Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Automate Trello boards, cards, and workflows via Rube MCP (Composio). Create cards, manage lists, assign members, and search across boards programmatically.
.claude/skills/davepoon-trello-automation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 140% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 229% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 57% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 78% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 377% | 0% |
Automate Trello board management, card creation, and team workflows through Composio's Rube MCP integration.
Toolkit docs: composio.dev/toolkits/trello
RUBE_MANAGE_CONNECTIONS with toolkit trelloRUBE_SEARCH_TOOLS first to get current tool schemasGet Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
RUBE_SEARCH_TOOLS respondsRUBE_MANAGE_CONNECTIONS with toolkit trelloWhen to use: User wants to add a new card/task to a Trello board
Tool sequence:
TRELLO_GET_MEMBERS_BOARDS_BY_ID_MEMBER - List boards to find target board ID Prerequisite]TRELLO_GET_BOARDS_LISTS_BY_ID_BOARD - Get lists on board to find target list ID Prerequisite]TRELLO_ADD_CARDS - Create the card on the resolved list Required]TRELLO_ADD_CARDS_CHECKLISTS_BY_ID_CARD - Add a checklist to the card Optional]TRELLO_ADD_CARDS_CHECKLIST_CHECK_ITEM_BY_ID_CARD_BY_ID_CHECKLIST - Add items to the checklist Optional]Key parameters:
idList: 24-char hex ID (NOT list name)name: Card titledesc: Card description (supports Markdown)pos: Position ('top'/'bottom')due: Due date (ISO 8601 format)Pitfalls:
When to use: User wants to view, browse, or restructure board layout
Tool sequence:
TRELLO_GET_MEMBERS_BOARDS_BY_ID_MEMBER - List all boards for the user Required]TRELLO_GET_BOARDS_BY_ID_BOARD - Get detailed board info Required]TRELLO_GET_BOARDS_LISTS_BY_ID_BOARD - Get lists (columns) on the board Optional]TRELLO_GET_BOARDS_MEMBERS_BY_ID_BOARD - Get board members Optional]TRELLO_GET_BOARDS_LABELS_BY_ID_BOARD - Get labels on the board Optional]Key parameters:
idMember: Use 'me' for authenticated userfilter: 'open', 'starred', or 'all'idBoard: 24-char hex or 8-char shortLink (NOT board name)Pitfalls:
When to use: User wants to change a card's status by moving it to another list
Tool sequence:
TRELLO_GET_SEARCH - Find the card by name or keyword Prerequisite]TRELLO_GET_BOARDS_LISTS_BY_ID_BOARD - Get destination list ID Prerequisite]TRELLO_UPDATE_CARDS_BY_ID_CARD - Update card's idList to move it Required]Key parameters:
idCard: Card ID from searchidList: Destination list IDpos: Optional ordering within new listPitfalls:
When to use: User wants to assign team members to cards
Tool sequence:
TRELLO_GET_BOARDS_MEMBERS_BY_ID_BOARD - Get member IDs from the board Prerequisite]TRELLO_ADD_CARDS_ID_MEMBERS_BY_ID_CARD - Add a member to the card Required]Key parameters:
idCard: Target card IDvalue: Member ID to assignPitfalls:
When to use: User wants to find specific cards across boards
Tool sequence:
TRELLO_GET_SEARCH - Search by query string Required]Key parameters:
query: Search string (supports board:, list:, label:, is:open/archived operators)modelTypes: Set to 'cards'partial: Set to 'true' for prefix matchingPitfalls:
When to use: User wants to add context to an existing card
Tool sequence:
TRELLO_ADD_CARDS_ACTIONS_COMMENTS_BY_ID_CARD - Post a comment on the card Required]TRELLO_ADD_CARDS_ATTACHMENTS_BY_ID_CARD - Attach a file or URL Optional]Key parameters:
text: Comment text (1-16384 chars, supports Markdown and @mentions)url OR file: Attachment source (not both)name: Attachment display namemimeType: File MIME typePitfalls:
Always resolve display names to IDs before operations:
TRELLO_GET_MEMBERS_BOARDS_BY_ID_MEMBER with idMember='me'TRELLO_GET_BOARDS_LISTS_BY_ID_BOARD with resolved board IDTRELLO_GET_SEARCH with query stringTRELLO_GET_BOARDS_MEMBERS_BY_ID_BOARDMost list endpoints return all items. For boards with 1000+ cards, use limit and before parameters on card listing endpoints.
300 requests per 10 seconds per token. Use TRELLO_GET_BATCH for bulk read operations to stay within limits.
| Task | Tool Slug | Key Params | |------|-----------|------------| | List user's boards | TRELLO_GET_MEMBERS_BOARDS_BY_ID_MEMBER | idMember='me', filter='open' | | Get board details | TRELLO_GET_BOARDS_BY_ID_BOARD | idBoard (24-char hex) | | List board lists | TRELLO_GET_BOARDS_LISTS_BY_ID_BOARD | idBoard | | Create card | TRELLO_ADD_CARDS | idList, name, desc, pos, due | | Update card | TRELLO_UPDATE_CARDS_BY_ID_CARD | idCard, idList (to move) | | Search cards | TRELLO_GET_SEARCH | query, modelTypes='cards' | | Add checklist | TRELLO_ADD_CARDS_CHECKLISTS_BY_ID_CARD | idCard, name | | Add comment | TRELLO_ADD_CARDS_ACTIONS_COMMENTS_BY_ID_CARD | idCard, text | | Assign member | TRELLO_ADD_CARDS_ID_MEMBERS_BY_ID_CARD | idCard, value (member ID) | | Attach file/URL | TRELLO_ADD_CARDS_ATTACHMENTS_BY_ID_CARD | idCard, url OR file | | Get board members | TRELLO_GET_BOARDS_MEMBERS_BY_ID_BOARD | idBoard | | Batch read | TRELLO_GET_BATCH | urls (comma-separated paths) |
Powered by Composio
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | pass→pass | 7,773 | 6,971 | -10% | 1 | 1 | 0% | 1,402 | 3,606 | +157% | 0 | 0 | — |
case-07 | fail→pass | 7,151 | 4,141 | -42% | 1 | 1 | 0% | 1,222 | 2,938 | +140% | 0 | 0 | — |
case-01 | fail→fail | 5,350 | 6,227 | +16% | 1 | 1 | 0% | 943 | 2,661 | +182% | 0 | 0 | — |
case-02 | fail→fail | 6,571 | 5,600 | -15% | 1 | 1 | 0% | 1,146 | 2,709 | +136% | 0 | 0 | — |
case-03 | fail→fail | 7,448 | 5,069 | -32% | 1 | 1 | 0% | 653 | 2,611 | +300% | 0 | 0 | — |
case-04 | pass→pass | 15,397 | 15,163 | -2% | 1 | 1 | 0% | 3,353 | 5,668 | +69% | 0 | 0 | — |
case-05 | pass→pass | 9,744 | 8,567 | -12% | 1 | 1 | 0% | 1,864 | 4,058 | +118% | 0 | 0 | — |
case-08 | fail→pass | 5,143 | 3,382 | -34% | 1 | 1 | 0% | 850 | 2,796 | +229% | 0 | 0 | — |
case-09 | fail→pass | 10,652 | 2,711 | -75% | 1 | 1 | 0% | 1,752 | 2,751 | +57% | 0 | 0 | — |
case-10 | fail→pass | 11,954 | 8,242 | -31% | 1 | 1 | 0% | 2,127 | 3,777 | +78% | 0 | 0 | — |
case-11 | fail→pass | 3,621 | 3,923 | +8% | 1 | 1 | 0% | 634 | 3,022 | +377% | 0 | 0 | — |
case-12 | pass→pass | 14,098 | 7,685 | -45% | 1 | 1 | 0% | 2,473 | 3,624 | +47% | 0 | 0 | — |
case-13 | pass→pass | 9,593 | 3,041 | -68% | 1 | 1 | 0% | 1,721 | 2,752 | +60% | 0 | 0 | — |
case-14 | fail→pass | 3,313 | 3,312 | -0% | 1 | 1 | 0% | 521 | 2,918 | +460% | 0 | 0 | — |
case-15 | pass→pass | 8,448 | 4,696 | -44% | 1 | 1 | 0% | 1,208 | 3,184 | +164% | 0 | 0 | — |
case-16 | pass→pass | 10,939 | 7,192 | -34% | 1 | 1 | 0% | 1,933 | 3,548 | +84% | 0 | 0 | — |
case-17 | fail→pass | 7,393 | 3,998 | -46% | 1 | 1 | 0% | 1,292 | 3,036 | +135% | 0 | 0 | — |
case-18 | fail→pass | 6,337 | 12,082 | +91% | 1 | 1 | 0% | 1,148 | 3,582 | +212% | 0 | 0 | — |
case-19 | fail→pass | 7,508 | 2,233 | -70% | 1 | 1 | 0% | 1,309 | 2,622 | +100% | 0 | 0 | — |
case-20 | pass→pass | 6,996 | 3,334 | -52% | 1 | 1 | 0% | 1,089 | 2,913 | +167% | 0 | 0 | — |
case-21 | pass→pass | 4,786 | 3,966 | -17% | 1 | 1 | 0% | 649 | 2,936 | +352% | 0 | 0 | — |
case-22 | fail→pass | 3,336 | 2,859 | -14% | 1 | 1 | 0% | 532 | 2,719 | +411% | 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 +45 percentage points is the difference between those two pass rates over the 19 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.