Token导航 LogoToken导航

Agent Skill · 研究检索

paw-ps-setup(爪子 ps 设置)

paw-ps-setup 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-ps-setup 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 55,679。

总安装 470周安装 19GitHub Stars 25下载 147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-ps-setup(爪子 ps 设置)
来源仓库:https://github.com/pawbytes/skill-suites
仓库路径:skills/paw-ps-setup
安装命令:
npx skills add https://github.com/pawbytes/skill-suites --skill paw-ps-setup
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-ps-setup

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-ps-setup 用于查找、检索和筛选相关信息。适合在 Codex、Claude、Cursor、Gemini CLI 中按关键词或场景获取结果。通过 npx skills add 命令从 pawbytes/skill-suites 仓库安装。使用前应检查权限、维护状态及是否调用外部接口。

建议查阅原始文档以明确功能细节和使用方式。

来源仓库内路径:skills/paw-ps-setup

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-ps-setup;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-ps-setup 怎么安装?

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

paw-ps-setup 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-ps-setup 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-ps-setup 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-ps-setup 用的人多吗?

公开数据是累计安装 470 次,近一周安装 19 次,下载 147 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-ps-setup 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-ps-setup

爪子 ps 设置 · 本页

47025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

Prodig Suites Setup

Overview

Installs and configures Prodig Suites into a project. Prodig Suites is a product creation system that guides users from vague idea to production-ready product, supporting four product families: Knowledge, Template, Software, and Service.

This setup skill scaffolds the complete workspace structure including:

  • {project-root}/.pawbytes/prodig-suites/ — Module root
  • {project-root}/.pawbytes/prodig-suites/memory/paw-ps-sidecar/ — Shared memory sidecar
  • {project-root}/.pawbytes/prodig-suites/products/ — Product workspaces
  • {project-root}/.pawbytes/prodig-suites/artifacts/ — Generated outputs

Configuration is written to the Pawbytes ecosystem config:

  • {project-root}/.pawbytes/config/config.yaml — Shared project config with ps: section for module-specific values
  • {project-root}/.pawbytes/config/config.user.yaml — Personal settings (user_name, communication_language)
  • {project-root}/.pawbytes/config/module-help.csv — Registers module capabilities

{project-root} is a literal token in config values — never substitute it with an actual path. It signals to the consuming LLM that the value is relative to the project root.

Principles

  • Sensible defaults: Every setting has a reasonable default; users only override what matters to them
  • Idempotent setup: Running setup multiple times preserves existing work and memory
  • Clear confirmation: Show exactly what will change before writing files
  • Progressive disclosure: Scaffold starter files with headings and brief instructions, not full content
  • Capability detection: Verify optional research/reporting capabilities and note what's missing

On Activation

  1. Read ./assets/module.yaml for module metadata and variable definitions (the code field ps is the module identifier)
  2. Check if {project-root}/.pawbytes/prodig-suites/ exists — if present, inform the user this is an update
  3. Check for core Pawbytes config at {project-root}/.pawbytes/config/config.yaml

If the user provides arguments (e.g. accept all defaults, --headless, or inline values like default mode is template, quality bar is publish-ready), map any provided values to config keys, use defaults for the rest, and skip interactive prompting. Still display the full confirmation summary at the end.

Collect Configuration

Ask the user for values. Show defaults in brackets. Present all values together so the user can respond once with only the values they want to change (e.g. "change quality bar to publish-ready, rest are fine"). Never tell the user to "press enter" or "leave blank" — in a chat interface they must type something to respond.

Default priority (highest wins): existing config values > ./assets/module.yaml defaults.

Core config (only if no core keys exist yet): user_name (default: Pawbytes), communication_language and document_output_language (default: English — ask as a single language question, both keys get the same answer). Of these, user_name and communication_language are written exclusively to config.user.yaml.

Module config: Read each variable in ./assets/module.yaml that has a prompt field. Ask using that prompt with its default value.

Load ./references/config-variables.md for detailed descriptions of each configuration variable.

Create Directory Structure

After collecting configuration, create the complete workspace structure:

Note: {project-root} is a literal token that resolves to the project root directory at runtime. Do not substitute it with an actual path.
# Main module directories
mkdir -p "{project-root}/.pawbytes/prodig-suites/memory/paw-ps-sidecar/curated/product-types"
mkdir -p "{project-root}/.pawbytes/prodig-suites/memory/paw-ps-sidecar/daily"
mkdir -p "{project-root}/.pawbytes/prodig-suites/products"
mkdir -p "{project-root}/.pawbytes/prodig-suites/artifacts"

Create Sidecar Files

1. Create index.md (Orientation File)

Create {project-root}/.pawbytes/prodig-suites/memory/paw-ps-sidecar/index.md:

# Prodig Suites Memory Index

**Created:** {YYYY-MM-DD}
**Last Updated:** {YYYY-MM-DD}

Welcome to Prodig Suites! This is the shared memory system that maintains context across all your product creation sessions.

## Active Products

No products yet. Start your first product with:
- "I want to create a course about..."
- "Help me build a template pack for..."
- "I have an idea for a SaaS product..."
- "I want to productize my service for..."

## Recent Activity

*No activity yet — this will be populated as you work.*

## Curated Files Status

| File | Status | Description |
|------|--------|-------------|
| product-context.md | Pending | Active product definition |
| market-intelligence.md | Pending | Research synthesis |
| audience-intelligence.md | Pending | Customer insights |
| product-decisions.md | Pending | Decision history |
| output-standards.md | Ready | Quality criteria (has defaults) |

## Product Types

Prodig Suites supports four product families:

1. **Knowledge Products** — Courses, ebooks, guides, memberships
2. **Template Products** — Templates, prompt packs, digital kits
3. **Software Products** — SaaS, apps, AI tools
4. **Service Products** — Productized services, consulting packages

## How Memory Works

- **Daily files** capture session activity (chronological, append-only)
- **Curated files** hold structured knowledge (updated as you progress)
- **Index** (this file) provides quick orientation
- All agents share this memory, so context persists across sessions

## Quick Reference

| Skill | Purpose |
|-------|---------|
| paw-ps-agent-product-builder | Main coordinator — start here |
| paw-ps-discovery | Idea exploration and validation |
| paw-ps-research | Market and competitor research |
| paw-ps-audience | Customer research and personas |
| paw-ps-research-to-brief | Convert research into product brief |
| paw-ps-strategist | Product packaging and positioning |
| paw-ps-concept-to-product-plan | Transform brief into executor-ready plan |
| paw-ps-knowledge-executor | Build courses, ebooks, guides |
| paw-ps-template-executor | Build templates, prompt packs, kits |
| paw-ps-software-executor | Build SaaS, apps, AI tools |
| paw-ps-service-executor | Build productized services |
| paw-ps-product-package-assembler | Bundle into deliverable package |
| paw-ps-publish-ready-check | Evaluate production readiness |

## Getting Started

Tell me what you want to create, and I'll help you through the full journey from idea to production-ready product.

2. Create Starter Curated Files

Create each curated file with headings and brief instructions:

product-context.md
# Product Context

*No active product yet. This file will be populated when you start a product.*

## How to Use This File

This file captures the essential context for your active product:

- **Product Name** — Working title
- **Product Type** — Knowledge, Template, Software, or Service
- **Core Premise** — What it does and why
- **Target Audience** — Who it's for
- **Current Stage** — discovery, research, brief, execution

## Starting a Product

Tell the orchestrator:
- What product you want to create
- What type it might be (if you know)
- Who it's for (if you know)
market-intelligence.md
# Market Intelligence

*Market research will be synthesized here.*

## Purpose

Captures competitive landscape, market positioning, and opportunity signals.

## Sections (populated by research)

- **Competitive Landscape** — Who else serves this market
- **Market Gaps** — Underserved needs and opportunities
- **Positioning Signals** — How to differentiate
- **Validation Points** — Evidence of demand
audience-intelligence.md
# Audience Intelligence

*Customer insights will be synthesized here.*

## Purpose

Captures deep understanding of target customers and their needs.

## Sections (populated by research)

- **Primary Persona** — Core customer profile
- **Pain Points** — Problems they're trying to solve
- **Desired Outcomes** — What success looks like
- **Buying Triggers** — What motivates purchase
- **Language Patterns** — How they describe their problems
product-decisions.md
# Product Decisions

*Key decisions will be logged here.*

## Purpose

Tracks important decisions made during product development with context for future reference.

## Decision Log Format

| Date | Decision | Rationale | Alternatives Considered |
|------|----------|-----------|------------------------|
| | | | |

## Why This Matters

- Provides context for future iterations
- Helps explain "why did we do X?"
- Prevents revisiting settled questions
output-standards.md
# Output Standards

Quality criteria for Prodig Suites deliverables.

## Configured Quality Bar

**Current Setting:** {quality_bar from config}

### Quality Bar Definitions

| Level | Definition |
|-------|------------|
| draft | Complete structure with placeholder content |
| production-ready | Complete, no placeholders, usable by intended audience |
| publish-ready | Polished, formatted, ready for publication |
| sellable-ready | Complete, polished, ready to sell |

## Product-Type Standards

### Knowledge Products
- Clear learning objectives
- Logical progression
- Actionable content
- Complete materials

### Template Products
- Working templates
- Clear instructions
- Consistent formatting
- Reusable design

### Software Products
- Clear feature definition
- User flow documented
- Technical requirements stated
- MVP scope defined

### Service Products
- Clear offer structure
- Defined deliverables
- Scope boundaries
- Pricing logic

## Output Style

**Current Setting:** {output_style from config}

| Style | Description |
|-------|-------------|
| structured-practical | Clear sections, actionable, ready to use |
| narrative-engaging | Story-driven, conversational, engaging |
| technical-detailed | Comprehensive, thorough, documentation-heavy |

3. Create Product Type Files

Create {project-root}/.pawbytes/prodig-suites/memory/paw-ps-sidecar/curated/product-types/:

knowledge-products.md
# Knowledge Products

Best practices and structures for courses, ebooks, guides, and memberships.

## Product Types

### Courses
- Define learning outcomes first
- Structure in modules → lessons → topics
- Include practice activities
- Plan assessments

### Ebooks/Guides
- Define reader transformation
- Structure in chapters → sections
- Include examples and templates
- Plan call-to-actions

### Memberships
- Define content pillars
- Plan release cadence
- Structure access levels
- Design community elements

## Output Structure

knowledge-product/ ├── curriculum.md # Course outline or chapter structure ├── modules/ │ ├── module-1.md │ └── ... ├── materials/ # Supporting materials └── assets/ # Images, downloads, etc.


## Quality Checklist

- [ ] Learning objectives defined
- [ ] Logical progression verified
- [ ] Practice activities included
- [ ] All content complete (no placeholders)
template-products.md
# Template Products

Best practices for templates, prompt packs, and digital kits.

## Product Types

### Templates
- Solve specific problems
- Include clear instructions
- Use placeholder conventions
- Design for reusability

### Prompt Packs
- Group by use case
- Include example outputs
- Document parameters
- Provide variation templates

### Digital Kits
- Combine complementary assets
- Provide assembly guide
- Include source files
- Document dependencies

## Output Structure

template-product/ ├── templates/ │ └── template-1.{ext} ├── guide.md # Usage instructions ├── examples/ # Example outputs └── assets/ # Supporting files


## Quality Checklist

- [ ] Templates are functional
- [ ] Instructions are clear
- [ ] Formatting is consistent
- [ ] Design is reusable
software-products.md
# Software Products

Best practices for SaaS, apps, and AI tools.

## Product Types

### SaaS/Apps
- Define core value proposition
- Map user journeys
- Define MVP features
- Plan technical architecture

### AI Tools
- Define AI capabilities
- Document prompts/flows
- Plan integrations
- Design user interface

## Output Structure

software-product/ ├── prd-lite.md # Product requirements ├── features/ │ └── feature-1.md ├── user-flows/ │ └── flow-1.md └── technical/ └── architecture.md


## Quality Checklist

- [ ] Value proposition clear
- [ ] MVP scope defined
- [ ] User flows documented
- [ ] Technical requirements stated
service-products.md
# Service Products

Best practices for productized services and consulting packages.

## Product Types

### Productized Services
- Define clear deliverables
- Set scope boundaries
- Standardize process
- Create pricing tiers

### Consulting Packages
- Define outcomes
- Structure engagements
- Create templates
- Document process

## Output Structure

service-product/ ├── offer.md # Offer structure and pricing ├── deliverables/ │ └── deliverable-1.md ├── process.md # Delivery process └── templates/ # Service delivery templates


## Quality Checklist

- [ ] Deliverables are clear
- [ ] Scope is bounded
- [ ] Pricing is defined
- [ ] Process is documented

Verify Capabilities

Check for optional capabilities that enhance Prodig Suites:

Research Capabilities

  • Web search tool available (WebSearch, mcp__exa__web_search_exa)
  • Code graph context available (mcp__CodeGraphContext__*)

Reporting Capabilities

  • Presentation generation available (paw-tools-presentation)
  • Release tools available (paw-tools-release)

Note any missing capabilities in the confirmation message. These are optional but enhance the suite's power.

Write Files

Write a temp JSON file with the collected answers structured as {"core": {...}, "module": {...}} (omit core if it already exists). Then run both scripts:

python3 ./scripts/merge-config.py \
  --config-path "{project-root}/.pawbytes/config/config.yaml" \
  --user-config-path "{project-root}/.pawbytes/config/config.user.yaml" \
  --module-yaml ./assets/module.yaml \
  --answers {temp-file}

python3 ./scripts/merge-help-csv.py \
  --target "{project-root}/.pawbytes/config/module-help.csv" \
  --source ./assets/module-help.csv \
  --module-code ps

Both scripts output JSON to stdout with results. If either exits non-zero, surface the error and stop.

Run ./scripts/merge-config.py --help or ./scripts/merge-help-csv.py --help for full usage.

Confirm

Use the script JSON output to display what was written — config values set, user settings written to config.user.yaml (user_keys in result), help entries added, fresh install vs update. Then display the module_greeting from ./assets/module.yaml to the user.

Display a comprehensive summary:

## Setup Complete

### Configuration
- Default product mode: {value}
- Quality bar: {value}
- Output style: {value}
- Research depth: {value}

### Created Directories
- .pawbytes/prodig-suites/memory/paw-ps-sidecar/
- .pawbytes/prodig-suites/products/
- .pawbytes/prodig-suites/artifacts/

### Created Files
- index.md — Orientation file
- product-context.md — Active product context
- market-intelligence.md — Market research synthesis
- audience-intelligence.md — Customer insights
- product-decisions.md — Decision log
- output-standards.md — Quality criteria
- product-types/*.md — Product family guides

### Capability Status
{List available/missing optional capabilities}

### What's Next
Start with `paw-ps-agent-product-builder` to create your first product.

Then display the module_greeting from ./assets/module.yaml.

Outcome

Once the user's user_name and communication_language are known (from collected input, arguments, or existing config), use them consistently for the remainder of the session: address the user by their configured name and communicate in their configured language.

Output Contract

Once setup completes, the following are guaranteed:

  • Action type: Module installation/configuration
  • Files created:

- {project-root}/.pawbytes/prodig-suites/ directory structure - {project-root}/.pawbytes/prodig-suites/memory/paw-ps-sidecar/index.md - {project-root}/.pawbytes/prodig-suites/memory/paw-ps-sidecar/curated/*.md - {project-root}/.pawbytes/prodig-suites/memory/paw-ps-sidecar/curated/product-types/*.md - {project-root}/.pawbytes/config/config.user.yaml (if core config collected)

  • Recommendations: Suggest running paw-ps-agent-product-builder to start first product
  • File saved to: {project-root}/.pawbytes/prodig-suites/

平台分布

Codex

35.07%
按下载量换算52

Claude

32.03%
按下载量换算47

Cursor

20.44%
按下载量换算30

Gemini CLI

10.45%
按下载量换算15

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