Skip to content
Back to skills

Skill Installer

ASecurity

Install Codex skills into the canonical git source tree 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).

  • 9 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added June 1, 2026
ai-agentsrustgit

Security analysis

A100/100

Pro scans all 15 files and shows the line behind each finding

Scanned June 1, 2026

npx -y skills add jscraik/Agent-Skills --skill skill-installer --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Skill Installer?

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

Security grade badge for Skill Installer
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jscraik-skill-installer/badge)](https://www.skillsdirectory.com/skills/jscraik-skill-installer)

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: skill-installer
description: Install Codex skills into the canonical git source tree 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
  skill-type: infrastructure_ops
---

# Skill Installer

Use this skill for listing and installing skills from trusted sources.

## When to use
- List available installable skills.
- Install from curated catalog or explicit GitHub repo/path.
- Verify install destination and runtime visibility.

## Do not use
- Skill creation or refactor design work: route to `[[skill-creator]]`.
- Release-hardening/eval work: route to `[[skill-builder]]`.

## Core Philosophy
- Verify source and destination before writing anything.
- Prefer explicit user intent over inferred replacement behavior.
- Preserve required operational context in `references/` with clear signposts.

## Core workflow
1. Classify request: `list` or `install`.
2. Resolve source and destination with explicit user intent.
3. Run minimal installer helper command.
4. Verify resulting filesystem state.
5. Report exact paths and restart requirement.

## Required output contract
Provide:
- `schema_version`
- `mode`
- `source`
- `destination`
- `validation_evidence`
- `restart_required`

## Progressive disclosure policy
Apply the context-disposition policy: move important still-valid context to references, and intentionally discard stale, duplicated, unsafe, superseded, or low-signal text.

Read when:
- handling source and install safety caveats: [install flows](./references/install-flows.md)
- handling failures: [troubleshooting](./references/troubleshooting.md)
- verifying policy boundaries: [contract](./references/contract.yaml)

## Anti-Patterns to Avoid
- Overwriting existing installs without explicit confirmation.
- Treating untrusted URLs or paths as safe inputs.
- Reporting success without filesystem verification evidence.

## Constraints
- Do not overwrite existing installs without explicit confirmation.
- Treat URLs and paths as untrusted input.
- Redact tokens, credentials, and secret values.

Files in this skill

  • LICENSE.txt141 B
  • SKILL.md2.2 KB
  • agents/openai.yaml217 B
  • assets/skill-installer-small.svg201 B
  • assets/skill-installer.png12.7 KB
  • references/contract.yaml750 B
  • references/evals.yaml2 KB
  • references/install-flows.md3 KB
  • references/task-profile.json1.4 KB
  • references/troubleshooting.md1.4 KB
  • scripts/github_utils.py379 B
  • scripts/install-skill-from-github.py155 B
  • scripts/install-skill-from-github.pyw33.3 KB
  • scripts/list-skills.py155 B
  • scripts/list-skills.pyw4.7 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.