Token导航 LogoToken导航TokenDH.com
研究检索需要联网github未标认证来源可访问许可证需确认审计异常

paw-cra-setup爪子克拉设置

Agent Skill

paw-cra-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。

总安装

447

周安装

19

GitHub Stars

25

下载量

157
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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-cra-setup(爪子克拉设置)
来源仓库:https://github.com/pawbytes/skill-suites
仓库路径:skills/paw-cra-setup
安装命令:
npx skills add https://github.com/pawbytes/skill-suites --skill paw-cra-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-cra-setup

简介

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。

SKILL.md

Pawbytes Creative Suites Setup

Overview

Installs and configures the Pawbytes Creative Suites module into a project. Module identity (name, code, version) comes from ./assets/module.yaml. Collects user preferences and writes them to the Pawbytes ecosystem config:

  • {project-root}/.pawbytes/config/config.yaml — shared project config: core settings at root plus a cra: section with module-specific values.
  • {project-root}/.pawbytes/config/config.user.yaml — personal settings intended to be gitignored: API keys and any variable marked user_setting: true in ./assets/module.yaml. These values live exclusively here.
  • {project-root}/.pawbytes/config/module-help.csv — registers module capabilities for the help system.

Both config scripts use an anti-zombie pattern — existing entries for this module are removed before writing fresh ones, so stale values never persist.

{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, not the skill root.

On Activation

  1. Read ./assets/module.yaml for module metadata and variable definitions (the code field cra is the module identifier)
  2. Check if {project-root}/.pawbytes/config/config.yaml exists — if a cra: section is already present, inform the user this is an update
  3. Check for existing config at {project-root}/_bmad/config.yaml (legacy BMad format). If found, inform the user that legacy config can be migrated to the new Pawbytes ecosystem format.

If the user provides arguments (e.g. accept all defaults, --headless, or inline values like user name is Alice, fal key is abc123), 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 fal_key to abc123, 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: user), 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.

API Keys (stored in config.user.yaml, not committed):

  • fal_keyRequired for image/video generation
  • elevenlabs_api_key — Optional, for AI voiceover
  • pexels_api_key — Optional, for stock media research

Write Files

Write a temp JSON file with the collected answers structured as {"core": {...}, "module": {...}}. Then run the config merge script:

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}

Then register capabilities with the help CSV merge:

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

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

Create Output Directories

After writing config, create any output directories that were configured. For filesystem operations, resolve the {project-root} token and create each path:

mkdir -p "{project-root}/.pawbytes/creative-suites"
mkdir -p "{project-root}/.pawbytes/creative-suites/brands"
mkdir -p "{project-root}/.pawbytes/creative-suites/knowledge"
mkdir -p "{project-root}/.pawbytes/creative-suites/daily"

Confirm

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

Outcome

Once the user's user_name and communication_language are known, use them consistently for the remainder of the session: address the user by their configured name and communicate in their configured language.

File Structure After Setup

{project-root}/
  .pawbytes/
    config/
      config.yaml           # Shared config (committed)
      config.user.yaml      # User settings (gitignored)
      module-help.csv       # Capability registry
    creative-suites/
      index.md              # Agency memory index
      brands/               # Brand guidelines and assets
      knowledge/            # Research and references
      daily/                # Activity logs

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

34.01%
按下载量换算53

Claude

29.92%
按下载量换算47

Cursor

17.62%
按下载量换算28

Gemini CLI

8.93%
按下载量换算14

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills