Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Automatically update OpenClaw and selected skills once daily. Runs via cron, checks for updates, applies them, and messages the user with a summary of what changed.
.claude/skills/jdrhyne-auto-updater/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -34% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -26% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -54% | 0% |
Keep OpenClaw and skills up to date automatically with daily update checks.
This skill sets up a daily cron job that:
clawhub update --all)Ask OpenClaw to set up the auto-updater:
Set up daily auto-updates for OpenClaw and installed skills.Or manually add the cron job:
bashopenclaw cron add \ --name "Daily Auto-Update" \ --cron "0 4 * * *" \ --tz "America/Los_Angeles" \ --session isolated \ --wake now \ --deliver \ --message "Run daily auto-updates: check for OpenClaw updates and update installed skills. Report what changed."
For npm installs:
bashnpm update -g openclaw@latest
After update, run health checks:
bashopenclaw --profile default doctor --fix openclaw gateway restart
bashclawhub update --all
This checks installed ClawHub skills and updates to latest versions.
Run a manual skill update:
bashclawhub update --all --no-input --force
List installed ClawHub skills:
bashclawhub list
Check OpenClaw version:
bashopenclaw --version
openclaw cron list)openclaw gateway status)openclaw --profile default doctor --fixbashopenclaw cron remove "Daily Auto-Update"
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 16,071 | 5,886 | -63% | 1 | 1 | 0% | 2,874 | 1,466 | -49% | 0 | 0 | — |
case-02 | fail→pass | 10,540 | 7,549 | -28% | 1 | 1 | 0% | 1,204 | 1,387 | +15% | 0 | 0 | — |
case-03 | fail→pass | 7,498 | 2,206 | -71% | 1 | 1 | 0% | 1,193 | 785 | -34% | 0 | 0 | — |
case-04 | fail→pass | 5,166 | 2,497 | -52% | 1 | 1 | 0% | 737 | 897 | +22% | 0 | 0 | — |
case-05 | fail→pass | 6,464 | 1,881 | -71% | 1 | 1 | 0% | 1,057 | 779 | -26% | 0 | 0 | — |
case-06 | fail→pass | 9,348 | 1,514 | -84% | 1 | 1 | 0% | 1,502 | 698 | -54% | 0 | 0 | — |
case-07 | pass→pass | 4,535 | 2,371 | -48% | 1 | 1 | 0% | 596 | 806 | +35% | 0 | 0 | — |
case-08 | pass→pass | 5,168 | 1,721 | -67% | 1 | 1 | 0% | 775 | 731 | -6% | 0 | 0 | — |
case-09 | pass→pass | 4,629 | 1,490 | -68% | 1 | 1 | 0% | 655 | 649 | -1% | 0 | 0 | — |
case-10 | fail→pass | 6,425 | 2,159 | -66% | 1 | 1 | 0% | 1,075 | 805 | -25% | 0 | 0 | — |
case-11 | fail→pass | 9,493 | 1,544 | -84% | 1 | 1 | 0% | 1,392 | 695 | -50% | 0 | 0 | — |
case-12 | fail→pass | 9,290 | 1,814 | -80% | 1 | 1 | 0% | 1,337 | 737 | -45% | 0 | 0 | — |
case-13 | fail→pass | 8,192 | 2,149 | -74% | 1 | 1 | 0% | 1,240 | 815 | -34% | 0 | 0 | — |
case-18 | pass→pass | 8,472 | 2,523 | -70% | 1 | 1 | 0% | 1,339 | 817 | -39% | 0 | 0 | — |
case-14 | fail→pass | 21,352 | 2,386 | -89% | 1 | 1 | 0% | 3,143 | 852 | -73% | 0 | 0 | — |
case-15 | fail→pass | 17,403 | 1,949 | -89% | 1 | 1 | 0% | 2,555 | 757 | -70% | 0 | 0 | — |
case-16 | fail→pass | 16,817 | 2,134 | -87% | 1 | 1 | 0% | 2,533 | 845 | -67% | 0 | 0 | — |
case-17 | fail→pass | 14,092 | 7,476 | -47% | 1 | 1 | 0% | 2,131 | 1,622 | -24% | 0 | 0 | — |
case-19 | pass→pass | 5,036 | 4,341 | -14% | 1 | 1 | 0% | 761 | 1,157 | +52% | 0 | 0 | — |
case-20 | pass→pass | 10,163 | 6,026 | -41% | 1 | 1 | 0% | 1,787 | 1,537 | -14% | 0 | 0 | — |
case-21 | pass→pass | 9,605 | 5,036 | -48% | 1 | 1 | 0% | 1,672 | 1,339 | -20% | 0 | 0 | — |
case-22 | pass→pass | 2,754 | 2,510 | -9% | 1 | 1 | 0% | 417 | 896 | +115% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +59 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.