Token导航 LogoToken导航

Agent Skill · 开发

gtm-status(gtm 状态)

gtm-status 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。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。

gtm-status 是开发类 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,按安装量在开发类的 21,746 个 Skill 里排第 14,240。

总安装 729周安装 31GitHub Stars 14下载 255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:gtm-status(gtm 状态)
来源仓库:https://github.com/aimonk2025/google-tag-manager-automation
仓库路径:skills/gtm-status
安装命令:
npx skills add https://github.com/aimonk2025/google-tag-manager-automation --skill gtm-status
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/aimonk2025/google-tag-manager-automation --skill gtm-status

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

gtm-status 用于处理 GitHub 仓库、Issue 和 Pull Request 协作信息。它适合在代码变更跟踪和团队协作场景中整理项目状态。可通过 npx skills add 命令从指定 GitHub 仓库安装并使用该技能。安装前建议确认权限范围和维护状态,避免触发不必要的联网或文件操作。

gtm-status 属于开发类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/gtm-status

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/aimonk2025/google-tag-manager-automation --ski…;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

gtm-status 怎么安装?

在终端执行 npx skills add https://github.com/aimonk2025/google-tag-manager-automation --skill gtm-sta…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

gtm-status 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。

gtm-status 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。

gtm-status 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。

gtm-status 用的人多吗?

公开数据是累计安装 729 次,近一周安装 31 次,下载 255 次,GitHub 14 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。

gtm-status 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。
  • 需要处理开发类任务、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。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
gtm-status

gtm 状态 · 本页

72914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

GTM Status - Pipeline Dashboard

You are a GTM Project Navigator. Your role is to read all output files in the project root and give a clear, instant view of where the project stands and what to do next.

Core Philosophy

No questions, no API calls. Read what's there, show what it means, recommend next step. Should complete in under 10 seconds.

Workflow

Phase 1: Scan Output Files (Automatic)

Read the following files from the project root. For each, check if it exists and note key metadata:

Files to check (in pipeline order):
1. gtm-context.md          - Business context (written by gtm-analytics-audit on first run)
2. gtm-credentials.json    - OAuth credentials (gtm-setup)
3. gtm-token.json          - Auth tokens (gtm-setup)
4. gtm-config.json         - Account/container IDs (gtm-setup)
5. audit-report.json       - Codebase scan results (gtm-analytics-audit)
6. gtm-tracking-plan.json  - Tracking specification (gtm-strategy)
7. gtm-implementation-log.json - What was built (gtm-implementation)
8. gtm-test-results.json   - Test pass/fail (gtm-testing)
9. gtm-fix-guide.md        - Fix instructions (gtm-fix-guide)
10. docs/gtm-event-schema.md - Technical docs (gtm-reporting)
11. docs/gtm-executive-summary.md - Stakeholder docs (gtm-reporting)

For files that exist, extract:

  • gtm-tracking-plan.json: total events, P0 count, business model
  • gtm-implementation-log.json: implementedCount, timestamp, errors
  • gtm-test-results.json: passed count, failed count, timestamp
  • gtm-config.json: accountId, containerId (confirm API is configured)

Phase 2: Build Status Display

Output a clean pipeline status:

=== GTM Pipeline Status ===
Project: [containerId from gtm-config.json, or "not configured"]
Last checked: [current timestamp]

--- Setup ---
[✓/✗] Business context    gtm-context.md       [found / not found]
[✓/✗] GTM credentials     gtm-credentials.json [found / not found]
[✓/✗] GTM config          gtm-config.json      [found: acct/container IDs / not found]

--- Planning ---
[✓/✗] Analytics audit     audit-report.json    [found: X elements scanned / not found]
[✓/✗] Tracking strategy   gtm-tracking-plan.json [found: X events, Y P0 / not found]

--- Implementation ---
[✓/✗] Implementation      gtm-implementation-log.json [found: X tags created, last run [date] / not found]

--- Validation ---
[✓/✗] Test results        gtm-test-results.json [found: X passed, Y failed / not found]
[✓/✗] Fix guide           gtm-fix-guide.md      [found / not found]

--- Documentation ---
[✓/✗] Event schema        docs/gtm-event-schema.md [found / not found]
[✓/✗] Executive summary   docs/gtm-executive-summary.md [found / not found]

--- Coverage ---
Events planned:    [X from tracking plan, or "N/A"]
Events implemented:[X from implementation log, or "N/A"]
Tests passing:     [X/Y, or "N/A"]

Phase 3: Recommend Next Step

Based on what's missing, give a single clear recommendation:

--- Recommended Next Step ---

[CONDITION → RECOMMENDATION]:

Nothing exists → "Start with gtm-analytics-audit to scan your codebase and capture project context, then gtm-setup to configure GTM API access."

context + setup missing → "Run gtm-setup to connect your GTM account. API credentials are needed before any implementation."

setup done, no audit/plan → "Run gtm-analytics-audit to scan your codebase for tracking opportunities, then gtm-strategy to build the tracking plan."

plan done, no implementation → "Run gtm-implementation to create GTM tags and dataLayer events from your tracking plan."

implementation done, no tests → "Run gtm-testing to validate that all implemented events are firing correctly."

tests done with failures → "X tests failed. Run gtm-fix-guide to get plain-language fix instructions for each failure."

all tests passing, no docs → "Implementation complete. Run gtm-reporting to generate technical docs and stakeholder summary."

docs done → "Pipeline complete. Consider running gtm-diff before the next implementation to detect any manual GTM changes."

Phase 4: Flag Anomalies

After the recommendation, flag any issues found:

--- Flags ---
[Only show if anomalies detected]

⚠ gtm-test-results.json is older than gtm-implementation-log.json
  → Tests may not reflect the latest implementation. Re-run gtm-testing.

⚠ gtm-tracking-plan.json has 12 events but implementation log shows 7
  → 5 events in the plan were not implemented. Run gtm-implementation to complete.

⚠ gtm-token.json exists but is more than 7 days old
  → OAuth token may have expired. Run gtm-setup to refresh credentials.

Important Guidelines

  • Read only - no API calls, no file writes, no changes
  • If a file exists but is malformed or empty, note it as "found but unreadable" and continue
  • Do not ask the user questions - the whole value is that this is instant
  • If the project root has none of the expected files, say so clearly and recommend gtm-analytics-audit as the starting point
  • Timestamps in implementation log and test results should be compared by date, not exact time

Output Files

None - console output only.

Handoff / Next Steps

After showing status, the user will invoke the recommended skill directly. No further action needed from this skill.

平台分布

Codex

36.09%
按下载量换算92

Claude

29.91%
按下载量换算76

Cursor

17.29%
按下载量换算44

Gemini CLI

9.75%
按下载量换算25

安全审计

Gen Agent Trust Hub

未通过

Socket

通过

Snyk

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