clickup-task-breakdown
Skill2 starsChanged 24 days agoMITView on GitHub
Turn scope documents (data model/UML, functional proposal, execution plan) into structured ClickUp tasks — modules as parent tasks, subtasks with "how to" descriptions, dependencies and CSV import. Use whenever you need to create tasks, break scope into activities, organize a backlog, plan a sprint or structure an execution plan in a project management tool.
In this repository28 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ai-newsSkill
- break-uiSkill
- ci-cd-and-automationSkill
- client-facing-docsSkill
- codebase-designSkill
- design-auditSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- express-prisma-patternSkill
- frontend-designSkill
- game-assetsSkill
- game-design-docSkill
- grillingSkill
- improve-codebase-architectureSkill
- motion-dictionarySkill
- playwright-cliSkill
- prisma-schema-conventionsSkill
- rag-architectSkill
- rbac-designSkill
- redesign-existing-projectsSkill
- screenshot-to-codeSkill
- secrets-gitleaksSkill
- security-auditSkill
- sentry-setup-ai-monitoringSkill
- tddSkill
- token-efficiencySkill
- web-design-guidelinesSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
If something isn't in any document, it doesn't become a task — it becomes a question for the tech lead.
- Distinctive: line 28
Assignee: when team allocation is already known
- Distinctive: line 50
No decorative Unicode characters (borders, emoji overload) — they break rendering in several places
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
From scope documents to ClickUp tasks
Process for converting a project's planning documents into an executable backlog, without inventing scope.
Rule number one: source of truth
Tasks are born exclusively from the project's source documents — typically three:
- Data model (UML/entity diagram)
- Functional proposal (what the system does, from the product view)
- Execution plan (modules, hours, sequence)
If something isn't in any document, it doesn't become a task — it becomes a question for the tech lead. Generating tasks from imagined scope is the most expensive mistake in this process.
Structure
- Parent task = module from the execution plan. One to one. If the plan has 7 modules, there are 7 parent tasks.
- Subtask = verifiable deliverable within the module (3–6 per module is normal). "Verifiable" = you can look at it and say whether it's done.
- Each subtask carries:
- Title: infinitive verb + object ("Implement task CRUD", "Set up CI pipeline")
- "How to" description: 3–8 lines grounded in the project's locked technical decisions — not a generic tutorial
- Estimate inherited/apportioned from the module's hours in the plan
- Assignee when team allocation is already known
Sequencing and dependencies
Build the dependency graph between modules BEFORE distributing work (e.g. Setup → Auth → domains in parallel → dashboards → QA). In ClickUp, use waiting on relations between parent tasks; within a module, the subtask order already expresses the sequence.
Deliver alongside it a half-page sequencing guide: the order, the why, and where the team can parallelize.
Import
For volume (20+ tasks), generate a CSV in ClickUp's Spreadsheet Importer format:
Task Name,Parent Task,Description,Time Estimate,Assignee
"Module A — Authentication and org structure",,"...",30h,
"Implement JWT login","Module A — Authentication and org structure","How to: ...",8h,JohnGotchas that have already caused rework:
Parent Taskreferences the exact name of the parent task (case-sensitive)- Descriptions containing commas/line breaks go inside double quotes
- Estimates in the format the importer accepts (
8h, not8 hours) - No decorative Unicode characters (borders, emoji overload) — they break rendering in several places
Quality checklist before delivering
- Every task traces back to a passage in a source document
- No module from the plan is missing a parent task
- Every subtask has a "how to" grounded in the project's decisions
- The sum of estimates matches the execution plan's hours (divergence = flag it, don't hide it)
- Sequencing guide delivered alongside
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

