Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Basecamp integration. Manage Projects, Persons, Clients. Use when the user wants to interact with Basecamp data.
.claude/skills/membranedev-basecamp/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | 37% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 184% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 68% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 110% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 45% | 0% |
Basecamp is a project management and team communication tool. It's used by businesses of all sizes to organize projects, tasks, and discussions in one place. Teams use it to collaborate, track progress, and stay on the same page.
Official docs: https://github.com/basecamp/bc3-api
Use action names and parameters as needed.
This skill uses the Membrane CLI to interact with Basecamp. 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 "" --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 Projects | list-projects | List all projects visible to the current user | | List Messages | list-messages | List all messages in a message board | | List To-dos | list-todos | List all to-dos in a to-do list | | List To-do Lists | list-todo-lists | List all to-do lists in a to-do set | | List Comments | list-comments | List all comments on a recording (message, to-do, etc.) | | List People | list-people | List all people visible to the current user | | List Project People | list-project-people | List all people on a specific project | | Get Project | get-project | Get a specific project by ID | | Get Message | get-message | Get a specific message by ID | | Get To-do | get-todo | Get a specific to-do by ID | | Get To-do List | get-todo-list | Get a specific to-do list by ID | | Get Comment | get-comment | Get a specific comment by ID | | Get Person | get-person | Get a person by ID | | Create Project | create-project | Create a new project | | Create Message | create-message | Create a new message in a message board | | Create To-do | create-todo | Create a new to-do in a to-do list | | Create To-do List | create-todo-list | Create a new to-do list in a to-do set | | Create Comment | create-comment | Create a new comment on a recording (message, to-do, etc.) | | Update Project | update-project | Update an existing project | | Update Message | update-message | Update an existing message |
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 Basecamp 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-06 | fail→pass | 10,455 | 1,782 | -83% | 1 | 1 | 0% | 1,537 | 2,100 | +37% | 0 | 0 | — |
case-01 | fail→fail | 9,484 | 6,552 | -31% | 1 | 1 | 0% | 1,232 | 2,145 | +74% | 0 | 0 | — |
case-02 | fail→fail | 8,585 | 5,927 | -31% | 1 | 1 | 0% | 817 | 2,238 | +174% | 0 | 0 | — |
case-03 | fail→fail | 5,987 | 5,789 | -3% | 1 | 1 | 0% | 883 | 2,170 | +146% | 0 | 0 | — |
case-04 | fail→pass | 4,710 | 1,378 | -71% | 1 | 1 | 0% | 714 | 2,031 | +184% | 0 | 0 | — |
case-05 | fail→pass | 16,939 | 2,234 | -87% | 1 | 1 | 0% | 1,330 | 2,236 | +68% | 0 | 0 | — |
case-07 | fail→pass | 7,218 | 3,962 | -45% | 1 | 1 | 0% | 1,224 | 2,570 | +110% | 0 | 0 | — |
case-08 | fail→pass | 9,789 | 1,905 | -81% | 1 | 1 | 0% | 1,471 | 2,140 | +45% | 0 | 0 | — |
case-09 | pass→pass | 11,433 | 4,809 | -58% | 1 | 1 | 0% | 1,708 | 2,714 | +59% | 0 | 0 | — |
case-10 | fail→pass | 12,064 | 2,931 | -76% | 1 | 1 | 0% | 1,675 | 2,354 | +41% | 0 | 0 | — |
case-11 | fail→pass | 7,573 | 1,213 | -84% | 1 | 1 | 0% | 1,187 | 2,019 | +70% | 0 | 0 | — |
case-12 | fail→pass | 7,977 | 1,972 | -75% | 1 | 1 | 0% | 1,146 | 2,143 | +87% | 0 | 0 | — |
case-13 | fail→pass | 6,962 | 1,860 | -73% | 1 | 1 | 0% | 1,098 | 2,141 | +95% | 0 | 0 | — |
case-14 | fail→pass | 5,412 | 1,487 | -73% | 1 | 1 | 0% | 731 | 2,035 | +178% | 0 | 0 | — |
case-15 | fail→pass | 6,652 | 1,536 | -77% | 1 | 1 | 0% | 1,132 | 2,070 | +83% | 0 | 0 | — |
case-16 | fail→pass | 6,714 | 1,613 | -76% | 1 | 1 | 0% | 993 | 2,060 | +107% | 0 | 0 | — |
case-17 | fail→pass | 7,683 | 2,448 | -68% | 1 | 1 | 0% | 1,243 | 2,259 | +82% | 0 | 0 | — |
case-18 | fail→pass | 4,565 | 2,753 | -40% | 1 | 1 | 0% | 820 | 2,275 | +177% | 0 | 0 | — |
case-19 | pass→pass | 4,116 | 2,442 | -41% | 1 | 1 | 0% | 734 | 2,291 | +212% | 0 | 0 | — |
case-20 | pass→pass | 5,723 | 1,710 | -70% | 1 | 1 | 0% | 839 | 2,179 | +160% | 0 | 0 | — |
case-21 | fail→pass | 8,478 | 2,723 | -68% | 1 | 1 | 0% | 1,311 | 2,266 | +73% | 0 | 0 | — |
case-22 | pass→pass | 7,586 | 6,394 | -16% | 1 | 1 | 0% | 1,336 | 2,896 | +117% | 0 | 0 | — |
case-23 | pass→pass | 10,374 | 7,768 | -25% | 1 | 1 | 0% | 1,911 | 3,360 | +76% | 0 | 0 | — |
case-24 | pass→pass | 12,452 | 14,949 | +20% | 1 | 1 | 0% | 1,962 | 4,401 | +124% | 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 +63 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.