Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Capsule CRM integration. Manage crm and sales data, records, and workflows. Use when the user wants to interact with Capsule CRM data.
.claude/skills/membranedev-capsule-crm/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-15 | ✗→✓ | ▲ Improved | 52% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 56% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 110% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 70% | 0% |
Capsule CRM is a customer relationship management (CRM) platform. It helps small to medium-sized businesses manage contacts, sales pipelines, and customer interactions. Sales teams and account managers use it to track leads and nurture customer relationships.
Official docs: https://developer.capsulecrm.com/
This skill uses the Membrane CLI to interact with Capsule CRM. 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@latest
bashmembrane login --tenant --clientName=<agentType>
This will either open a browser for authentication or print an authorization URL to the console, depending on whether interactive mode is available.
Headless environments: The command will print an authorization URL. Ask the user to open it in a browser. When they see a code after completing login, finish with:
bashmembrane login complete <code>
Add --json to any command for machine-readable JSON output.
Agent Types : claude, openclaw, codex, warp, windsurf, etc. Those will be used to adjust tooling to be used best with your harness
Use membrane connection ensure to find or create a connection by app URL or domain:
bashmembrane connection ensure "https://capsulecrm.com/" --json
The user completes authentication in the browser. The output contains the new connection id.
This is the fastest way to get a connection. The URL is normalized to a domain and matched against known apps. If no app is found, one is created and a connector is built automatically.
If the returned connection has state: "READY", skip to Step 2.
If the connection is in BUILDING state, poll until it's ready:
bashnpx @membranehq/cli connection get <id> --wait --json
The --wait flag long-polls (up to --timeout seconds, default 30) until the state changes. Keep polling until state is no longer BUILDING.
The resulting state tells you what to do next:
READY — connection is fully set up. Skip to Step 2.CLIENT_ACTION_REQUIRED — the user or agent needs to do something. The clientAction object describes the required action:clientAction.type — the kind of action needed:"connect" — user needs to authenticate (OAuth, API key, etc.). This covers initial authentication and re-authentication for disconnected connections."provide-input" — more information is needed (e.g. which app to connect to).clientAction.description — human-readable explanation of what's needed.clientAction.uiUrl (optional) — URL to a pre-built UI where the user can complete the action. Show this to the user when present.clientAction.agentInstructions (optional) — instructions for the AI agent on how to proceed programmatically.After the user completes the action (e.g. authenticates in the browser), poll again with membrane connection get <id> --json to check if the state moved to READY.
CONFIGURATION_ERROR or SETUP_FAILED — something went wrong. Check the error field for details.Search using a natural language description of what you want to do:
bashmembrane action list --connectionId=CONNECTION_ID --intent "QUERY" --limit 10 --json
You should always search for actions in the context of a specific connection.
Each result includes id, name, description, inputSchema (what parameters the action accepts), and outputSchema (what it returns).
| Name | Key | Description | | --- | --- | --- | | List Users | list-users | List all users on the Capsule account | | List Projects | list-projects | List all projects in Capsule CRM | | List Tasks | list-tasks | List all tasks in Capsule CRM | | List Opportunities | list-opportunities | List all opportunities in Capsule CRM | | List Parties | list-parties | List all parties (people and organizations) in Capsule CRM | | Get User | get-user | Get a specific user by ID | | Get Project | get-project | Get a specific project by ID | | Get Task | get-task | Get a specific task by ID | | Get Opportunity | get-opportunity | Get a specific opportunity by ID | | Get Party | get-party | Get a specific party (person or organization) by ID | | Create Project | create-project | Create a new project in Capsule CRM | | Create Task | create-task | Create a new task in Capsule CRM | | Create Opportunity | create-opportunity | Create a new opportunity in Capsule CRM | | Create Party | create-party | Create a new party (person or organization) in Capsule CRM | | Update Project | update-project | Update an existing project in Capsule CRM | | Update Task | update-task | Update an existing task in Capsule CRM | | Update Opportunity | update-opportunity | Update an existing opportunity in Capsule CRM | | Update Party | update-party | Update an existing party in Capsule CRM | | Delete Project | delete-project | Delete a project from Capsule CRM | | Delete Task | delete-task | Delete a task from Capsule CRM |
bashmembrane action run <actionId> --connectionId=CONNECTION_ID --json
To pass JSON parameters:
bashmembrane action run <actionId> --connectionId=CONNECTION_ID --input '{"key": "value"}' --json
The result is in the output field of the response.
When the available actions don't cover your use case, you can send requests directly to the Capsule CRM 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-15 | fail→pass | 8,344 | 1,726 | -79% | 1 | 1 | 0% | 1,332 | 2,024 | +52% | 0 | 0 | — |
case-01 | fail→fail | 6,353 | 16,393 | +158% | 1 | 1 | 0% | 447 | 2,034 | +355% | 0 | 0 | — |
case-02 | fail→fail | 7,221 | 6,337 | -12% | 1 | 1 | 0% | 1,178 | 2,030 | +72% | 0 | 0 | — |
case-03 | fail→fail | 8,467 | 6,132 | -28% | 1 | 1 | 0% | 1,340 | 2,010 | +50% | 0 | 0 | — |
case-04 | pass→pass | 2,145 | 3,268 | +52% | 1 | 1 | 0% | 302 | 2,237 | +641% | 0 | 0 | — |
case-05 | pass→pass | 2,548 | 1,904 | -25% | 1 | 1 | 0% | 392 | 2,013 | +414% | 0 | 0 | — |
case-06 | pass→pass | 2,727 | 3,482 | +28% | 1 | 1 | 0% | 426 | 2,138 | +402% | 0 | 0 | — |
case-07 | fail→pass | 9,819 | 2,689 | -73% | 1 | 1 | 0% | 1,408 | 2,198 | +56% | 0 | 0 | — |
case-08 | fail→pass | 14,881 | 1,586 | -89% | 1 | 1 | 0% | 2,428 | 1,985 | -18% | 0 | 0 | — |
case-09 | pass→pass | 11,679 | 1,906 | -84% | 1 | 1 | 0% | 1,751 | 2,010 | +15% | 0 | 0 | — |
case-10 | pass→pass | 21,013 | 1,153 | -95% | 1 | 1 | 0% | 1,955 | 1,940 | -1% | 0 | 0 | — |
case-11 | fail→pass | 8,050 | 4,789 | -41% | 1 | 1 | 0% | 1,192 | 2,499 | +110% | 0 | 0 | — |
case-12 | fail→pass | 8,341 | 2,778 | -67% | 1 | 1 | 0% | 1,294 | 2,201 | +70% | 0 | 0 | — |
case-13 | pass→fail | 16,571 | 1,736 | -90% | 1 | 1 | 0% | 2,656 | 1,952 | -27% | 0 | 0 | — |
case-14 | pass→pass | 6,679 | 2,391 | -64% | 1 | 1 | 0% | 1,120 | 2,161 | +93% | 0 | 0 | — |
case-16 | fail→pass | 11,560 | 2,378 | -79% | 1 | 1 | 0% | 1,747 | 2,179 | +25% | 0 | 0 | — |
case-17 | pass→pass | 5,874 | 1,423 | -76% | 1 | 1 | 0% | 907 | 1,925 | +112% | 0 | 0 | — |
case-18 | pass→pass | 8,125 | 1,118 | -86% | 1 | 1 | 0% | 1,201 | 1,894 | +58% | 0 | 0 | — |
case-19 | pass→pass | 5,674 | 1,569 | -72% | 1 | 1 | 0% | 821 | 1,933 | +135% | 0 | 0 | — |
case-20 | pass→pass | 4,617 | 1,434 | -69% | 1 | 1 | 0% | 635 | 1,950 | +207% | 0 | 0 | — |
case-21 | pass→pass | 6,043 | 1,288 | -79% | 1 | 1 | 0% | 926 | 1,921 | +107% | 0 | 0 | — |
case-22 | pass→pass | 7,773 | 3,127 | -60% | 1 | 1 | 0% | 1,017 | 2,157 | +112% | 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 19 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 +23 percentage points is the difference between those two pass rates over the 19 comparable cases. 1 case got worse with the skill loaded, and it is 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.