Skip to content
cccskills
FreePublished on GitHub

sn-update

Update installed SenseNova Skills in OpenClaw or hermes-agent, either as a complete bundle or as selected skills. Compare versions before replacing files, back up existing installations, and report which skills changed or were already current.

OriginalShow the original description

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.

See how to install

Good for

  • Updating the complete installed sn-* bundle
  • Updating only selected skills
  • Reinstalling skills even when already current
  • Checking updates while keeping recent backups

Files included (1)

  • SKILL.md5.5 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

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
existsabsentopenclaw
absentexistshermes
existsexistsask the user — never silently dual-write
absentabsentno 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 selected skills/<name> paths before copying them. --filter=blob:none alone 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 whole sn-* bundle, expect most/all skill blobs to be downloaded.
  • URL changed: if cache's origin differs 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:

git -C <cache> log -1 --format=%H -- skills/<skill-name>
  • A — .sn-version marker: one-line file inside the installed skill holding the SHA from its last install.
  • B — .sn-release marker (fallback): one-line file holding the upstream tag name. Compare against git describe --tags --abbrev=0.
  • C — optional version: field in SKILL.md frontmatter: parse from YAML on both sides, but only for forks or skills that explicitly add this field. If either side lacks it, C does not apply.
  • Nothing usable → treat as stale and install.

Always write .sn-version on install so future runs can use A.


Install with backup

For each skill flagged "install":

  1. Move (not copy) any existing <agent-skills>/<skill-name>/ into a single timestamped backup bucket shared by all skills in this run: ~/.<agent>/skills_backup/<UTC-timestamp>/<skill-name>/ (e.g. 2026-04-30T15-29-07Z).
  2. Copy <cache>/skills/<skill-name>/ → <agent-skills>/<skill-name>/. Never symlink (ln -s) from the cache. The cache lives under ~/.cache/ with permissions the agent runtime may not be able to traverse, and some runtimes refuse to load skills resolved through symlinks. Always do a real recursive copy so the installed tree is self-contained and owned by the agent skills dir.
  3. Write .sn-version with the upstream subtree SHA inside the new copy.

If the bucket ends up empty (all targets were fresh installs), remove it.

The backup tree is a sibling of skills/, never a .bak folder inside it — most agent runtimes scan the whole skills/ directory and would pick up stale duplicates.


Enforce backup retention

After every run, prune the per-agent backup root to at most 3 buckets. Timestamps sort lexicographically; keep the newest 3, delete the rest. Run this even when the current run produced no backup of its own.


Report to the user

Group by status, keep it short:

Updated (3): sn-ppt-standard, sn-image-base, sn-deep-research
Already up-to-date (5): sn-ppt-creative, sn-ppt-doctor, ...
Backup: ~/.openclaw/skills_backup/2026-04-30T15-29-07Z/
  • Omit Backup: when nothing was backed up.
  • Show SHA pairs (abc1234 → def5678) only if the user asks for detail.
  • Errors get their own line — never bury them in a success summary.

Edge cases

  • Asks to delete sn- skills* — not this skill's job. Decline; point at ~/.<agent>/skills_backup/ if they want to roll back.
  • User is in the dev repo and asks to "update sn skills" — they mean push to their agent install. Proceed normally; this skill only touches the cache and the agent install dirs, never the dev checkout.
  • sn-update updating itself — fine; the new copy takes effect on the next invocation.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Compare counts and shares for two categories in Excel data. The skill cleans the selected columns, calculates differences and percentages, and produces a summary spreadsheet plus bar and pie charts.

  • Comparing counts for two categories
  • Visualizing category shares
  • Cleaning merged-cell data before counting
OpenSenseNova/SenseNova-Skills5.8KUpdated Oct 9, 2026

Analyze Excel data using custom categories, count distributions, and compare groups with charts. Score text using its length, technical terms, numbers, and selected complex concepts, then visualize difficulty levels and the relationship between text length and scores.

  • Summarize Excel records using custom categories
  • Compare category distributions across groups
  • Score and grade text using adjustable rules
OpenSenseNova/SenseNova-Skills5.8KUpdated Oct 9, 2026

Count categories in a chosen data column after removing missing values and placeholder labels. Calculate each category’s share and create high-resolution charts combining counts, percentages, pie charts, and horizontal bars for distribution reports.

  • Compare record counts across categories
  • Show category shares with pie and bar charts
  • Exclude placeholder labels before counting
OpenSenseNova/SenseNova-Skills5.8KUpdated Oct 9, 2026

Clean category and numeric fields in structured data, compare groups with counts and cross-tabulations, and produce charts, Excel results, and a Markdown report. Export visuals as high-resolution PNG and SVG files for use in reports.

  • Compare category distributions across groups
  • Clean category labels and fill merged-cell gaps
  • Export analysis results to Excel
OpenSenseNova/SenseNova-Skills5.8KUpdated Oct 9, 2026

Filter Excel data using candidate column names, RGB color values, text prefixes, and regular expressions, which match text patterns. Calculate totals and averages, then export results to Excel with highlighted rows and a download link.

  • Filtering rows by RGB values or identifier prefixes
  • Converting text to numbers and calculating totals or averages
  • Extracting matching commands with their identifiers and descriptions
OpenSenseNova/SenseNova-Skills5.8KUpdated Oct 9, 2026

Filter rows from Excel or previously converted Parquet files, a format designed for efficient data storage. Summarize matching records by group with counts, percentages, and totals, then export the summary to Excel.

  • Count records containing a specified risk level by work category
  • Calculate group shares among matching records
  • Summarize large datasets already converted to Parquet
OpenSenseNova/SenseNova-Skills5.8KUpdated Oct 9, 2026

See all skills by OpenSenseNova

Report a problem with this skill