Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Bilionis integration. Manage data, records, and automate workflows. Use when the user wants to interact with Bilionis data.
.claude/skills/membranedev-bilionis/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 536% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 40% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 63% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 8% | 0% |
I don't have enough information to do that. I'm a large language model, able to communicate in response to a wide range of prompts and questions, but my knowledge about that specific app is limited. Is there anything else I can do to help?
Official docs: https://bilion.io/en/api-documentation/
This skill uses the Membrane CLI to interact with Bilionis. Membrane handles authentication and credentials refresh automatically — so you can focus on the integration logic rather than auth plumbing.
Install the Membrane CLI so you can run membrane from the terminal:
bashnpm install -g @membranehq/cli
bashmembrane login --tenant
A browser window opens for authentication.
Headless environments: Run the command, copy the printed URL for the user to open in a browser, then complete with membrane login complete <code>.
bash membrane search bilionis --elementType=connector --json Take the connector ID from output.items[0].element?.id, then: bash membrane connect --connectorId=CONNECTOR_ID --json The user completes authentication in the browser. The output contains the new connection id.
When you are not sure if connection already exists:
bash membrane connection list --json If a Bilionis connection exists, note its connectionId
When you know what you want to do but not the exact action ID:
bashmembrane action list --intent=QUERY --connectionId=CONNECTION_ID --json
This will return action objects with id and inputSchema in it, so you will know how to run it.
| Name | Key | Description | | --- | --- | --- | | Search Messages by City | search-messages-by-city | Search for messages/leads from a specific city in Bilionis. | | Search Messages by Email | search-messages-by-email | Search for messages/leads from a specific email address in Bilionis. | | Find Message by ID | find-message-by-id | Find a specific message/lead by its ID in Bilionis. | | Count Messages | count-messages | Count the total number of messages/leads in Bilionis. | | Get Today's Messages | get-todays-messages | Retrieve all messages/leads received today from Bilionis. | | Get Messages by Date Range | get-messages-by-date-range | Retrieve messages/leads from Bilionis within a specific date range. | | Get Unread Messages | get-unread-messages | Retrieve all unread messages/leads from Bilionis. | | List Messages | list-messages | Retrieve a list of messages/leads from Bilionis. |
bashmembrane action run --connectionId=CONNECTION_ID ACTION_ID --json
To pass JSON parameters:
bashmembrane action run --connectionId=CONNECTION_ID ACTION_ID --json --input "{ \"key\": \"value\" }"
When the available actions don't cover your use case, you can send requests directly to the Bilionis API through Membrane's proxy. Membrane automatically appends the base URL to the path you provide and injects the correct authentication headers — including transparent credential refresh if they expire.
bashmembrane request CONNECTION_ID /path/to/endpoint
Common options:
| Flag | Description | |------|-------------| | -X, --method | HTTP method (GET, POST, PUT, PATCH, DELETE). Defaults to GET | | -H, --header | Add a request header (repeatable), e.g. -H "Accept: application/json" | | -d, --data | Request body (string) | | --json | Shorthand to send a JSON body and set Content-Type: application/json | | --rawData | Send the body as-is without any processing | | --query | Query-string parameter (repeatable), e.g. --query "limit=10" | | --pathParam | Path parameter (repeatable), e.g. --pathParam "id=123" |
membrane action list --intent=QUERY (replace QUERY with your intent) to find existing actions before writing custom API calls. Pre-built actions handle pagination, field mapping, and edge cases that raw API calls miss.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 10,493 | 5,520 | -47% | 1 | 1 | 0% | 1,158 | 1,291 | +11% | 0 | 0 | — |
case-02 | fail→pass | 3,188 | 12,891 | +304% | 1 | 1 | 0% | 444 | 2,823 | +536% | 0 | 0 | — |
case-03 | fail→fail | 7,719 | 1,811 | -77% | 1 | 1 | 0% | 1,102 | 1,335 | +21% | 0 | 0 | — |
case-04 | fail→pass | 5,683 | 1,258 | -78% | 1 | 1 | 0% | 906 | 1,269 | +40% | 0 | 0 | — |
case-05 | fail→pass | 8,472 | 1,662 | -80% | 1 | 1 | 0% | 1,294 | 1,379 | +7% | 0 | 0 | — |
case-06 | fail→pass | 4,692 | 1,585 | -66% | 1 | 1 | 0% | 817 | 1,335 | +63% | 0 | 0 | — |
case-07 | fail→pass | 8,403 | 1,604 | -81% | 1 | 1 | 0% | 1,274 | 1,375 | +8% | 0 | 0 | — |
case-08 | fail→pass | 11,300 | 2,396 | -79% | 1 | 1 | 0% | 1,677 | 1,456 | -13% | 0 | 0 | — |
case-09 | fail→pass | 6,121 | 1,751 | -71% | 1 | 1 | 0% | 973 | 1,434 | +47% | 0 | 0 | — |
case-10 | fail→pass | 6,792 | 1,920 | -72% | 1 | 1 | 0% | 1,016 | 1,447 | +42% | 0 | 0 | — |
case-11 | fail→pass | 8,554 | 2,644 | -69% | 1 | 1 | 0% | 1,288 | 1,589 | +23% | 0 | 0 | — |
case-12 | fail→pass | 8,195 | 7,119 | -13% | 1 | 1 | 0% | 1,328 | 1,517 | +14% | 0 | 0 | — |
case-13 | pass→pass | 11,437 | 2,716 | -76% | 1 | 1 | 0% | 2,129 | 1,567 | -26% | 0 | 0 | — |
case-14 | pass→pass | 6,714 | 1,968 | -71% | 1 | 1 | 0% | 999 | 1,483 | +48% | 0 | 0 | — |
case-15 | fail→pass | 10,594 | 1,545 | -85% | 1 | 1 | 0% | 1,896 | 1,417 | -25% | 0 | 0 | — |
case-16 | fail→pass | 5,597 | 2,526 | -55% | 1 | 1 | 0% | 875 | 1,585 | +81% | 0 | 0 | — |
case-17 | fail→pass | 12,150 | 1,824 | -85% | 1 | 1 | 0% | 2,003 | 1,410 | -30% | 0 | 0 | — |
case-18 | pass→pass | 11,928 | 3,068 | -74% | 1 | 1 | 0% | 1,689 | 1,674 | -1% | 0 | 0 | — |
case-19 | fail→pass | 7,399 | 1,367 | -82% | 1 | 1 | 0% | 1,142 | 1,359 | +19% | 0 | 0 | — |
case-20 | pass→pass | 4,943 | 3,693 | -25% | 1 | 1 | 0% | 896 | 1,826 | +104% | 0 | 0 | — |
case-21 | pass→pass | 3,967 | 4,155 | +5% | 1 | 1 | 0% | 696 | 1,819 | +161% | 0 | 0 | — |
case-22 | pass→pass | 4,230 | 3,777 | -11% | 1 | 1 | 0% | 602 | 1,738 | +189% | 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.