The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses a shell script scripts/monday_api.sh to interact directly with the Monday.com GraphQL API. The script securely manages the API token by reading it from .env or .env.local files and includes error handling for authentication and rate limits.
[EXTERNAL_DOWNLOADS]: Instructions are provided to configure an MCP server using npx @mondaydotcomorg/monday-api-mcp@latest. This fetches and executes a package from the official Monday.com organization on the npm registry.
[REMOTE_CODE_EXECUTION]: The skill supports a hosted MCP server at https://mcp.monday.com/mcp, which is an official service endpoint provided by Monday.com.
[PROMPT_INJECTION]: The skill processes external data from Monday.com boards and items, creating a potential surface for indirect prompt injection.
Ingestion points: Board items, updates (comments), and schemas fetched via scripts/monday_api.sh and MCP tools like get_board_items_page.
Boundary markers: Not explicitly defined in the prompt templates to distinguish between instructions and ingested data.
Capability inventory: Subprocess execution (via shell script), network operations (API calls), and data modification (mutations) within the workspace.
Sanitization: No specific sanitization or validation of the content of Monday.com item names or comments is mentioned before processing.

monday-com