Skill Installer
Official Codex skill for listing and installing skills from curated OpenAI sources or GitHub repositories.
- Skill Road
- Skill Installer
Categories
Skill Installer is an official sample skill from the OpenAI Codex repository. The verified primary source is https://github.com/openai/codex/tree/main/codex-rs/skills/src/assets/samples/skill-installer. It helps Codex discover skills for a local working environment and install them into the skills directory. The candidate source reported by Smithery originally pointed to codex-rs/core/src/skills/assets/samples/skill-installer. That path is no longer reachable on the current main branch. The verified, semantically matching primary source is codex-rs/skills/src/assets/samples/skill-installer, which contains SKILL.md and the supporting helper scripts. According to the provider, the skill covers three common situations: listing available skills, installing a named skill from the curated collection, and installing a skill from a GitHub repository and a supplied path.
Purpose and workflow
The skill packages a repeatable installation workflow without becoming a general package manager. For a listing it uses list-skills.py. The default collection is the curated area of the official openai/skills repository; experimental skills can be requested explicitly through the experimental path. For GitHub installation, the instructions point to install-skill-from-github.py. A repository owner and name, a path inside the repository, or a complete GitHub URL can be supplied. The default method downloads directly. If permission or authentication failures occur, the intended Git fallback can be used.
The destination is the skills directory below CODEX_HOME/skills, while an environment can provide its own CODEX_HOME value. Without that variable, Codex uses the user-directory default described by the provider. Several paths can be installed in one operation. A name option can set the destination name; otherwise the name is derived from the final path component. The workflow aborts when the destination already exists, preventing an existing installation from being overwritten silently. After a successful installation, the user should be told that the skill will be available on the next turn. The official documentation also explains that a restart may be needed if a newly installed capability does not appear immediately.
Practical value and boundaries
Skill Installer is useful when a team wants to extend Codex deliberately without rewriting installation instructions for every individual skill directory. It makes the source and destination of an installation more explicit and separates curated, experimental, and repository-based sources. It does not guarantee the quality of the installed skill. An accessible GitHub repository proves neither that its scripts are safe nor that every instruction it contains is trustworthy. Before team-wide use, review the repository, revision, license, change history, and required tools.
The skill is not an OpenAI API client, an MCP server, or a central permission manager. It installs files into a local Codex environment. Network access occurs during the intended listing and download operations; private repositories may depend on existing Git credentials or already configured authentication. Credentials, tokens, private source code, and confidential project data do not belong in the skill description or installation examples. Installed material can contain instructions and scripts that are later used in an agent context. Teams should therefore require a controlled working copy, least-privilege access, and human review before productive changes.
Classification and security
The official Codex documentation describes skills as directories with a required SKILL.md and optional scripts, references, or resources. Skill Installer follows that model by installing complete skill directories rather than isolated text fragments. According to the provider, system skills are already preinstalled and normally do not need to be installed again. Anyone who nevertheless wants to overwrite a system skill should review the consequences and local configuration explicitly. A local skill can be disabled through the relevant skills entry in Codex configuration without immediately deleting its files.
The canonical source for this catalog entry is the current Codex path at codex-rs/skills/src/assets/samples/skill-installer; the original candidate URL is preserved as an outdated registry mapping. The Codex repository publishes its source under Apache-2.0. GitHub stars are not stored because the Skill model has no github_stars field. This classification was reviewed on September 9, 2026. Skill Installer makes local distribution easier, but it does not replace dependency review, permission review, or approval by the responsible person.
Installation instructions
Step 1: What the Skill Installer is and why it matters
The Skill Installer is a system skill from OpenAI that is built directly into the openai/skills repository at skills/.system/skill-installer and ships by default with OpenAI's Codex CLI tool. Codex is OpenAI's command-line assistant for coding tasks, conceptually comparable to Claude Code, and likewise uses a skill system in which individual markdown files with instructions provide additional knowledge or capabilities. The Skill Installer's job is to install further skills, either from OpenAI's curated list under skills/.curated in the same repository or from any other GitHub repository, including private repositories, when the appropriate credentials are available. The skill is relevant for anyone who wants to extend Codex with additional community or internal company capabilities without manually copying files into the right directory.
Step 2: Prerequisites
Since the Skill Installer already ships as a preinstalled system skill with every Codex installation, all that is initially needed is a working Codex CLI installation. Installing skills themselves requires network access, so the underlying helper scripts, per the documentation, need explicit permission for network access when running inside a sandboxed environment. Anyone wanting to install skills from private GitHub repositories needs either existing git credentials already present on the system or an environment variable holding a GitHub token, named either GITHUB_TOKEN or GH_TOKEN.
Setting it up step by step
Because the skill is already preinstalled, there is no separate setup step for the skill itself; it is used directly by asking Codex for it. To first see which skills are available, you can request the curated list, where the underlying script by default reads the .curated folder and can be switched to the .experimental folder via the --path option to view experimental skills. Installing a specific skill from the curated list only requires naming it, after which the install-skill-from-github.py script creates the skill under the CODEX_HOME/skills directory named after the skill, defaulting to the .codex/skills path inside the user's home directory. For skills from other repositories, you instead provide either the repository path together with the path to the skill inside that repository, or the full GitHub URL to the corresponding directory directly, optionally combined with a different branch name via the --ref option.
Security and best practices
Because installing a skill from an arbitrary GitHub repository means adopting instructions, and sometimes executable helper scripts, written by a third party, the content of a SKILL.md file and any referenced scripts should be reviewed before installation, especially when the source is not OpenAI's curated list. The curated list is at least subject to editorial selection by OpenAI, while arbitrary GitHub repositories are not, and should be treated with the same caution as any other external code dependency. Per the documentation, the installer aborts if the destination directory already exists, which prevents accidental overwrites; the preinstalled system skills under .system can be overwritten if a user explicitly insists, but this is generally not recommended.
Practical example and limitations
A typical call is asking the Skill Installer to install a specific experimental skill, such as a planning skill from the .experimental folder, or alternatively providing a GitHub directory URL of a third-party repository directly to install a skill from it. The limitations are that the installer itself performs no content or security review of the skill being installed, only handling the transfer process, and that it is built exclusively for Codex's directory structure. It therefore cannot be used directly for Claude Code, since both systems follow a similar underlying concept but use different storage locations and configuration formats for skills.
- Provider
- OpenAI
- License
- Apache-2.0
- Last reviewed
- 09.09.2026
Repository and documentation
Categories
Compatible with
Related guides
Guides and background related to this entry.