Token导航 LogoToken导航

Agent Skill · 研究检索

appstorereject-scan(应用商店拒绝扫描)

appstorereject-scan 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。

appstorereject-scan 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,权限为接触敏感数据;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 70,834。

总安装 198周安装 8GitHub Stars 公开资料未说明下载 62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:appstorereject-scan(应用商店拒绝扫描)
来源仓库:https://github.com/nickgdwn/appstorereject-skills
仓库路径:skills/appstorereject-scan
安装命令:
npx skills add https://github.com/nickgdwn/appstorereject-skills --skill appstorereject-scan
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/nickgdwn/appstorereject-skills --skill appstorereject-scan

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。

appstorereject-scan 用于查找、检索和筛选应用商店拒绝扫描相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词或任务场景快速定位候选结果时使用。

扫描开发者代码库中的常见 App Store 和 Google Play 拒绝触发器,所有分析均在本地进行,不离开机器。通过 npx skills add 命令从指定 GitHub 仓库安装,需确认权限范围和维护状态,避免触发联网、命令执行或文件读写。

建议结合来源仓库和原始 README 核验具体用法,确保与宿主环境兼容,并在使用前验证 API 调用和配置选项的有效性。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/appstorereject-scan

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/nickgdwn/appstorereject-skills --skill appstor…;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

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

appstorereject-scan 怎么安装?

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

appstorereject-scan 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。

appstorereject-scan 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

appstorereject-scan 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。

appstorereject-scan 用的人多吗?

公开数据是累计安装 198 次,近一周安装 8 次,下载 62 次。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。

appstorereject-scan 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。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 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。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 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
appstorereject-scan

应用商店拒绝扫描 · 本页

198—接触敏感数据未明确未通过

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

Pre-Submission Scan

Scan the developer's codebase for common App Store and Google Play rejection triggers. All analysis happens locally — no code leaves the machine. Check definitions are served by the API for up-to-date coverage.

Scan Lifecycle

Execute these steps in order. Each step is a script call or API curl. Do NOT skip steps. Do NOT dispatch subagents.

0. Resolve API Key

Before any authenticated API call, resolve the API key. Check in this order:

  1. Run echo $ASR_API_KEY — if non-empty, use that value
  2. If empty, read ~/.appstorereject/config.json with the Read tool and extract the apiKey field value

Store the resolved key in your working memory. You will use it directly in curl commands throughout this scan. In every authenticated curl command below, replace $ASR_API_KEY with the actual key value — do NOT rely on the shell env var, because each Bash call runs in a separate shell context and exports do not persist.

If neither source has a key, tell the developer to set up an API key (see hub skill for setup instructions).

1. Detect Platform & Framework

node {baseDir}/scripts/detect-platform.js ./

Read the JSON output. Confirm with the developer:

  • "Detected {framework} targeting {platforms}. Bundle ID: {bundleId}. Is this correct?"
  • Ask: "Is this your first submission or an update?"
  • If both iOS and Android detected, ask: "Scan iOS, Android, or both?"

2. Auth Gate

Start the scan session:

curl -s -X POST -H "Authorization: Bearer $ASR_API_KEY" -H "Content-Type: application/json" -d '{"bundleId":"<bundleId>","scanType":"<first_submission|update>","platform":"<ios|android>"}' "https://api.appstorereject.com/api/scans/start"
  • 200: Save scanToken from response.
  • 403: Show error to developer (scan/app limit reached). Include upgrade URL.
  • 401: API key not set. Tell developer to run setup (see hub skill).

3. Load Graph

curl -s "https://api.appstorereject.com/api/scan/graph?platform=<detected>" > /tmp/asr-graph.json

4. Evaluate Skip Conditions

node {baseDir}/scripts/evaluate-section.js ./ --graph-file /tmp/asr-graph.json

Read the JSON output. Note sectionsToScan — these are the sections to load checks for.

5. Load Checks (Single Request)

curl -s "https://api.appstorereject.com/api/scan/checks?sections=<comma-separated-sectionsToScan>&framework=<detected>&platform=<detected>&scanToken=<token>" > /tmp/asr-checks.json

6. Execute Checks

For each section in sectionsToScan order, read that section's checks from /tmp/asr-checks.json.

For each check in the section:

  1. Execute the executionRule field — it contains Grep, Glob, and Read instructions. Run them against the developer's project.
  2. If the check triggers (the condition described in the execution rule is met), record a finding:

- guideline: from the check's guideline field — do NOT override - risk: from the check's risk field — do NOT override - finding: from the check's findingTemplate field, filling in {placeholders} from your analysis - slug: from the check's slug field — copy exactly (or null if absent) - checkId: from the check's checkId field - context: following the check's contextTemplate (max 200 chars, no code snippets, no file paths with usernames)

  1. If the check does NOT trigger, move to the next check silently.

After all sections are complete, write findings to temp file:

# Write the findings array as JSON to /tmp/asr-findings.json

Do NOT invent findings that aren't in the check definitions. If you notice something concerning without a matching check, mention it in a separate "Additional observations" section after the main output.

7. Collect Slugs

node {baseDir}/scripts/collect-slugs.js --findings-file /tmp/asr-findings.json

8. Fetch Resolution Guides

Run the fetchCommand from step 7's output:

# Execute the exact fetchCommand string from collect-slugs output
# Save response to /tmp/asr-guides.json

If fetchCommand is null (no slugs to fetch), skip to step 9 with no guides file.

9. Format Report

Pass the scan metadata from steps 1-2 so the analytics payload is complete:

node {baseDir}/scripts/format-report.js --findings-file /tmp/asr-findings.json --guides-file /tmp/asr-guides.json --scan-token <scanToken from step 2> --bundle-id <bundleId from step 1> --platform <platform> --framework <framework from step 1>

10. Present Results

Read format-report.js output:

  1. Show the findingsTable to the developer.
  2. For each entry in guideSections:

- Display resolutionSteps verbatim — do NOT paraphrase, summarize, or rewrite - Run the codebaseContextPrompt to search the developer's project for relevant files - Add an "In your codebase" subsection with what you found - Include prevention section if present

  1. For each entry in unguidedFindings:

- Note the finding and that no community guide is available yet - Provide brief guidance based on the finding details

NEVER silently replace API resolution guides with your own generated steps. The API guides are community-maintained. Your role: present them verbatim and add codebase context.

11. Report Analytics

curl -s -X POST -H "Authorization: Bearer $ASR_API_KEY" -H "Content-Type: application/json" -d '<analyticsPayload from format-report output>' "https://api.appstorereject.com/api/scans/complete"

12. Cleanup

rm -f /tmp/asr-graph.json /tmp/asr-checks.json /tmp/asr-findings.json /tmp/asr-guides.json

平台分布

Codex

36.49%
按下载量换算23

Claude

30.78%
按下载量换算19

Cursor

17.06%
按下载量换算11

Gemini CLI

8.22%
按下载量换算5

安全审计

Gen Agent Trust Hub

可疑

Socket

可疑

Snyk

未通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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