Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Algomo integration. Manage data, records, and automate workflows. Use when the user wants to interact with Algomo data.
.claude/skills/membranedev-algomo/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-20 | ✗→✓ | ▲ Improved | 20% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-19 | ✗→✓ | ▲ Improved | -15% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 65% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -10% | 0% |
Algomo is a customer communication platform that helps businesses manage and automate interactions across various channels. It's used by customer support, sales, and marketing teams to improve engagement and streamline communication workflows.
Official docs: https://docs.algomo.com/
This skill uses the Membrane CLI to interact with Algomo. 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 algomo --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 Algomo 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 | | --- | --- | --- | | Get Bot Response | get-bot-response | Generate a response from an Algomo chatbot. |
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 Algomo 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-20 | fail→pass | 8,654 | 4,419 | -49% | 1 | 1 | 0% | 1,319 | 1,587 | +20% | 0 | 0 | — |
case-14 | fail→pass | 11,619 | 3,621 | -69% | 1 | 1 | 0% | 1,678 | 1,512 | -10% | 0 | 0 | — |
case-01 | fail→fail | 1,812 | 18,544 | +923% | 1 | 1 | 0% | 252 | 1,072 | +325% | 0 | 0 | — |
case-19 | fail→pass | 9,928 | 2,349 | -76% | 1 | 1 | 0% | 1,536 | 1,302 | -15% | 0 | 0 | — |
case-02 | fail→fail | 4,196 | 3,959 | -6% | 1 | 1 | 0% | 296 | 1,063 | +259% | 0 | 0 | — |
case-03 | fail→pass | 6,313 | 3,390 | -46% | 1 | 1 | 0% | 921 | 1,523 | +65% | 0 | 0 | — |
case-04 | fail→pass | 7,614 | 1,240 | -84% | 1 | 1 | 0% | 1,188 | 1,071 | -10% | 0 | 0 | — |
case-05 | fail→pass | 10,295 | 2,547 | -75% | 1 | 1 | 0% | 1,578 | 1,313 | -17% | 0 | 0 | — |
case-06 | pass→pass | 10,699 | 2,740 | -74% | 1 | 1 | 0% | 1,593 | 1,326 | -17% | 0 | 0 | — |
case-07 | fail→pass | 7,676 | 23,209 | +202% | 1 | 1 | 0% | 1,144 | 1,339 | +17% | 0 | 0 | — |
case-08 | pass→pass | 10,221 | 2,690 | -74% | 1 | 1 | 0% | 1,688 | 1,388 | -18% | 0 | 0 | — |
case-09 | pass→pass | 5,332 | 2,213 | -58% | 1 | 1 | 0% | 930 | 1,351 | +45% | 0 | 0 | — |
case-10 | fail→pass | 8,679 | 1,569 | -82% | 1 | 1 | 0% | 1,294 | 1,187 | -8% | 0 | 0 | — |
case-11 | fail→pass | 13,953 | 2,514 | -82% | 1 | 1 | 0% | 2,480 | 1,343 | -46% | 0 | 0 | — |
case-12 | fail→pass | 9,433 | 3,312 | -65% | 1 | 1 | 0% | 1,854 | 1,457 | -21% | 0 | 0 | — |
case-13 | fail→pass | 8,486 | 1,709 | -80% | 1 | 1 | 0% | 1,276 | 1,177 | -8% | 0 | 0 | — |
case-15 | pass→pass | 8,110 | 2,949 | -64% | 1 | 1 | 0% | 1,238 | 1,364 | +10% | 0 | 0 | — |
case-16 | fail→pass | 9,365 | 1,660 | -82% | 1 | 1 | 0% | 1,329 | 1,176 | -12% | 0 | 0 | — |
case-17 | fail→pass | 9,409 | 1,300 | -86% | 1 | 1 | 0% | 1,400 | 1,096 | -22% | 0 | 0 | — |
case-18 | fail→pass | 8,720 | 1,982 | -77% | 1 | 1 | 0% | 1,321 | 1,202 | -9% | 0 | 0 | — |
case-21 | fail→pass | 13,698 | 9,359 | -32% | 1 | 1 | 0% | 2,151 | 2,313 | +8% | 0 | 0 | — |
case-22 | fail→fail | 14,887 | 14,164 | -5% | 1 | 1 | 0% | 2,294 | 2,729 | +19% | 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 20 counted toward the lift figure. The other 2 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 +68 percentage points is the difference between those two pass rates over the 20 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.