Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nwave-ai/nw-continue
Detects current wave progress for a feature and resumes at the next step. Scans docs/feature/ for artifacts.
Passed 12 of 18 test cases with the skill, and 7 of 18 without it.
and 5 more in the full report
7 fixed8 passed either way7 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
When analyzing progress for a feature currently in implementation state, we need to determine which micro-step to resume. What specific log file inside `docs/feature/{id}/deliver/` should be read to count COMMIT and PASS entries?
| Checked | Without skill | With skill |
|---|---|---|
| Reads execution-log.json inside the deliver subdirectory | Missed | Passed |
The instructions your model reads when the skill loads.
Wave: CROSS_WAVE (entry point) | Agent: Main Instance (self — wizard) | Command: /nw-continue
Scans docs/feature/ for active projects, detects wave artifacts, displays progress summary, launches next wave command. Eliminates manual artifact inspection when returning after hours/days.
You (main Claude instance) run this wizard directly. No subagent delegation.
If project ID provided as argument, use it directly.
Otherwise scan docs/feature/ for project directories:
ls -d docs/feature/*/
No directories found: Display "No active projects found under docs/feature/." Suggest /nw-new. Stop.
If multiple directories exist, list by most recent file modification:
find docs/feature/{feature-id}/ -type f -printf '%T@ %p\n' | sort -rn | head -1
Present via AskUserQuestion: project name|last modified date|most recent first. Ask user to select.
Check each wave's artifacts using Wave Detection Rules in ~/.claude/nWave/skills/common/wizard-shared-rules.md.
Check before showing progress:
test cases passed, vs 7 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.