Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use this skill when the user needs official desktop Obsidian CLI Sync workflows and, when detected as available, Publish workflows. This skill is for remote-side-effect operations and must use explicit intent, capability probing, and conservative safety checks.
.claude/skills/hashgraph-online-obsidian-cli-sync-and-publish/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 57% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 19% | 0% |
Use this skill for Obsidian Sync operations and capability-gated Obsidian Publish operations 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.
publish:* command. Use a read-only check like obsidian help publish:status.No commands matching, treat Publish as unsupported in this environment and refuse publish actions plainly.sync:status; and publish:status only when publish support is confirmed).sync:restore), require explicit version=<n> plus explicit file= or path= unless the user clearly specifies active-file restore.sync:status, sync:history, sync:read, sync:deleted; and publish:site, publish:list, publish:status only when supportedsync, sync:open; and publish:open only when supportedsync:restore; and publish:add, publish:remove only when supportedAlways return:
low, medium, high)direct or escalated)Sync:
syncsync:statussync:historysync:readsync:restoresync:opensync:deletedPublish:
publish:site (only when supported)publish:list (only when supported)publish:status (only when supported)publish:add (only when supported)publish:remove (only when supported)publish:open (only when supported)references/obsidian-cli-sync-publish-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→pass | 24,621 | 13,575 | -45% | 1 | 1 | 0% | 2,770 | 2,900 | +5% | 0 | 0 | — |
case-02 | fail→fail | 16,558 | 20,198 | +22% | 1 | 1 | 0% | 1,668 | 1,677 | +1% | 0 | 0 | — |
case-03 | fail→pass | 18,176 | 12,082 | -34% | 1 | 1 | 0% | 1,817 | 1,913 | +5% | 0 | 0 | — |
case-04 | pass→pass | 10,808 | 6,894 | -36% | 1 | 1 | 0% | 1,714 | 2,154 | +26% | 0 | 0 | — |
case-05 | fail→pass | 21,487 | 10,593 | -51% | 1 | 1 | 0% | 2,896 | 1,844 | -36% | 0 | 0 | — |
case-06 | pass→pass | 9,466 | 10,197 | +8% | 1 | 1 | 0% | 1,702 | 1,738 | +2% | 0 | 0 | — |
case-07 | pass→pass | 12,296 | 7,921 | -36% | 1 | 1 | 0% | 2,102 | 2,082 | -1% | 0 | 0 | — |
case-08 | fail→pass | 16,223 | 15,796 | -3% | 1 | 1 | 0% | 1,689 | 2,648 | +57% | 0 | 0 | — |
case-09 | pass→pass | 10,462 | 10,862 | +4% | 1 | 1 | 0% | 1,760 | 2,015 | +14% | 0 | 0 | — |
case-10 | fail→pass | 15,650 | 5,506 | -65% | 1 | 1 | 0% | 1,713 | 2,036 | +19% | 0 | 0 | — |
case-11 | fail→pass | 13,544 | 10,590 | -22% | 1 | 1 | 0% | 1,958 | 1,980 | +1% | 0 | 0 | — |
case-12 | fail→pass | 12,289 | 9,935 | -19% | 1 | 1 | 0% | 1,147 | 1,925 | +68% | 0 | 0 | — |
case-13 | fail→pass | 12,048 | 6,269 | -48% | 1 | 1 | 0% | 1,912 | 1,913 | +0% | 0 | 0 | — |
case-14 | fail→pass | 9,774 | 5,120 | -48% | 1 | 1 | 0% | 1,721 | 1,991 | +16% | 0 | 0 | — |
case-15 | fail→pass | 17,033 | 3,846 | -77% | 1 | 1 | 0% | 1,883 | 1,714 | -9% | 0 | 0 | — |
case-16 | fail→pass | 12,535 | 11,019 | -12% | 1 | 1 | 0% | 1,058 | 1,757 | +66% | 0 | 0 | — |
case-17 | fail→pass | 6,460 | 11,220 | +74% | 1 | 1 | 0% | 1,062 | 2,210 | +108% | 0 | 0 | — |
case-18 | fail→pass | 10,284 | 5,686 | -45% | 1 | 1 | 0% | 1,829 | 1,779 | -3% | 0 | 0 | — |
case-19 | pass→pass | 14,256 | 4,208 | -70% | 1 | 1 | 0% | 1,525 | 1,519 | -0% | 0 | 0 | — |
case-20 | fail→pass | 11,857 | 4,609 | -61% | 1 | 1 | 0% | 1,951 | 1,874 | -4% | 0 | 0 | — |
case-21 | fail→pass | 15,997 | 3,507 | -78% | 1 | 1 | 0% | 1,731 | 1,465 | -15% | 0 | 0 | — |
case-22 | fail→pass | 11,900 | 11,000 | -8% | 1 | 1 | 0% | 1,615 | 1,886 | +17% | 0 | 0 | — |
case-23 | fail→pass | 7,850 | 7,023 | -11% | 1 | 1 | 0% | 1,201 | 2,303 | +92% | 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 22 counted toward the lift figure. The other 1 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 +74 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.