external-skill-import

Review third-party agent skill archives for safety, licensing, and compatibility before installation.

Updated Jun 15, 2026
One-click install
npx skills add https://github.com/ravenslight2010/Production-run-calculator --skill external-skill-import-ravenslight2010
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: external-skill-import
Source: https://github.com/ravenslight2010/Production-run-calculator/tree/main/.agents/skills/external-skill-import
Command: npx skills add https://github.com/ravenslight2010/Production-run-calculator --skill external-skill-import-ravenslight2010

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Installing third-party agent skills from uploaded archives or GitHub repositories carries risks: malicious scripts, missing licenses, credential leaks, duplicate names, and provider-specific behavior that cannot run locally. This Skill provides a structured review workflow that treats external content as untrusted data and produces an accept, adapt, defer, or reject recommendation before any files are written. ## Core Features & Use Cases - Safe archive inventory: Lists archive entries, detects path traversal, symlinks, and suspicious compression before any extraction, and reconciles manifest entries against actual SKILL.md implementations. - Provenance and license gating: Records source identity, hashes, and license evidence, blocking installation when licensing is absent or unclear. - Compatibility mapping: Classifies every external dependency as portable, adaptable, or unsupported, and flags provider-specific behavior such as credential discovery or restart instructions. - Use Case: A user uploads a zip bundle of community skills. The Skill inventories the candidates, detects one duplicate of an existing project-owned skill, redacts credential-like fields in a bundled config, and recommends accept for two licensed skills while deferring the rest. ## Quick Start Review the uploaded skill archive and tell me whether each candidate skill is safe to install, without installing anything yet.

Frequently Asked Questions about external-skill-import

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I safely review a third-party agent skill before installing it?

Inventory the archive or repository without extracting or executing anything, verify license and provenance, check for duplicate names against existing skills, and map every dependency to a portable, adaptable, or unsupported classification. Install only after an explicit accept or adapt recommendation is approved.

How to import a skill from a GitHub repository?

Provide the repository URL with an optional subpath and ref, preferably an immutable commit. The review records provenance and licensing, inventories actual SKILL.md candidates, and recommends a disposition before any files are copied into an editable skill root.

What archive threats does the review check for?

The inspection stops on absolute or traversal paths, symlinks and special files, duplicate or case-colliding paths, encrypted members, and suspicious compression ratios. Extraction, when needed, uses a temporary directory with regular files only and is deleted afterward.

What happens when an external skill duplicates an existing one?

A duplicate is treated as a conflict, never an overwrite. The review preserves existing authoritative identities and recommends adapt or defer, proposing only genuinely portable guidance for merging into the project-owned skill.

Can provider-specific skills built for other AI platforms be installed?

Only if every provider-specific behavior has a verified local equivalent. Features like credential discovery, plugin marketplaces, or restart instructions are classified as unsupported and must be removed with stated limitations, or the candidate is deferred or rejected.

What are the limitations of the external skill review workflow?

The review cannot verify provenance when source identity is missing, cannot install skills with absent or incompatible licenses, and never executes bundled scripts to test them. Unverifiable sources stop at a defer recommendation until exact files or URLs are supplied.