work-breakdown
Skill0 starsChanged yesterdayMITView on GitHub
Break a project into deliverables and tasks small enough to estimate and assign (a work breakdown structure), estimate each task with optimistic, likely and pessimistic durations, and spot dependencies, in a table that pastes into a spreadsheet or a to-do app. Use when a project feels too big to start, when someone asks for a task list or a plan, or before building a schedule. Triggers: "task list", "break down the project", "WBS", "to-do list for my project", "estimate", "liste des tâches", "découper le projet", "estimer les tâches", "lista de tareas", "desglosar el proyecto", "estimar tareas".
5 other projects use a version of this.
Adopted by
Most recently taken up by
- HACK-WU/skillstheir own version, first seen Sep 25, 2026
- dataGriff/skillstheir own version, first seen Sep 9, 2026
- khuynh22/agent-dev-teamtheir own version, first seen Aug 31, 2026
- tarikhamilton/claude-skillstheir own version, first seen Jul 1, 2026
- Docat0209/SoloForgetheir own version, first seen Apr 4, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- khuynh22/agent-dev-team★ 9same name
- HACK-WU/skills★ 2same name
- Docat0209/SoloForge★ 1same name
- dataGriff/skills★ 0same name
- tarikhamilton/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- decision-makingSkill
- delegation-briefSkill
- meeting-toolkitSkill
- project-budgetSkill
- project-charterSkill
- project-recoverySkill
- project-scheduleSkill
- responsibility-matrixSkill
- retrospectiveSkill
- risk-registerSkill
- scope-changeSkill
- stakeholder-mapSkill
- status-updateSkill
- vendor-selectionSkill
- weekly-reviewSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
After project-charter, before project-schedule.
- Distinctive: line 21
When a project feels too big or vague to start.
- Very specific: line 22
Not for daily to-do management: use weekly-review.
- Distinctive: line 51
Every task has one owner, a clear "done" and a three-point estimate.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Work breakdown
A project becomes manageable once it is cut into pieces that someone can finish in a few days. This skill builds that list, estimates it honestly and shows what depends on what.
When to use
- After
project-charter, beforeproject-schedule. - When a project feels too big or vague to start.
- Not for daily to-do management: use
weekly-review.
Inputs
- The goal, scope and deliverables (from
project-charter). - Who can work on it, and how much time each person has.
- Anything already done.
Method
- Start from the deliverables, not from activities: what will exist at the end (a painted room, a signed contract, a migrated database).
- Break each deliverable down until each task takes between a few hours and a few days, has a clear "done" and can be given to one person. Group tasks under their deliverable (a work breakdown structure).
- Check for forgotten work: buying, waiting for deliveries, permits and paperwork, cleaning up, testing, telling people, training.
- Estimate with three numbers: optimistic, most likely, pessimistic. The PERT average (optimistic + 4 × most likely + pessimistic) ÷ 6 gives a planning value, and the spread shows the uncertainty.
- Mark the dependencies: what cannot start before something else is finished, and waiting times that cost no effort but take calendar time (drying, delivery, approval).
- Assign an owner to each task (one name, not a team).
- Export the table so that it pastes into a spreadsheet or a task app, then go to
project-schedule.
Output
### Work breakdown: <project>
| ID | Deliverable | Task | Done when | Owner | Optimistic | Likely | Pessimistic | PERT | Depends on |
|---|---|---|---|---|---|---|---|---|---|
| 1.1 | … | … | … | … | 1 d | 2 d | 4 d | 2.2 d | – |Quality bar
- Every task has one owner, a clear "done" and a three-point estimate.
- Waiting times, paperwork, testing and communication are in the list.
- The PERT values are computed, not guessed, and estimates come from the people who will do the work when possible.
- Written in the user's language, with the terms below.
Terminology
| English | Français | Español |
| Work breakdown structure (WBS) | Organigramme des tâches (WBS) | Estructura de desglose del trabajo (EDT) |
| Task | Tâche | Tarea |
| Dependency | Dépendance | Dependencia |
| Estimate | Estimation | Estimación |
| Three-point estimate | Estimation à trois points | Estimación de tres puntos |
| Owner | Responsable | Responsable |
Sources
- Project Management Institute. (2021). A Guide to the Project Management Body of Knowledge (PMBOK Guide) (7th ed.). Project Management Institute.
- Malcolm, D. G., Roseboom, J. H., Clark, C. E., & Fazar, W. (1959). Application of a technique for research and development program evaluation. Operations Research, 7(5), 646–669.
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.

