Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use the Inbox Zero API CLI to inspect the live API schema, list and manage automation rules, and read inbox analytics through the public API. Use this when a task involves Inbox Zero rules, stats, or API-driven automation and can be solved through the CLI instead of browser interaction.
.claude/skills/elie222-inbox-zero-api/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 53% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -55% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -50% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -37% | 0% |
Use this skill when the task is to inspect or change Inbox Zero state through the public API.
--json so the output is stable and machine-readable.rules, stats, etc.), keep credentials in INBOX_ZERO_API_KEY or OpenClaw skill config. Avoid passing API keys as CLI flags unless there is no alternative.inbox-zero-api openapi --json (no API key required).rules update as a full replacement. Read the current rule first if you only intend to change part of it.bashinbox-zero-api rules list --json inbox-zero-api stats by-period --period week --json inbox-zero-api openapi --json
If the CLI is not installed yet, install it with the OpenClaw installer or run npm install -g @inbox-zero/api.
Set INBOX_ZERO_API_KEY when using authenticated commands (rules, stats, etc.); openapi --json works without a key. Use shell profile, Cursor env, or a local env file—never commit keys. Install: npm install -g @inbox-zero/api or npx @inbox-zero/api.
Set the API key in ~/.openclaw/openclaw.json under skills.entries.inboxZeroApi.apiKey, or export INBOX_ZERO_API_KEY in the host environment.
Use INBOX_ZERO_BASE_URL or inbox-zero-api config set base-url <url> only for self-hosted or nonstandard deployments.
For exact command patterns and a safe mutation flow, read references/cli-reference.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 | 4,813 | 8,825 | +83% | 1 | 1 | 0% | 835 | 1,277 | +53% | 0 | 0 | — |
case-02 | fail→fail | 9,957 | 2,985 | -70% | 1 | 1 | 0% | 1,807 | 940 | -48% | 0 | 0 | — |
case-13 | fail→pass | 12,631 | 6,690 | -47% | 1 | 1 | 0% | 1,994 | 1,751 | -12% | 0 | 0 | — |
case-03 | fail→fail | 7,463 | 4,856 | -35% | 1 | 1 | 0% | 321 | 708 | +121% | 0 | 0 | — |
case-04 | fail→pass | 9,686 | 2,274 | -77% | 1 | 1 | 0% | 1,704 | 773 | -55% | 0 | 0 | — |
case-05 | fail→pass | 8,802 | 3,637 | -59% | 1 | 1 | 0% | 1,463 | 728 | -50% | 0 | 0 | — |
case-06 | pass→pass | 6,918 | 3,706 | -46% | 1 | 1 | 0% | 1,029 | 879 | -15% | 0 | 0 | — |
case-07 | fail→pass | 8,624 | 2,648 | -69% | 1 | 1 | 0% | 1,551 | 971 | -37% | 0 | 0 | — |
case-08 | fail→pass | 8,857 | 2,161 | -76% | 1 | 1 | 0% | 1,559 | 858 | -45% | 0 | 0 | — |
case-09 | fail→pass | 9,698 | 2,322 | -76% | 1 | 1 | 0% | 1,673 | 812 | -51% | 0 | 0 | — |
case-10 | fail→pass | 10,062 | 2,542 | -75% | 1 | 1 | 0% | 1,578 | 828 | -48% | 0 | 0 | — |
case-11 | pass→pass | 11,030 | 6,476 | -41% | 1 | 1 | 0% | 1,804 | 1,550 | -14% | 0 | 0 | — |
case-12 | fail→pass | 4,231 | 1,450 | -66% | 1 | 1 | 0% | 651 | 629 | -3% | 0 | 0 | — |
case-14 | fail→pass | 9,550 | 1,489 | -84% | 1 | 1 | 0% | 1,561 | 660 | -58% | 0 | 0 | — |
case-15 | pass→pass | 8,074 | 4,164 | -48% | 1 | 1 | 0% | 1,256 | 1,157 | -8% | 0 | 0 | — |
case-16 | fail→pass | 10,512 | 3,559 | -66% | 1 | 1 | 0% | 1,961 | 1,036 | -47% | 0 | 0 | — |
case-17 | fail→pass | 6,335 | 2,507 | -60% | 1 | 1 | 0% | 927 | 840 | -9% | 0 | 0 | — |
case-18 | fail→pass | 13,978 | 3,811 | -73% | 1 | 1 | 0% | 2,356 | 1,055 | -55% | 0 | 0 | — |
case-19 | fail→pass | 7,712 | 5,478 | -29% | 1 | 1 | 0% | 1,394 | 1,411 | +1% | 0 | 0 | — |
case-20 | pass→pass | 7,644 | 5,426 | -29% | 1 | 1 | 0% | 1,365 | 1,302 | -5% | 0 | 0 | — |
case-21 | pass→pass | 9,156 | 7,269 | -21% | 1 | 1 | 0% | 1,671 | 1,632 | -2% | 0 | 0 | — |
case-22 | pass→pass | 18,285 | 11,962 | -35% | 1 | 1 | 0% | 2,763 | 2,744 | -1% | 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, and 21 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 +64 percentage points is the difference between those two pass rates over the 21 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.