Token导航 LogoToken导航

Agent Skill · 研究检索

ghpm-status(ghpm 状态)

ghpm-status 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。

ghpm-status 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 48,806。

总安装 675周安装 29GitHub Stars 19下载 237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:ghpm-status(ghpm 状态)
来源仓库:https://github.com/jackchuka/ghpm
仓库路径:skills/ghpm-status
安装命令:
npx skills add https://github.com/jackchuka/ghpm --skill ghpm-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/jackchuka/ghpm --skill ghpm-status

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。

GHPM 状态技能用于信息查找、检索和筛选,支持关键词快速定位。适用于需要根据任务场景或来源线索定位候选结果的场景。通过 GitHub 仓库安装,使用 npx skills add 命令添加技能模块。安装前建议确认权限范围和维护状态,注意可能触发的网络请求。

ghpm-status 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/ghpm-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/jackchuka/ghpm --skill ghpm-status;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

ghpm-status 怎么安装?

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

ghpm-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。

ghpm-status 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。

ghpm-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。

ghpm-status 用的人多吗?

公开数据是累计安装 675 次,近一周安装 29 次,下载 237 次,GitHub 19 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。

ghpm-status 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
ghpm-status

ghpm 状态 · 本页

67519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

ghpm-status

PREREQUISITE: Read ../ghpm-shared/SKILL.md for prerequisites and error handling.

Comprehensive project health dashboard. The goal is to give the user a rich, actionable overview — not just counts, but breakdowns that surface where work is concentrated, who's overloaded, and what needs attention. Think of this as the dashboard a project manager checks every morning.

Arguments

  • /ghpm-status — full dashboard for the project
  • /ghpm-status <scope> — scoped to a team or component name (matched against field options in .ghpm/config.json)

Workflow

Phase 1: Load Config and Cache

Follow the startup sequence in ../ghpm-shared/SKILL.md and load cache per ../ghpm-shared/references/cache.md.

Phase 2: Aggregate

Count items by workflow column (using the workflow.field name from config to find the matching field on each item). Include a count for items with no status.

If a scope argument was provided, filter items first:

  • Match the argument against all field option names in .ghpm/config.json (case-insensitive).
  • If no exact match, try semantic/fuzzy matching. The user may use informal or umbrella terms that don't match any single field option but logically group several. Use your understanding of the project's team/component names to infer which options the user likely means, and combine them. Explain the mapping you chose (e.g., "Interpreting '' as + ").
  • If you still can't determine a reasonable match, list available options and ask the user to clarify — but try hard to infer first.
  • Filter items to only those matching the scope before aggregating.

Build the following sections from the cached items. Each section adds a different dimension of insight. Include all sections where the data exists — skip a section only if the project doesn't have that field.

Component Health

If a "Component" (or similar grouping) field exists, break down items by component × status. This reveals which areas of the project are healthy vs struggling. Show completion percentage per component and flag components with low completion or high active workload.

Epic Tracker

If items have a "Level" or type field that distinguishes epics from tasks, show epic-level status separately. Active epics (InProgress) are especially useful — list them with their component and assignees. Flag unassigned active epics as a risk.

Team Workload

Count InProgress items per assignee. This surfaces overload — anyone with 8+ concurrent InProgress items deserves a flag. Also count unassigned InProgress items.

Attention Items

Identify items needing attention:

  • Untriaged: items with no status, no component, or no assigned team (check which fields exist in config — not all projects have these fields).
  • No assignee: items in non-Done columns with empty assignees. Call out ReadyForDev items without owners specifically — they're bottlenecked.
  • Active InProgress: items in InProgress status — count as a workload indicator. No date info is available, so don't claim staleness.
Available Views

List available views with their layout type and filter text. Do NOT attempt to count items per view — filter parsing is handled by /ghpm-view. Just show the view name, layout, and raw filter so the user knows what's available.

For key normalization when matching fields, see ../ghpm-shared/references/cache.md.

Phase 3: Format Output

Format per conventions in ../ghpm-shared/references/format.md. Use markdown tables for breakdowns — they're easier to scan than flat text. Include a brief "Key Observations" section at the end that highlights 3-5 actionable insights (bottlenecks, risks, overloaded contributors).

The output should feel comprehensive. A good dashboard is one where the user doesn't need to ask follow-up questions to understand the project's health.

If scoped, prefix with the scope name: <Project Title> — <scope> — <filtered count> of <total> items

End with: Use /ghpm-view <name> to drill into a view.

Tips

  • Read-only — never modifies the project or its items.

See Also

平台分布

Codex

35.46%
按下载量换算84

Claude

30.08%
按下载量换算71

Cursor

19.5%
按下载量换算46

Gemini CLI

8.62%
按下载量换算20

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