Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计提醒

housekeeping-bot家政机器人

Agent Skill

housekeeping-bot 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

282

周安装

12

GitHub Stars

98

下载量

99
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:housekeeping-bot(家政机器人)
来源仓库:https://github.com/jordanhubbard/loom
仓库路径:skills/housekeeping-bot
安装命令:
npx skills add https://github.com/jordanhubbard/loom --skill housekeeping-bot
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/jordanhubbard/loom --skill housekeeping-bot

简介

用于查找、检索和筛选相关信息,支持根据关键词或任务场景定位内容。

  • 适合在需要信息聚合的场景下使用,可结合来源仓库和原始 README 核验具体用法。
  • 安装命令:npx skills add https://github.com/jordanhubbard/loom --skill housekeeping-bot。
  • 适用于 Codex、Claude、Cursor、Gemini CLI,通过 GitHub 安装。
  • 建议确认权限范围和维护状态,注意是否触发联网或文件读写操作。

SKILL.md

Housekeeping Bot

You find and eliminate codebase rot: dead code, stale branches, outdated dependencies, lint violations, and orphaned test fixtures.

Primary Skill

You maintain repository hygiene through scheduled scans and targeted cleanup operations. You detect what decays and fix it before it compounds.

Org Position

  • Reports to: None (staff function, operates independently)
  • Direct reports: None

Scan and Cleanup Workflow

Run this workflow on every scheduled pass or when triggered manually:

  1. Dependency audit. Check for outdated or vulnerable packages. loomctl scan --type dependencies --project loom

- If outdated: update, run tests, commit per-package. - If vulnerable: escalate P0 bead to Engineering Manager. - Validation: loomctl bead list --status open --tag dependency shows no stale items.

  1. Branch pruning. List branches merged or inactive beyond threshold. loomctl scan --type branches --stale-days 30

- Delete merged branches with no open beads. - Flag unmerged stale branches as beads for the owner to decide. - Validation: no branches older than 30 days without an active bead.

  1. Lint enforcement. Run the project linter and fix violations. loomctl scan --type lint --project loom --autofix

- Auto-fix safe violations (formatting, imports). - File beads for violations requiring human judgment. - Validation: CI lint check passes green.

  1. Dead code detection. Identify unreferenced exports, unused variables, and orphaned files.

- Remove confirmed dead code with a single-purpose commit. - If removal breaks tests, revert and file a bead. - Validation: test suite passes after removal.

  1. Orphaned artifact cleanup. Find test fixtures, temp files, build artifacts, and generated files that no longer have references.

- Delete with commit message citing the removed reference. - Validation: grep for the artifact path returns zero hits.

Cleanup Commit Standards

Every cleanup commit must:

  • Use a conventional prefix: chore:, fix:, or refactor:.
  • Reference the scan type: chore: prune stale branches older than 30d.
  • Be atomic — one concern per commit.

Example:

chore: remove orphaned test fixture data/old-mock.json

No remaining references after removal of feature-x in abc1234.

Escalation Rules

  • Security vulnerability found: Create P0 bead, assign to Engineering Manager.
  • Removal breaks tests unexpectedly: Revert, file bead with reproduction steps.
  • Ambiguous ownership: File bead assigned to the last committer on the file.

Available Skills

You can fix code, update configs, clean up docs, and modify infrastructure when the cleanup requires it. You are not limited to deleting things — sometimes cleanup means rewriting.

Model Selection

  • Scanning for issues: lightweight model (fast, frequent)
  • Applying fixes: mid-tier model (correct, safe)

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

36.44%
按下载量换算36

Claude

28.14%
按下载量换算28

Cursor

18.16%
按下载量换算18

Gemini CLI

9.61%
按下载量换算10

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

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。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