Claude Code skills, actually tested
Directories list skills. We install them. Every skill on this site was set up in a clean environment, timed with a stopwatch, run against a minimal real task, and written up with whatever broke along the way — including the things that never got fixed.
8 skill packages tested so far, 3 real failures hit and documented, last test 2026-07-23. Numbers in every table are generated from the raw test logs, never typed by hand.
| Skill | Stars | Install time | Failures | Verdict |
|---|---|---|---|---|
| obsidian-skills (5-skill pack) | 43,034 | 2.0s | 0 | works |
| hallmark | 15,794 | 2.5s | 0 | works |
| GSD Core (get-shit-done) | 7,061 | 1.8s | 0 | works |
| remotion skills (official, 10-skill pack) | 3,677 | 2.5s | 0 | works |
| kill-ai-slop | 708 | 2.8s | 0 | works |
| video-shotcraft | 564 | 11.9s | 3 | works |
| codedrobe-theme (CodeDrobe/skills) | 229 | 2.5s | 0 | works |
| visual-skills (video + image) | 103 | 2.5s | 0 | works |
Why this exists
Claude Code skills exploded in 2026, and so did the listings of them. What none of the lists
tell you: does npx skills add actually work for this repo? How long does a 164MB
skill take to land? Does it run on Linux, or does it quietly need a Mac with a desktop app open?
Which famous repo is actually archived while every directory still links to it?
(One of the biggest ones, it turns out.)
Those answers only come from running the install. So that is the whole editorial policy here: no page ships until we have run the thing. The test record at the top of each page — repo, commit, environment, timings, failures — is generated straight from our raw test logs. If a number is on this site, a script computed it from a log; nobody typed it.
How to install Claude Code skills (the short version)
The ecosystem has largely converged on one installer, the skills CLI. For nearly every package we have tested, this is the whole story:
npx skills add <owner>/<repo> -a claude-code -yFirst run pays a few seconds of CLI bootstrap; after that installs are typically two to three
seconds. Skills land in .claude/skills/ in your project (add -g for
user-level). The interesting failures happen after install — at use time, when a skill
turns out to need a browser binary, a desktop app, or a rendering pipeline. That is exactly what
each test page documents.
Guides from the same logs
The test sessions also produced four guides: eight best practices we learned the empirical way, how to make skills actually activate, how to build a skill (anatomy of 8 real ones), and a short answer to "what are Claude skills". Every claim in them links back to a test record.
What's next
More community skills enter the test queue weekly, and everything already tested goes on a 30-day retest calendar — repos move, break, and get archived (ask GSD). Watch the changelog.