mirror of
https://github.com/runkids/skillshare.git
synced 2026-11-20 20:34:19 +00:00
The intro and team pages still described skillshare as a sync tool for one person, and some security wording promised more than the code does: "symlink isolation" implied a sandbox, and audit read as runtime protection. Teams evaluating skillshare need to know what is actually shared, pinned and enforced. - Intro and READMEs open with the positioning and a team example: one checklist in .skillshare/, shared by teammates on different tools. - Team onboarding follows the real project flow: install -p (honoring skills.lock.json), audit with a threshold, then sync. - The hub guide walks through a private hub over SSH: an index at the repo root or a //path, a pinned CLI version in CI, and pinned actions. - The security pages separate what audit, .skillignore, the lockfile and each AI tool's own permissions control. Blocking follows finding severity, not the risk score. - The SARIF CI example now fails the job on findings. With audit-output set, setup-skillshare only records the exit code. All pages are mirrored to ja, ko, zh-Hans and zh-Hant.