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) page soon | 43,034 | 2.0s | 0 | works |
| hallmark page soon | 15,794 | 2.5s | 0 | works |
| GSD Core (get-shit-done) | 7,061 | 1.8s | 0 | works |
| remotion skills (official, 10-skill pack) page soon | 3,500 | 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) page soon | — | 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.
What's next
Pages for the rest of the tested batch — the Obsidian five-pack, the design skills (hallmark vs kill-ai-slop, tested head-to-head), Remotion's official pack, and how-to guides for activation and skill authoring — are being written from the same test logs and land over the next days. Watch the changelog.