Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nwave-ai/nw-update
Queues a deferred self-update of nwave-ai. Writes a PendingUpdateFlag that the SessionStart hook replays on the next Claude Code launch, so the current session is not interrupted. Falls back to manual instructions when the package manager cannot be detected.
Passed 14 of 18 test cases with the skill, and 3 of 18 without it.
and 15 more in the full report
13 fixed4 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
If the user runs the update command with `v1.9.0-rc1`, what target version string should be written to the pending update service?
| Checked | Without skill | With skill |
|---|---|---|
| The target version passed to PendingUpdateService.request_update is 1.9.0-rc1 without a leading v character. | Missed | Passed |
The instructions your model reads when the skill loads.
Wave: CROSS_WAVE | Agent: Main Instance (self) | Command: /nw-update
/nw-update records a PendingUpdateFlag on disk. The actual upgrade is performed
by the SessionStart hook on the next Claude Code launch, so the user can keep
working in the current session and apply the new version whenever they restart.
You (the main Claude instance) run this command directly — no subagent delegation. Do NOT attempt to upgrade nwave-ai in the current session.
$ARGUMENTS), treat it as the target version
after stripping a leading v.update_check.latest_available):python3 -c "
import sys, os
sys.path.insert(0, os.path.expanduser('~/.claude/lib/python'))
from des.adapters.driven.config.des_config import DESConfig
print(DESConfig().update_check_latest_available or '')"
Invoke the detector and resolve the PM binary absolute path in a single Bash call.
This runs under whatever python3 the shell provides, which is NOT the
interpreter nwave-ai was installed under — so sys.executable is the wrong
anchor for detection. Use resolve_nwave_pm, which prefers the value the
test cases passed, vs 3 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.