Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.
.claude/skills/leoyeai-obsidian/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -58% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -37% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -52% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -34% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | -52% | 0% |
Obsidian vault = a normal folder on disk.
Vault structure (typical)
*.md (plain text Markdown; edit with any editor).obsidian/ (workspace + plugin settings; usually don’t touch from scripts)*.canvas (JSON)Obsidian desktop tracks vaults here (source of truth):
~/Library/Application Support/obsidian/obsidian.jsonobsidian-cli resolves vaults from that file; vault name is typically the folder name (path suffix).
Fast “what vault is active / where are the notes?”
obsidian-cli print-default --path-only~/Library/Application Support/obsidian/obsidian.json and use the vault entry with "open": true.Notes
~/Documents, work/personal, etc.). Don’t guess; read config.print-default.Pick a default vault (once):
obsidian-cli set-default "<vault-folder-name>"obsidian-cli print-default / obsidian-cli print-default --path-onlySearch
obsidian-cli search "query" (note names)obsidian-cli search-content "query" (inside notes; shows snippets + lines)Create
obsidian-cli create "Folder/New note" --content "..." --openobsidian://…) working (Obsidian installed)..something/...) via URI; Obsidian may refuse.Move/rename (safe refactor)
obsidian-cli move "old/path/note" "new/path/note"[[wikilinks]] and common Markdown links across the vault (this is the main win vs mv).Delete
obsidian-cli delete "path/note"Prefer direct edits when appropriate: open the .md file and change it; Obsidian will pick it up.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 17,042 | 3,925 | -77% | 1 | 1 | 0% | 2,761 | 1,161 | -58% | 0 | 0 | — |
case-02 | fail→pass | 8,309 | 2,829 | -66% | 1 | 1 | 0% | 1,494 | 941 | -37% | 0 | 0 | — |
case-03 | fail→pass | 11,285 | 2,623 | -77% | 1 | 1 | 0% | 2,014 | 975 | -52% | 0 | 0 | — |
case-04 | pass→pass | 10,525 | 2,368 | -78% | 1 | 1 | 0% | 1,966 | 951 | -52% | 0 | 0 | — |
case-05 | pass→pass | 6,744 | 2,075 | -69% | 1 | 1 | 0% | 1,242 | 832 | -33% | 0 | 0 | — |
case-06 | pass→pass | 6,304 | 2,257 | -64% | 1 | 1 | 0% | 1,103 | 859 | -22% | 0 | 0 | — |
case-07 | fail→pass | 10,795 | 4,324 | -60% | 1 | 1 | 0% | 1,855 | 1,230 | -34% | 0 | 0 | — |
case-08 | pass→pass | 10,583 | 2,724 | -74% | 1 | 1 | 0% | 1,851 | 981 | -47% | 0 | 0 | — |
case-09 | pass→pass | 10,407 | 1,968 | -81% | 1 | 1 | 0% | 1,830 | 830 | -55% | 0 | 0 | — |
case-10 | pass→pass | 7,223 | 4,517 | -37% | 1 | 1 | 0% | 1,189 | 1,239 | +4% | 0 | 0 | — |
case-11 | pass→pass | 8,154 | 1,715 | -79% | 1 | 1 | 0% | 1,339 | 760 | -43% | 0 | 0 | — |
case-12 | pass→pass | 10,680 | 6,399 | -40% | 1 | 1 | 0% | 1,782 | 1,598 | -10% | 0 | 0 | — |
case-13 | pass→pass | 11,548 | 9,170 | -21% | 1 | 1 | 0% | 2,405 | 2,416 | +0% | 0 | 0 | — |
case-14 | pass→pass | 12,199 | 5,801 | -52% | 1 | 1 | 0% | 1,865 | 1,383 | -26% | 0 | 0 | — |
case-15 | pass→pass | 7,701 | 3,372 | -56% | 1 | 1 | 0% | 1,461 | 1,143 | -22% | 0 | 0 | — |
case-16 | pass→pass | 7,691 | 1,809 | -76% | 1 | 1 | 0% | 1,297 | 829 | -36% | 0 | 0 | — |
case-17 | pass→pass | 10,998 | 5,056 | -54% | 1 | 1 | 0% | 1,938 | 1,423 | -27% | 0 | 0 | — |
case-18 | pass→pass | 11,994 | 4,847 | -60% | 1 | 1 | 0% | 2,021 | 1,213 | -40% | 0 | 0 | — |
case-19 | pass→pass | 18,119 | 8,318 | -54% | 1 | 1 | 0% | 3,387 | 2,355 | -30% | 0 | 0 | — |
case-20 | pass→pass | 7,512 | 5,874 | -22% | 1 | 1 | 0% | 1,248 | 1,531 | +23% | 0 | 0 | — |
case-21 | pass→pass | 11,982 | 9,371 | -22% | 1 | 1 | 0% | 2,028 | 2,165 | +7% | 0 | 0 | — |
case-22 | pass→pass | 7,024 | 4,832 | -31% | 1 | 1 | 0% | 1,127 | 1,308 | +16% | 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 +18 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.