Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cowork-style cleanup of a messy folder or shared drive -- classifies every file, proposes a target structure, renames to a consistent convention, deduplicates, and writes an index. Use on Downloads, Desktop, client folders, or team shared drives.
.claude/skills/onewave-ai-cowork-folder-organizer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 624% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -62% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -20% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -6% | 0% |
Turn a chaotic folder into an organized, navigable workspace the way Claude Cowork works through a directory: inventory everything first, propose before moving, then execute with a full undo trail. Never destroy information -- every move is logged and reversible.
Take a directory path. If none is provided, ask for one. Confirm scope before touching anything: subdirectories included or not, and whether any paths are off-limits.
~$ locks, empty files).final, final2, v3, (1)). Identify the canonical copy (newest complete version) and mark the rest.YYYY-MM-DD-descriptive-name.ext for dated documents, client-project-doctype for client work), the duplicate resolution list, and the junk list. Wait for approval before moving anything._review-before-deleting/ -- never delete outright. Log every operation as old-path -> new-path in _organizer-log.md.INDEX.md at the root: the new tree, what lives where, and a table of the 20 most recently active files so the owner can re-orient instantly._review-before-deleting/ and let the human pull the trigger.When run as a recurring Cowork scheduled task (e.g. weekly on Downloads), skip the approval step only for previously approved rules: apply the established convention to new files, quarantine new junk, and post a summary of what moved. Anything that does not match an existing rule goes to _needs-decision/ and is listed in the summary.
_organizer-log.md| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 3,154 | 12,619 | +300% | 1 | 1 | 0% | 400 | 2,896 | +624% | 0 | 0 | — |
case-02 | fail→pass | 40,195 | 7,785 | -81% | 1 | 1 | 0% | 5,197 | 1,985 | -62% | 0 | 0 | — |
case-03 | fail→fail | 24,922 | 9,610 | -61% | 1 | 1 | 0% | 5,027 | 2,276 | -55% | 0 | 0 | — |
case-04 | fail→pass | 13,364 | 7,972 | -40% | 1 | 1 | 0% | 2,651 | 2,133 | -20% | 0 | 0 | — |
case-05 | fail→fail | 8,259 | 6,943 | -16% | 1 | 1 | 0% | 1,508 | 2,077 | +38% | 0 | 0 | — |
case-06 | fail→pass | 10,197 | 6,730 | -34% | 1 | 1 | 0% | 1,618 | 1,812 | +12% | 0 | 0 | — |
case-07 | fail→fail | 8,795 | 8,327 | -5% | 1 | 1 | 0% | 1,625 | 2,230 | +37% | 0 | 0 | — |
case-08 | fail→pass | 8,839 | 3,614 | -59% | 1 | 1 | 0% | 1,472 | 1,377 | -6% | 0 | 0 | — |
case-09 | pass→pass | 5,985 | 16,121 | +169% | 1 | 1 | 0% | 958 | 3,767 | +293% | 0 | 0 | — |
case-10 | pass→pass | 9,813 | 9,485 | -3% | 1 | 1 | 0% | 1,740 | 2,304 | +32% | 0 | 0 | — |
case-11 | fail→pass | 8,192 | 7,633 | -7% | 1 | 1 | 0% | 1,348 | 2,115 | +57% | 0 | 0 | — |
case-12 | fail→pass | 9,013 | 7,538 | -16% | 1 | 1 | 0% | 1,588 | 1,957 | +23% | 0 | 0 | — |
case-13 | pass→pass | 12,415 | 7,680 | -38% | 1 | 1 | 0% | 2,052 | 2,108 | +3% | 0 | 0 | — |
case-14 | pass→pass | 12,694 | 9,788 | -23% | 1 | 1 | 0% | 2,158 | 2,468 | +14% | 0 | 0 | — |
case-15 | pass→pass | 11,778 | 9,598 | -19% | 1 | 1 | 0% | 1,752 | 2,180 | +24% | 0 | 0 | — |
case-16 | pass→pass | 14,087 | 8,784 | -38% | 1 | 1 | 0% | 2,206 | 2,094 | -5% | 0 | 0 | — |
case-17 | pass→pass | 12,132 | 3,828 | -68% | 1 | 1 | 0% | 1,766 | 1,378 | -22% | 0 | 0 | — |
case-18 | fail→fail | 13,444 | 3,436 | -74% | 1 | 1 | 0% | 2,165 | 1,269 | -41% | 0 | 0 | — |
case-19 | pass→pass | 9,354 | 9,370 | +0% | 1 | 1 | 0% | 1,783 | 2,617 | +47% | 0 | 0 | — |
case-20 | pass→pass | 17,656 | 15,791 | -11% | 1 | 1 | 0% | 3,402 | 3,974 | +17% | 0 | 0 | — |
case-21 | pass→pass | 12,651 | 10,995 | -13% | 1 | 1 | 0% | 2,326 | 2,878 | +24% | 0 | 0 | — |
case-22 | pass→pass | 11,333 | 4,567 | -60% | 1 | 1 | 0% | 2,028 | 1,589 | -22% | 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 +32 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.