Feature Requests

Allow Workspace Administrators to upload or write custom instructional files (e.g., SKILL.md format) to explicitly train ClickUp Brain or Super Agents on complex, multi-step company workflows, strict data validation rules, and context-dependent task creation. Currently, ClickUp Brain and Super Agents are excellent at scanning existing data and generating single-turn summaries or code. However, when it comes to executing complex, proprietary business workflows, the AI relies heavily on reactive prompt engineering. In contrast, Anthropic Claude uses a modular, token-saving "Skills" concept (via .md instruction packages and references). Without a native equivalent in ClickUp, teams must host external scripts on third-party servers or route data out of ClickUp via external MCP setups just to enforce rigid, step-by-step workflow procedures for the AI. Proposed Solution / Feature Request A native "AI Skill Builder / Manager" within ClickUp's settings where admins can deploy reusable AI blueprints: Skill Definition Files ( SKILL.md Editor): A dedicated text/markdown area for a Space or Folder where we define exactly when and how ClickUp Brain should execute a workflow (e.g., "When a ticket changes to 'SOW Signed', build 5 specific subtasks, assign them based on role, and calculate relative due dates"). Instead of feeding massive prompt templates into every single AI interaction (which drains performance and context limits), ClickUp Brain should dynamically load the specific "Skill" only when the defined trigger or manual @mention occurs. Also, skills should be added to agents and being able to execute actions with integrations (Google Drive, Docs, MCP Tools, etc.).

It'd be dope if clickup AI would support https://modelcontextprotocol.io/ . With that its agent could instantly integrate with a ton of tools without you having to do first party integrations in the first place. Some tools like cursor.ai just allow you to paste in an MCP link and bam, you have it in your agent. Support this ONE thing and save time integrating all the others. Let your users do the job and give them the power to integrate properly.

I would like to request a feature for ClickUp AI Super Agents. We need Super Agents to be able to apply saved task templates from the ClickUp Template Center, such as “SKUs”, “Crono Geral”, “KITs”, and other workspace templates. Our Super Agents create and organize PMO tasks automatically, but today they cannot directly apply saved templates. Because of this, they try to recreate the task structure manually, which can cause: Subtasks created out of order Missing template elements Duplicated subtasks Incorrect task structures Extra manual work for the PMO team The expected behavior is that a Super Agent should be able to: Find saved task templates in the workspace. Apply a selected template to a new or existing task. Preserve subtasks, order, custom fields, descriptions, dependencies, and time estimates. Use templates created by our team, not only default ClickUp templates. Apply templates based on rules such as client, complexity, collection, or task status. Could you please confirm if Super Agents currently support this? If not, please consider this as a feature request for a future release.

It would be great to be able to use AI to quickly generate clean, and cool looking whiteboards. Currently the AI Brain in whiteboard only generates images, and they are all cut off. Instead, i'd like to ask it to "pull all tasks from this board as headers with unique colors, and put descriptions as sub sticky notes". That way I could create a quick org chart, or view of specific tasks quickly, efficiently, and in a cool looking way. On some other tools this involves importing .json and .csv data which most LLM/AI tech can work with. If I could simply copy and paste in such formats and choose my template look or describe it then it would save tons of time in the long run. No current workaround to generate formatted whiteboard material. I can almost get there by importing .csv or .json as tasks using import or AI Brain. Then I have to drag in each tasks. However, once I try to do any whiteboarding the AI just generates faulty images instead of editable structures in a useful format. Final goal, open whiteboard, ask AI to pull in tasks I've already got of a tag type from X project, tell it to build a color coded structure using bubbles at the top and stickies below it (or from template example), and presto it builds a structure. Example attached. I've use a different tool and AI to do this with prompts so it's very possible. Giving users a few preset prompts and styles would solidify this as useful for all sorts of purposes in the whiteboard tool.

The AI notetake lists the date in US format (MM/DD/YYY). It would be good to choose DD/MM/YYYY as most of the world uses that format over the US one.

For obvious reasons. When I try to connect Grok with Clickup, I see the attached window where filling workspace id as Client ID does not help. I see this JSON error when I try to connect Clickup APIs to Grok connectors { "error": "invalid_client", "error_description": "Invalid client_id" } Kindly resolve this issue.

Please expand Super Agent capabilities so it could gather reported time by date on which it have been allocated, not on when its reported. (For example - if employee reports time on specific task in different months (event if he/she reports in april time for march entries etc.)), So Agent could gather it in report.

AI-powered Gmail integration that scans my inbox, summarizes missed/important emails, and suggests action items or tasks to add to ClickUp—ideal for Education Foundations and users without Gemini.

Would be nice if we have a detailed breakdown of autopilot agents usage breakdown, similar to the Super Agents usage breakdown where you can see which ones are consuming alot of credits. Thank you

Our company previously used Fathom and you had the ability to click any of the key takeaways, next steps, key topics, and transcript and they would link directly to that part of the meeting recording with a time stamp. This feature is very useful and is something I would use daily. It is very hard to find a point in the meeting recording when I have no reference of what time it happened in the meeting based on the transcript. Thank you!