Token导航 LogoToken导航TokenDH.com
待分类敏感数据github未标认证来源可访问许可证需确认审计通过

aios-skill-publisheraios 技能发布者

Agent Skill

aios-skill-publisher 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。

总安装

312

周安装

13

GitHub Stars

公开资料未说明

下载量

104
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:aios-skill-publisher(aios 技能发布者)
来源仓库:https://github.com/mrnobrands/aios-skills
仓库路径:skills/aios-skill-publisher
安装命令:
npx skills add https://github.com/mrnobrands/aios-skills --skill aios-skill-publisher
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/mrnobrands/aios-skills --skill aios-skill-publisher

简介

aios-skill-publisher 用于自动化创建和发布专有技能,确保技能格式一致并通过 npx 安装到指定 GitHub 仓库。

  • 适用于内部技能开发、工作流转换和重复性任务封装,支持自定义技能命名和发布流程标准化。
  • 通过 npx skills add 命令从 mrnobrands/aios-skills 仓库安装,需遵循 aios- 前缀命名规则。
  • 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读写操作。
  • 使用前应确认是否为专有技能创建,避免用于市场技能安装或通用流程处理。

SKILL.md

AIOS Skill Publisher

Purpose

Automate the creation and publishing of proprietary skills for Claim Supply / NoManagement B.V. Ensures every custom skill follows a consistent format, uses the aios- prefix, publishes to the mrnobrands/aios-skills GitHub repo, and becomes installable via npx.

When to Use

  • User asks to create, build, make, or write a new skill
  • User asks to publish a skill to the AIOS repo
  • User wants to convert a workflow or process into a reusable skill
  • User references proprietary skill creation or aios-skills

Do NOT Use For

  • Installing marketplace skills (use npx skills add directly)
  • Editing existing marketplace community skills
  • Creating skills for other repos or systems

Context Loading

Always Read

  1. This SKILL.md
  2. references/skill-template.md — blank template for new skills
  3. references/naming-rules.md — naming and format conventions

Process

Step 1: Gather Requirements

Ask the user (if not already clear):

  • What does this skill do? (one sentence)
  • When should it trigger? (what phrases or tasks activate it)
  • Does it need reference files? (templates, examples, patterns)

If the user has already provided enough detail, skip to Step 2.

Step 2: Determine Skill Name

  • Take the users description and create a kebab-case name
  • Prepend aios- prefix (always lowercase)
  • Examples: aios-lead-scoring, aios-weekly-digest, aios-client-onboarding
  • Confirm the name with the user before proceeding

Step 3: Locate the Repo

Detect which machine you are on:

  • If /Users/luca exists → Mac path: /Users/luca/NoBrands Dropbox/MR. NO/Github/aios-skills/
  • If /home/luca exists and no /Users → VPS path: /home/luca/aios-skills/

Step 4: Create Skill Directory

mkdir -p [REPO_PATH]/aios-[skill-name]/references

Step 5: Write SKILL.md

Use the template from references/skill-template.md. Critical rules:

  • name field matches directory name exactly (all lowercase, kebab-case)
  • description under 1024 characters, no XML angle brackets
  • description includes trigger phrases, NOT a workflow summary
  • Include metadata.author: claim-supply and metadata.version: 1.0.0
  • Required sections: Purpose, When to Use, Context Loading, Process, Quality Gates, Output Format

Step 6: Create Reference Files (if needed)

Place in references/ directory. Each file is kebab-case.md. Only create references the skill actually needs.

Step 7: Validate

  • name field matches directory name (lowercase kebab-case)
  • description has trigger phrases, not workflow summary
  • description under 1024 characters, no angle brackets
  • All required sections present
  • No placeholder text remaining
  • No README.md in skill folder

Step 8: Publish to GitHub

cd [REPO_PATH] && git add -A && git commit -m "Add aios-[skill-name]" && git push

Step 9: Install Locally

npx -y skills add -y -g mrnobrands/aios-skills

Step 10: Notify User

Report: skill name, GitHub URL, install command, confirmation of local install.

Quality Gates

  • Lowercase aios- prefix naming convention followed
  • Folder name matches name field exactly
  • YAML frontmatter valid and under 1024 chars
  • Description contains trigger phrases only
  • All SKILL.md sections present and filled in
  • No README.md in skill folder
  • Git push succeeded
  • npx install succeeded

Output Format

  1. New directory in mrnobrands/aios-skills repo
  2. Valid SKILL.md with proper frontmatter
  3. Optional reference files in references/
  4. Git commit and push to GitHub
  5. Local npx install

Examples

Example 1: Create a lead scoring skill

User says: "Create a new skill for scoring incoming leads" Result: aios-lead-scoring/ with SKILL.md, pushed to GitHub, installed locally

Example 2: Convert a process to a skill

User says: "Turn our weekly digest process into a skill" Result: aios-weekly-digest/ with full process as a skill

Troubleshooting

Git push fails

Cause: No git credentials or repo not cloned. Fix Mac: Check gh auth status. Run gh auth login if needed. Fix VPS: Check git config. May need personal access token.

npx install shows old skills

Cause: npm cache serving stale version. Fix: Wait 1-2 minutes and retry.

Skill does not trigger

Cause: Description missing trigger phrases or too vague. Fix: Add specific keywords. Test: "When would you use the [skill] skill?"

References

  • references/skill-template.md — Blank SKILL.md template
  • references/naming-rules.md — Naming conventions and rules

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

33.25%
按下载量换算35

Claude

33.72%
按下载量换算35

Cursor

17.25%
按下载量换算18

Gemini CLI

10.04%
按下载量换算10

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

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。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