trello-card-creator — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited trello-card-creator (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
This skill provides a standardized workflow for expanding high-level sprint structures into testable, developer-ready Trello cards using the context_todo_board MCP server tools. It acts as an "Experienced Senior Full Stack Developer," breaking down features into clear Acceptance Criteria (AC) and highly prescriptive QA validation procedures.
When the user asks to generate Trello cards or detail the tasks for a sprint, follow these exact steps:
Before detailing any tasks, you MUST ensure you have the necessary context. Instead of asking the user directly, leverage the MCP tools to pull this information:
mcp_context_todo_board_list_boards or mcp_context_todo_board_get_active_board_info to identify the correct board. You'll also need the target list using mcp_context_todo_board_get_lists.mcp_context_todo_board_get_business_context and pass the target board's ID to automatically retrieve the MLP/MVP Definition, User Journey Flow, and any Integrations or overall context stored with the board.Only ask the user to provide pieces of information if they cannot be retrieved from the MCP tools or logically inferred from the available context.
For each task in the sprint structure, formulate its contents with Extreme Specificity. If the user hasn't provided fully fleshed-out task titles and descriptions, refine or create them based on the following task definition standards before moving to Acceptance Criteria and QA Steps. Remember the project context (Next.js, React, Node.js, PostgreSQL, Storybook, etc.) and the rule against writing test files.
Task Definition Standards:
Standard Tasks MUST include:
pnpm dev, curl -X POST ...)http://localhost:3000/dashboard)Manual Integration Tasks MUST include (if title ends with `[Manual]`):
[Manual].Once the details are prepared or approved by the user, automate the creation of the cards physically on Trello using the context_todo_board MCP tools:
mcp_context_todo_board_add_card_to_list.name to [Task ID] Title.description to the verbatim sprint task description, appended with the Dependencies and Sprint Goal (if any).mcp_context_todo_board_create_checklist (or the equivalent checklist tool) to add an "Acceptance Criteria" checklist to the card.mcp_context_todo_board_add_checklist_item to add each AC as a separate item.mcp_context_todo_board_add_checklist_item for every specific prescriptive testing instruction.CRITICAL: Respect the original Sprint Assignment, Ordering, and Dependencies. Do not reorganize the sprint.
After all task cards have been fully provisioned, provide the user with a summary of the created cards. Verify that all components (AC, QA steps, Descriptions) were attached successfully to each Trello card.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.