How to Design Todoist Filters and Labels from a Role Description
Todoist setups bloat when a prompt dumps 30 starter tasks and a karma grind. You asked for filters and labels for one role. Query syntax is the deliverable. Gym and kids calendars stay out if you said they stay out.
The matching generator is the Todoist Filter and Label Scheme from a Role Description prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).
Use projects you already have
Design a Todoist filter and label scheme from a role description. No invented projects, karma scores, or tasks the role did not imply. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.
Paste these fields before you hit run:
Role title and company type: [Role]
Work hours and timezone: [Hours]
Projects I already have (or NONE): [Projects]
Priorities I actually use (p1-p4): [Priorities]
People I may mention: [People]
Tools I live in: [Tools]
Energy or context labels I want: [Contexts]
Words I must not use: [Banned]
How many filters max: [FilterCap]
What I refuse to track: [Refuse]
That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.
Cap the filter count
Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.
Walk the Generate list in order:
- Tool lock: Todoist 2026. Filter query syntax only. Not Notion. Not Outlook.
- Project list: only Projects. If NONE, propose at most 3 names clearly marked PROPOSED, not existing.
- Label taxonomy from Contexts, People, and Tools. No label for Refuse items.
- Filter queries (count <= FilterCap) with Todoist query syntax. Explain each in one line.
- Today vs upcoming vs waiting. Hours and timezone from Hours.
- Priority policy from Priorities only. Do not invent a p0.
- What not to put in Todoist: Refuse.
- Compliance pass: quote Banned words, invented karma, and extra people. Cut them.
If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.
Honor timezone and the refuse list
Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.
Honor the constraints as hard stops, not vibes:
- Todoist filter syntax (2026). Do not emit Things 3 or OmniFocus syntax.
- Never invent a karma score or completed-task count.
- Do not add collaborators not in People.
- Stay at or under FilterCap filters.
- Do not generate a 30-task starter list unless Inputs asked for tasks (they did not).
When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.
No karma score, no extra collaborators
Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.
Tags on the card (todoist filters labels, todoist role scheme, todoist no invented karma) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.
Fill the card, then run
Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.