Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use this skill when the user needs Obsidian runtime administration through official desktop CLI commands for plugins, restricted mode, themes, CSS snippets, command catalog/hotkeys, or targeted command execution. Keep this skill separate from note CRUD, Sync/Publish, and devtools diagnostics.
.claude/skills/hashgraph-online-obsidian-cli-runtime-admin/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -45% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 141% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 26% | 0% |
Use this skill for Obsidian runtime administration through official desktop obsidian CLI commands.
Use this skill when:
Do not use this skill when:
obsidian-cli-workflows)Assume these must be true before relying on this skill:
obsidian command is installed and registeredIn Codex Desktop on macOS, prefer this wrapper:
bashscript -q /dev/null /usr/local/bin/zsh -ilc 'unset __CFBundleIdentifier LaunchInstanceID XPC_SERVICE_NAME CODEX_CI CODEX_SANDBOX CODEX_SHELL; export TERM=xterm-256color; obsidian ...'
Escalate the wrapped command only when required by sandbox boundaries.
plugins, plugins:enabled, themes, snippets, commands, hotkeys.command id=<...>, require explicit command ID and do not guess silently.plugins, plugins:enabled, plugin, themes, theme, snippets, snippets:enabled, commands, hotkeys, hotkeyplugins:restrict, commandplugin:install, plugin:uninstall, plugin:enable, plugin:disable, theme:install, theme:uninstall, theme:set, snippet:enable, snippet:disableAlways return:
low, medium, high)direct or escalated)Plugins:
pluginsplugins:enabledplugins:restrictpluginplugin:enableplugin:disableplugin:installplugin:uninstallplugin:reloadThemes/snippets:
themesthemetheme:settheme:installtheme:uninstallsnippetssnippets:enabledsnippet:enablesnippet:disableCommand palette:
commandscommandhotkeyshotkeyreferences/obsidian-cli-runtime-admin-playbook.mdreferences/limitations-and-boundaries.mdreferences/validation.mdreferences/source-links.md| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 9,284 | 18,264 | +97% | 1 | 1 | 0% | 1,764 | 1,364 | -23% | 0 | 0 | — |
case-02 | fail→fail | 16,169 | 11,919 | -26% | 1 | 1 | 0% | 1,541 | 1,454 | -6% | 0 | 0 | — |
case-03 | fail→fail | 15,230 | 13,882 | -9% | 1 | 1 | 0% | 1,743 | 1,444 | -17% | 0 | 0 | — |
case-04 | pass→pass | 8,948 | 9,406 | +5% | 1 | 1 | 0% | 592 | 1,614 | +173% | 0 | 0 | — |
case-05 | pass→pass | 13,904 | 12,804 | -8% | 1 | 1 | 0% | 1,476 | 1,883 | +28% | 0 | 0 | — |
case-06 | pass→pass | 6,884 | 9,557 | +39% | 1 | 1 | 0% | 1,108 | 1,646 | +49% | 0 | 0 | — |
case-07 | fail→pass | 10,877 | 9,034 | -17% | 1 | 1 | 0% | 1,995 | 2,459 | +23% | 0 | 0 | — |
case-08 | fail→pass | 19,302 | 10,472 | -46% | 1 | 1 | 0% | 3,387 | 1,854 | -45% | 0 | 0 | — |
case-09 | fail→fail | 17,124 | 12,967 | -24% | 1 | 1 | 0% | 2,432 | 1,475 | -39% | 0 | 0 | — |
case-10 | fail→pass | 16,045 | 13,333 | -17% | 1 | 1 | 0% | 2,225 | 2,477 | +11% | 0 | 0 | — |
case-11 | fail→fail | 12,612 | 15,149 | +20% | 1 | 1 | 0% | 1,322 | 1,387 | +5% | 0 | 0 | — |
case-12 | pass→fail | 8,228 | 18,861 | +129% | 1 | 1 | 0% | 1,310 | 1,337 | +2% | 0 | 0 | — |
case-13 | fail→fail | 9,094 | 13,375 | +47% | 1 | 1 | 0% | 1,488 | 1,401 | -6% | 0 | 0 | — |
case-14 | fail→pass | 5,666 | 16,290 | +188% | 1 | 1 | 0% | 884 | 2,128 | +141% | 0 | 0 | — |
case-15 | fail→fail | 8,475 | 13,289 | +57% | 1 | 1 | 0% | 1,311 | 1,494 | +14% | 0 | 0 | — |
case-16 | fail→fail | 9,706 | 8,960 | -8% | 1 | 1 | 0% | 1,328 | 1,602 | +21% | 0 | 0 | — |
case-17 | fail→pass | 16,495 | 14,911 | -10% | 1 | 1 | 0% | 1,622 | 2,051 | +26% | 0 | 0 | — |
case-18 | fail→fail | 16,951 | 8,119 | -52% | 1 | 1 | 0% | 1,704 | 1,445 | -15% | 0 | 0 | — |
case-19 | fail→pass | 11,510 | 12,301 | +7% | 1 | 1 | 0% | 1,605 | 2,063 | +29% | 0 | 0 | — |
case-20 | fail→fail | 6,497 | 13,414 | +106% | 1 | 1 | 0% | 362 | 1,428 | +294% | 0 | 0 | — |
case-21 | fail→pass | 10,850 | 15,804 | +46% | 1 | 1 | 0% | 760 | 2,447 | +222% | 0 | 0 | — |
case-22 | fail→pass | 13,217 | 17,610 | +33% | 1 | 1 | 0% | 1,803 | 2,776 | +54% | 0 | 0 | — |
case-23 | pass→pass | 14,457 | 5,368 | -63% | 1 | 1 | 0% | 1,247 | 1,642 | +32% | 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 13 counted toward the lift figure. The other 10 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 +30 percentage points is the difference between those two pass rates over the 13 comparable cases. 4 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.