Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Moves track markdown files to the correct album location. Use when the user has track files in Downloads or other locations that need to be placed in an album.
.claude/skills/bitwize-music-studio-import-track/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 45% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 22% | 0% |
Input: $ARGUMENTS
Import a track markdown file (.md) to the correct album location based on config.
You move track markdown files to the correct location in the user's content directory.
Expected format: <file-path> <album-name> [track-number]
Examples:
~/Downloads/track.md sample-album 03~/Downloads/t-day-beach.md sample-album 03~/Downloads/03-t-day-beach.md sample-album (number already in filename)If arguments are missing, ask:
Usage: /import-track <file-path> <album-name> [track-number]
Example: /import-track ~/Downloads/track.md sample-album 03find_album(album_name) — fuzzy match by name, slug, or partial. Returns album metadata including genre.resolve_path("tracks", album_slug) — returns the full tracks directory pathIf album not found, MCP returns available albums:
Error: Album "{album-name}" not found.
Available albums:
[list from MCP response]
Create album first with: /new-album {album-name} <genre>The target path is ALWAYS:
{content_root}/artists/{artist}/albums/{genre}/{album}/tracks/{XX}-{track-name}.mdExample with:
content_root: ~/bitwize-musicartist: bitwizegenre: electronic (found from album location)album: sample-albumtrack-number: 03track-name: t-day-beachResult:
~/bitwize-music/artists/bitwize/albums/electronic/sample-album/tracks/03-t-day-beach.mdTrack numbering:
03)03-name.md), preserve itbashmv "{source_file}" "{target_path}"
Report:
Moved: {source_file}
To: {target_path}Source file doesn't exist:
Error: File not found: {source_file}Config file missing:
Error: Config not found at ~/.bitwize-music/config.yaml
Run /configure to set up.Album not found:
Error: Album "{album-name}" not found.
Create it first with: /new-album {album-name} <genre>Track already exists:
Warning: Track already exists at destination.
Overwrite? (The original was not moved)/import-track ~/Downloads/t-day-beach.md sample-album 03Config has:
yamlpaths: content_root: ~/bitwize-music artist: name: bitwize
Album found at: ~/bitwize-music/artists/bitwize/albums/electronic/sample-album/
Result:
Moved: ~/Downloads/t-day-beach.md
To: ~/bitwize-music/artists/bitwize/albums/electronic/sample-album/tracks/03-t-day-beach.mdWrong:
bashcat ~/.bitwize-music/config.yaml find . -name "README.md" -path "*albums/$album_name*"
Right:
# Use MCP to find album and resolve path
find_album(album_name) → returns album metadata with genre
resolve_path("tracks", album_slug) → returns full tracks directory pathWhy it matters: MCP handles config reading, fuzzy matching, and path resolution in single calls.
Wrong destination:
{album_path}/01-track.md
# Example: ~/bitwize-music/artists/bitwize/albums/electronic/sample-album/01-track.mdCorrect destination:
{album_path}/tracks/01-track.md
# Example: ~/bitwize-music/artists/bitwize/albums/electronic/sample-album/tracks/01-track.mdWhy it matters: Tracks always go in the tracks/ subdirectory within the album folder.
Wrong:
bash# Not validating track number format mv track.md {album_path}/tracks/$track_num-track.md # Could result in: 3-track.md instead of 03-track.md
Right:
bash# Ensure zero-padding track_num=$(printf "%02d" $track_num) mv track.md {album_path}/tracks/$track_num-track.md # Results in: 03-track.md
Why it matters: Track numbers must be zero-padded (01, 02, 03...) for proper sorting.
Wrong:
bash# Guessing album is in electronic genre mv track.md ~/music-projects/artists/bitwize/albums/electronic/sample-album/tracks/
Right:
# Use MCP to find the album (handles genre resolution)
find_album(album_name) → returns album metadata including genre and pathWhy it matters: Albums are organized by genre. find_album resolves the genre automatically.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 13,500 | 4,750 | -65% | 1 | 1 | 0% | 1,087 | 1,713 | +58% | 0 | 0 | — |
case-02 | fail→fail | 8,675 | 6,158 | -29% | 1 | 1 | 0% | 1,439 | 1,721 | +20% | 0 | 0 | — |
case-03 | fail→fail | 14,510 | 5,774 | -60% | 1 | 1 | 0% | 2,490 | 1,786 | -28% | 0 | 0 | — |
case-04 | fail→pass | 8,808 | 3,712 | -58% | 1 | 1 | 0% | 1,435 | 2,081 | +45% | 0 | 0 | — |
case-05 | fail→pass | 9,584 | 2,490 | -74% | 1 | 1 | 0% | 1,644 | 1,764 | +7% | 0 | 0 | — |
case-06 | pass→pass | 8,364 | 4,603 | -45% | 1 | 1 | 0% | 1,524 | 2,182 | +43% | 0 | 0 | — |
case-07 | fail→fail | 6,903 | 5,829 | -16% | 1 | 1 | 0% | 1,155 | 1,759 | +52% | 0 | 0 | — |
case-08 | fail→pass | 9,704 | 2,398 | -75% | 1 | 1 | 0% | 1,644 | 1,842 | +12% | 0 | 0 | — |
case-09 | pass→pass | 7,337 | 2,512 | -66% | 1 | 1 | 0% | 1,310 | 1,837 | +40% | 0 | 0 | — |
case-10 | fail→pass | 8,273 | 1,788 | -78% | 1 | 1 | 0% | 1,378 | 1,676 | +22% | 0 | 0 | — |
case-11 | pass→pass | 5,171 | 1,621 | -69% | 1 | 1 | 0% | 870 | 1,672 | +92% | 0 | 0 | — |
case-12 | fail→fail | 8,886 | 2,450 | -72% | 1 | 1 | 0% | 1,569 | 1,851 | +18% | 0 | 0 | — |
case-13 | pass→pass | 7,733 | 9,160 | +18% | 1 | 1 | 0% | 1,377 | 2,539 | +84% | 0 | 0 | — |
case-14 | pass→pass | 5,328 | 2,257 | -58% | 1 | 1 | 0% | 1,107 | 1,834 | +66% | 0 | 0 | — |
case-15 | fail→pass | 10,695 | 4,125 | -61% | 1 | 1 | 0% | 1,725 | 2,099 | +22% | 0 | 0 | — |
case-16 | pass→pass | 8,959 | 3,532 | -61% | 1 | 1 | 0% | 1,644 | 2,074 | +26% | 0 | 0 | — |
case-17 | fail→pass | 8,337 | 3,017 | -64% | 1 | 1 | 0% | 1,663 | 2,101 | +26% | 0 | 0 | — |
case-18 | pass→fail | 4,852 | 2,528 | -48% | 1 | 1 | 0% | 780 | 1,900 | +144% | 0 | 0 | — |
case-19 | pass→pass | 8,648 | 2,997 | -65% | 1 | 1 | 0% | 1,524 | 1,964 | +29% | 0 | 0 | — |
case-20 | fail→pass | 7,689 | 3,415 | -56% | 1 | 1 | 0% | 1,537 | 2,005 | +30% | 0 | 0 | — |
case-21 | fail→pass | 10,070 | 2,833 | -72% | 1 | 1 | 0% | 1,863 | 1,883 | +1% | 0 | 0 | — |
case-22 | fail→pass | 7,192 | 4,445 | -38% | 1 | 1 | 0% | 1,294 | 2,280 | +76% | 0 | 0 | — |
case-23 | pass→pass | 7,657 | 6,763 | -12% | 1 | 1 | 0% | 1,454 | 2,598 | +79% | 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. 23 cases were attempted, and 19 counted toward the lift figure. The other 4 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +35 percentage points is the difference between those two pass rates over the 19 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
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.