Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use this skill when the user needs Obsidian runtime debugging or developer introspection through official desktop Obsidian CLI developer commands, including devtools, console/errors capture, DOM/CSS inspection, screenshots, CDP calls, and controlled eval. Do not use for regular note CRUD, task/property editing, Sync/Publish administration, or community tooling outside the official CLI.
.claude/skills/hashgraph-online-obsidian-cli-devtools/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 68% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -26% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -30% | 0% |
Use this skill for runtime debugging and developer diagnostics through official desktop obsidian CLI developer commands.
Use this skill when:
eval or dev:cdpDo not use this skill when:
obsidian-cli-workflows)obsidian:// launcher flowsAssume these must be true before relying on this skill:
obsidian command is installed and registeredobsidian child launches can crash; use the sanitized wrapperIn 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 or filesystem boundaries.
dev:errors, dev:console, dev:dom, dev:css.eval and dev:cdp as high-risk commands.eval or dev:cdp only when the user explicitly asked for runtime code execution or CDP calls.eval or dev:cdp, state the exact code/method and parameters being executed.dev:errors, dev:console, dev:dom, dev:css, dev:screenshotdevtools, dev:debug, dev:mobileeval, dev:cdpAlways return:
low, medium, high)direct or escalated)devtoolsdev:debugdev:cdpdev:errorsdev:screenshotdev:consoledev:cssdev:domdev:mobileevalreferences/obsidian-cli-devtools-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 | 7,877 | 27,235 | +246% | 1 | 1 | 0% | 1,540 | 2,583 | +68% | 0 | 0 | — |
case-12 | fail→pass | 16,131 | 9,895 | -39% | 1 | 1 | 0% | 1,803 | 1,631 | -10% | 0 | 0 | — |
case-02 | fail→fail | 9,146 | 20,405 | +123% | 1 | 1 | 0% | 1,229 | 1,329 | +8% | 0 | 0 | — |
case-03 | fail→fail | 13,182 | 14,181 | +8% | 1 | 1 | 0% | 1,385 | 1,366 | -1% | 0 | 0 | — |
case-04 | fail→pass | 11,761 | 7,545 | -36% | 1 | 1 | 0% | 1,977 | 1,888 | -5% | 0 | 0 | — |
case-05 | fail→fail | 5,593 | 16,571 | +196% | 1 | 1 | 0% | 909 | 1,584 | +74% | 0 | 0 | — |
case-06 | fail→pass | 18,952 | 13,747 | -27% | 1 | 1 | 0% | 2,808 | 2,066 | -26% | 0 | 0 | — |
case-07 | fail→pass | 18,444 | 9,026 | -51% | 1 | 1 | 0% | 2,142 | 1,497 | -30% | 0 | 0 | — |
case-08 | fail→pass | 19,574 | 4,386 | -78% | 1 | 1 | 0% | 1,843 | 1,535 | -17% | 0 | 0 | — |
case-09 | fail→fail | 19,945 | 3,377 | -83% | 1 | 1 | 0% | 2,089 | 1,310 | -37% | 0 | 0 | — |
case-10 | fail→pass | 9,714 | 9,164 | -6% | 1 | 1 | 0% | 1,570 | 1,489 | -5% | 0 | 0 | — |
case-11 | fail→pass | 9,545 | 10,526 | +10% | 1 | 1 | 0% | 1,462 | 1,758 | +20% | 0 | 0 | — |
case-13 | fail→pass | 20,699 | 23,889 | +15% | 1 | 1 | 0% | 2,740 | 2,203 | -20% | 0 | 0 | — |
case-14 | pass→pass | 12,027 | 9,925 | -17% | 1 | 1 | 0% | 1,847 | 1,527 | -17% | 0 | 0 | — |
case-15 | fail→pass | 8,749 | 9,584 | +10% | 1 | 1 | 0% | 1,182 | 1,583 | +34% | 0 | 0 | — |
case-16 | pass→pass | 9,760 | 2,522 | -74% | 1 | 1 | 0% | 787 | 1,190 | +51% | 0 | 0 | — |
case-17 | pass→pass | 26,703 | 11,467 | -57% | 1 | 1 | 0% | 2,900 | 1,917 | -34% | 0 | 0 | — |
case-18 | fail→pass | 13,443 | 9,123 | -32% | 1 | 1 | 0% | 1,342 | 1,578 | +18% | 0 | 0 | — |
case-19 | pass→pass | 12,305 | 4,992 | -59% | 1 | 1 | 0% | 1,494 | 1,584 | +6% | 0 | 0 | — |
case-20 | pass→pass | 27,599 | 14,249 | -48% | 1 | 1 | 0% | 1,987 | 2,000 | +1% | 0 | 0 | — |
case-21 | pass→pass | 11,636 | 3,724 | -68% | 1 | 1 | 0% | 1,672 | 1,407 | -16% | 0 | 0 | — |
case-22 | pass→pass | 14,159 | 7,173 | -49% | 1 | 1 | 0% | 1,337 | 1,864 | +39% | 0 | 0 | — |
case-23 | fail→fail | 11,995 | 3,327 | -72% | 1 | 1 | 0% | 1,501 | 1,231 | -18% | 0 | 0 | — |
case-24 | fail→pass | 20,362 | 9,280 | -54% | 1 | 1 | 0% | 2,511 | 1,565 | -38% | 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. 24 cases were attempted, and 21 counted toward the lift figure. The other 3 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 +50 percentage points is the difference between those two pass rates over the 21 comparable cases. 2 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.