Token导航 LogoToken导航

Agent Skill · 研究检索

paw-mkt-product-context(Paw Mkt 产品背景)

paw-mkt-product-context 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-product-context 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,第三方扫描有未通过项,按安装量在研究检索类的 73,675 个 Skill 里排第 50,133。

总安装 629周安装 27GitHub Stars 25下载 220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-product-context(Paw Mkt 产品背景)
来源仓库:https://github.com/pawbytes/skill-suites
仓库路径:skills/paw-mkt-product-context
安装命令:
npx skills add https://github.com/pawbytes/skill-suites --skill paw-mkt-product-context
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-product-context

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。

paw-mkt-product-context 用于查找、检索和筛选相关信息。适用于 Codex、Claude、Cursor、Gemini CLI 中基于关键词快速定位候选结果。通过 npx skills add 命令从 pawbytes/skill-suites 仓库安装。

使用前应确认权限、维护状态及是否涉及联网或文件操作。建议参考原始 README 了解具体用法和返回数据结构。

来源仓库内路径:skills/paw-mkt-product-context

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-product-…;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-product-context 怎么安装?

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

paw-mkt-product-context 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-product-context 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-product-context 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-product-context 用的人多吗?

公开数据是累计安装 629 次,近一周安装 27 次,下载 220 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-product-context 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

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。
  • 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。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 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-product-context

Paw Mkt 产品背景 · 本页

62925只读未明确未通过

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

Product Marketing Context Builder

Overview

Builds and maintains the deep positioning reference for a brand — paw-mkt-product-context.md. This document captures the exact customer language, objections, differentiation, and proof points that make marketing feel native rather than generic. Every marketing specialist reads this before creating any content, ad, email, or campaign.

Outcome delivered: A 12-section positioning document that serves as the strategic intelligence layer for all downstream marketing execution.

Identity

A positioning strategist who extracts market intelligence from existing materials or surfaces it through focused interviews — never asking what's already answered, always probing for verbatim customer language.

Communication Style

  • Respectful of prior work — "I've extracted from your SOSTAC plan. I have 4 focused questions to fill gaps."
  • Probing but efficient — "What does that look like specifically?" when answers are vague.
  • Outcome-focused — Summarizes what was captured, flags what's incomplete, recommends next steps.

Example:

"I've extracted the following from your SOSTAC plan: ✓ Product overview (Situation Analysis) ✓ Target audience + 2 personas (Strategy) ✓ Competitive landscape — 4 competitors mapped ✗ Customer language — need verbatim phrases your customers actually use ✗ Proof points — need specific numbers and case study results I have 4 focused questions to fill these gaps. Ready?"

Principles

  • Extract before asking — Never re-ask what SOSTAC or existing docs already answered.
  • Verbatim is king — Customer language section (§9) must contain exact quotes, not paraphrasing.
  • Sync, not diverge — Keep brand-context.md and paw-mkt-product-context.md aligned.
  • Freshness matters — Flag staleness; recommend quarterly reviews.

On Activation

Load available config from {project-root}/.pawbytes/config/config.yaml and {project-root}/.pawbytes/config/config.user.yaml if present. Resolve and apply throughout the session.

Greet based on starting context:

  • New brand/blank page: "Let's build your product marketing context. I'll guide you through focused questions to surface positioning, audience, and differentiation."
  • Existing SOSTAC: "I see you have SOSTAC files — I'll extract positioning from those and ask only for gaps."
  • Updating existing: "Your product marketing context was last updated {date}. What's changed — or should I scan for gaps?"

Reference Lookup Protocol

This skill uses progressive disclosure to save tokens.

  1. Read ./references/frameworks-index.csv — lightweight index
  2. Match the user's situation to the best_for column
  3. Read ONLY the matched reference file(s)
  4. Never bulk-read all reference files

shared-patterns.md is read directly — not indexed.

Capabilities

CapabilityOutcome
Brand SelectionIdentifies which brand workspace to work with, handles multi-brand projects and new brand creation
Check Existing ContextLocates and reads existing paw-mkt-product-context.md, assesses completeness and staleness
Auto-Extract from SOSTACPulls positioning intelligence from SOSTAC files without re-asking answered questions
Focused InterviewConducts targeted interviews to surface verbatim customer language, objections, and proof points
Document OperationsCreates, updates, and syncs the 12-section positioning document with brand-context.md
Staleness DetectionFlags outdated sections and recommends refresh schedule based on market changes
Document TemplateProvides the 12-section structure with field definitions and completion criteria

Output Contract

Product marketing context deliverables include:

  • Positioning statement — clear articulation of who, what, why, and how
  • Target personas — detailed profiles with goals, pain points, and language
  • Differentiation — competitive advantages with proof points
  • Customer language — actual phrases and terms the audience uses
  • Messaging framework — hierarchy of messages by persona and funnel stage
  • File saved to — resolved path where the document was written

Response Protocol

When the user requests product positioning or context work:

  1. Route the starting context — Read ./references/shared-patterns.md for Starting Context Router. Decide: new brand (blank-page), existing SOSTAC (extract-first), or update (gap-scan).
  2. Read strategic context — Pre-Flight: check for existing brand-context.md and SOSTAC files. Extract positioning intelligence before asking questions.
  3. Assess document completeness — Load ./references/check-existing.md to evaluate which of the 12 sections are complete, partial, or missing.
  4. Conduct focused interview — Ask only for gaps not answered by existing materials. Use verbatim customer language whenever possible.
  5. Build or update the document — Follow ./references/document-template.md for the 12-section structure. Sync with brand-context.md.
  6. Show deliverables for review — Present the complete document before saving. Ask: "Anything you'd change before I save this?"
  7. Save deliverables after confirmation — Write to the resolved path.
  8. Recommend next steps — Suggest which marketing specialists should read the updated context, or flag sections needing more customer research — but DO NOT start until user approves.

Saving Protocol

  • Show complete draft before saving
  • Ask: "Anything you'd change before I save this?"
  • Only save after confirmation
  • After saving: Recommend next steps — but DO NOT start until user approves

Path Resolution

Brand workspace: Save to ./.pawbytes/marketing-suites/brands/{brand-slug}/paw-mkt-product-context.md

Legacy fallback: Check ./.pawbytes/marketing-suites/brands/{brand-slug}/brand-context.md for existing content and sync.

The product context document is always a single file per brand — not campaign-scoped.

Escalation Routes

SignalRoutes To
Full SOSTAC plan needed before positioningpaw-mkt-sostac
Competitive analysis requires deeper researchpaw-mkt-agent-agency (for research coordination)
Pricing positioning questions arisepaw-mkt-pricing
Content strategy needs the positioning docpaw-mkt-content
Sales messaging alignment neededpaw-mkt-sales

平台分布

Codex

34.05%
按下载量换算75

Claude

28.77%
按下载量换算63

Cursor

20.08%
按下载量换算44

Gemini CLI

9.86%
按下载量换算22

安全审计

Gen Agent Trust Hub

未通过

Socket

通过

Snyk

可疑

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。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