Sn Update
Update SenseNova Skills (the sn-* bundle) inside an OpenClaw or hermes-agent install.
Install
npx skills add OpenSenseNova/SenseNova-Skills --skill sn-update -g -a claude-code -y- Repository
- OpenSenseNova/SenseNova-Skills6k
- Category
- AI and agents
- Updated
- 6d ago
- License
- MIT
- Context cost
- Lightabout 1,191 tokens
- Runs scripts
- No, instructions only
What it does
Update SenseNova Skills (the sn-* bundle) inside an OpenClaw or hermes-agent install. ALWAYS use this skill when the user says any of: "update SenseNova skills", "update SN skills", "更新 sensenova skills", "更新 sn skills", "刷新 sn-*", "升级 sn-* skills", or names a specific sn-* skill to update (e.g. "更新 sn-ppt-standard", "refresh sn-image-base"). Default scope is the whole sn-* bundle; if the user names specific skills, update ONLY those.
sn-update
Refresh installed sn-* skills from upstream
SenseNova-Skills.
Decide the scope
- No list given → every
sn-*skill upstream. - Specific skills named → only those. Don't expand.
- A named skill missing upstream → surface as error and stop.
- User said "force / 强制" → re-install even when up-to-date.
Decide the target agent
Check which directories exist:
~/.openclaw/skills/ | ~/.hermes/skills/ | Target |
|---|---|---|
| exists | absent | openclaw |
| absent | exists | hermes |
| exists | exists | ask the user, never silently dual-write |
| absent | absent | no install found, stop |
Sync the upstream repo
Persistent cache at ~/.cache/sn-update/repo/. Default URL:
https://github.com/OpenSenseNova/SenseNova-Skills.git. User may override
with a fork URL.
- First run: if you want to actually limit blob download, use partial
clone with
--filter=blob:none --no-checkout, then sparse-checkout only the selectedskills/<name>paths before copying them.--filter=blob:nonealone does not keep the cache small if the full worktree is checked out; that checkout will still download most or all needed blobs. It still preserves history metadata for SHA queries. - Subsequent runs: fetch + hard-reset to the upstream default branch, and
re-apply sparse-checkout for only the requested
skills/<name>paths before copying. If updating the wholesn-*bundle, expect most/all skill blobs to be downloaded. - URL changed: if cache's
origindiffers from the requested URL, delete and re-clone.
Compare versions per skill (A → B → C)
For each skill, pick the highest-precedence signal present on both sides (installed + upstream); equal → skip, differ → install.
Upstream "version" is the per-subtree commit SHA, using repo HEAD would mark unrelated skills as stale every time:
