update-skills
Re-apply your installed skills to pull their latest code from upstream.
Profile →npx skills add nanocoai/nanoclaw --skill update-skills --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# About Each skill is a self-installing additive unit: its folder under `.claude/skills/<name>/` carries its own apply steps (`SKILL.md`), and channel/provider skills fetch their code files from a long-lived upstream branch (`channels`, `providers`) with `git fetch origin <branch>` + `git show origin/<branch>:path > path`. Every apply is idempotent and safe to re-run. Updating a skill means **re-running its own apply**. The apply re-fetches the latest files from upstream and overwrites the copied-in code, so newer versions land additively. Run `/update-skills` in Claude Code. ## How it works **Preflight**: checks for a clean working tree and the upstream remote. **Detection**: reads the channel and provider barrels to list which skills have copied code into your tree, and lists the operational/utility skills present under `.claude/skills/`. **Selection**: presents the installed skills and lets you pick which to re-apply. **Re-apply**: invokes each selected skill's own apply (e.g. `/add-slack`), which fetches its latest files. Then validates with build + test. --- # Goal Help users pull the latest skill code from upstream by re-applying their installed skills, without losing local c
- How it works
What does the update-skills skill do?
Re-apply your installed skills to pull their latest code from upstream.
How do I install it?
Run `npx skills add nanocoai/nanoclaw --skill update-skills --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From nanocoai/nanoclaw, a repository with 30,426 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.