Skip to content
Back to skills

X Openai Skill Installer B36e203

ASecurity

Install Agent Skills into an explicitly selected host skill directory from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 14, 2026
ai-agentsshellgitapidocumentation

Works with

  • cli
  • api
  • mcp

Security analysis

A100/100

Pro scans all 9 files and shows the line behind each finding

Scanned October 14, 2026

npx -y skills add Geruyang/agent-skills-library --skill x-openai-skill-installer-b36e203 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of X Openai Skill Installer B36e203?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for X Openai Skill Installer B36e203
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/geruyang-x-openai-skill-installer-b36e203/badge)](https://www.skillsdirectory.com/skills/geruyang-x-openai-skill-installer-b36e203)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: x-openai-skill-installer-b36e203
description: Install Agent Skills into an explicitly selected host skill directory from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
metadata:
  short-description: Install curated skills from openai/skills or other repos
---

### 导出副本边界与技能别名

迁移、安装、修复和经验回写只作用于当前加载的目标宿主技能副本。原 Codex 技能/MCP、下载的源码和 `original-skills` 均为来源材料,不因执行本副本而写入;只有用户另行明确要求配置 Codex 产品本身时,才按该产品流程处理指定目标。脚本需要安装目录或状态目录时,显式提供目标路径;不得从 `CODEX_HOME` 隐式推断写入位置。

跨技能名称可能沿用源库别名。先查 [技能别名表](../../skill-aliases.json),优先选择同来源、同插件的条目,再使用其 `id` 调用或读取对应入口;不得假定旧 `$skill`、`superpowers:skill` 名称在新宿主直接注册。不能确定目标时先核对,不替换真实产品命令或 Shell 环境变量。

## 跨宿主使用约定

本副本供支持 Agent Skills 的客户端使用。先检查当前宿主实际提供的工具、权限和已连接服务,再执行正文工作流。原文中的宿主工具标识是能力参考;只有实际发现该工具时才可调用,其他宿主应使用经核验的等价 MCP、CLI 或 API。没有等价能力的步骤必须报告不可用,不能虚构调用或完成状态。

技能资源以本技能目录为基准;输出写入当前项目中用户指定的位置。通过技能名称或自然语言触发,具体快捷命令由宿主决定。涉及真实产品、模型 API、协议字段和官方网址的名称保持原意。授权、审批、隐私和工具范围限制在迁移后仍然有效;不得为兼容而扩大权限。具体依赖与迁移说明见同目录 `PORTABILITY.md`。

# Skill Installer

Helps install skills. By default these are from https://github.com/openai/skills/tree/main/skills/.curated, but users can also provide other locations.

Use the helper scripts based on the task:
- List skills when the user asks what is available, or if the user uses this skill without specifying what to do. Default listing is `.curated`, but you can pass `--path skills/.experimental` when they ask about experimental skills.
- Install from the curated list when the user provides a skill name.
- Install from another repo when the user provides a GitHub repo/path (including private repos).

Install skills with the helper scripts.

## Communication

When listing skills, output approximately as follows, depending on the context of the user's request. If they ask about experimental skills, list from `.experimental` instead of `.curated` and label the source accordingly:
"""
Skills from {repo}:
1. skill-1
2. skill-2 (already installed)
3. ...
Which ones would you like installed?
"""

After installing a skill, follow the current host's documented reload or restart behavior. Do not promise next-turn availability without verifying discovery.

## Scripts

These scripts use network access. Follow the current host's network and filesystem approval policy; request its supported approval when required, and stop if approval is denied.

- `scripts/list-skills.py` (prints skills list with installed annotations)
- `scripts/list-skills.py --format json`
- Example (experimental list): `scripts/list-skills.py --path skills/.experimental`
- `scripts/install-skill-from-github.py --repo <owner>/<repo> --path <path/to/skill> [<path/to/skill> ...]`
- `scripts/install-skill-from-github.py --url https://github.com/<owner>/<repo>/tree/<ref>/<path>`
- Example (experimental skill): `scripts/install-skill-from-github.py --repo openai/skills --path skills/.experimental/<skill-name>`

## Behavior and Options

- Defaults to direct download for public GitHub repos.
- If download fails with auth/permission errors, falls back to git sparse checkout.
- Aborts if the destination skill directory already exists.
- Pass `--dest <verified-host-skills-directory>` or set `AGENT_SKILLS_DIR`; the helper does not assume a host installation path. Verify this directory using the current host documentation and preserve all write approvals.
- Multiple `--path` values install multiple skills in one run, each named from the path basename unless `--name` is supplied.
- Options: `--ref <ref>` (default `main`), `--dest <path>`, `--method auto|download|git`.

## Notes

- Curated listing is fetched from `https://github.com/openai/skills/tree/main/skills/.curated` via the GitHub API. If it is unavailable, explain the error and exit.
- Private GitHub repos can be accessed via existing git credentials or optional `GITHUB_TOKEN`/`GH_TOKEN` for download.
- Git fallback tries HTTPS first, then SSH.
- The `.system` skills at https://github.com/openai/skills/tree/main/skills/.system may be bundled by particular products. Check the current installation before claiming they are preinstalled. Never overwrite an existing skill without explicit authorization; the helper aborts on an existing destination.
- Installed annotations come from `AGENT_SKILLS_DIR`. Set it to the same verified directory used for installation; without it, the list has no local installation annotations.

Files in this skill

  • LICENSE.txt11.3 KB
  • PORTABILITY.md1012 B
  • SKILL.md5.4 KB
  • agents/openai.yaml226 B
  • assets/skill-installer-small.svg926 B
  • assets/skill-installer.png1 KB
  • scripts/github_utils.py680 B
  • scripts/install-skill-from-github.py10.3 KB
  • scripts/list-skills.py3.1 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.