Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nicepkg/skill-downloader
Download and install Claude Code skills from various sources. Supports GitHub repositories, compressed archives (.zip, .tar.gz, .skill), and direct URLs.
Passed 20 of 24 test cases with the skill, and 6 of 24 without it.
and 22 more in the full report
14 fixed6 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
While trying to grab a tool from a direct URL, I got a 'Network error'. What are the exact two solutions recommended for this scenario?
| Checked | Without skill | With skill |
|---|---|---|
| Advises the user to retry the operation | Missed | Passed |
| Recommends checking the URL for accuracy rather than debugging local firewall rules | Missed | Passed |
The instructions your model reads when the skill loads.
Download and install Claude Code skills from multiple sources.
| Source Type | Examples |
|---|---|
| GitHub Repository | https://github.com/user/repo, github.com/user/repo |
| Compressed Archive | .zip, .tar.gz, .tgz, .skill (renamed zip) |
| Direct URL | URL pointing to archive or skill folder |
python scripts/download_from_github.py <repo-url> <skill-path> --output <target-dir>
Examples:
# Official Anthropic skills
python scripts/download_from_github.py https://github.com/anthropics/skills skills/docx --output ./.claude/skills/
# Community skills (root level)
python scripts/download_from_github.py https://github.com/gked2121/claude-skills social-repurposer --output ./.claude/skills/
# Nested skill path
python scripts/download_from_github.py https://github.com/MadAppGang/claude-code skills/content-brief --output ./.claude/skills/
python scripts/download_from_archive.py <url-or-path> --output <target-dir>
Examples:
test cases passed, vs 6 / 24 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.