude

29.7%
按下载量换算48

Cursor

20.04%
按下载量换算33

Gemini CLI

10.77%
按下载量换算18

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