brief-to-tasks
Skill32 starsChanged 49 days agoMITView on GitHub
Break a design brief into executable time-boxed tasks, each with a done-when line. Use immediately before a build session.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- drinkspiller/skillstheir own version, first seen Nov 6, 2026
- taro1037-design/claude-skillstheir own version, first seen Oct 20, 2026
- hakushiidev/claude-skillstheir own version, first seen Oct 15, 2026
- DanielNoamTuby/claude-skillstheir own version, first seen Sep 20, 2026
- Nihalgraphics/AI-Product-OS-for-UI-UX-Brand-Prototypetheir own version, first seen Jun 11, 2026
- julianoczkowski/designer-skillstheir own version, first seen Mar 28, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- julianoczkowski/designer-skills★ 536same name
- Nihalgraphics/AI-Product-OS-for-UI-UX-Brand-Prototype★ 2same name
- drinkspiller/skills★ 1same name
- DanielNoamTuby/claude-skills★ 0same name
- hakushiidev/claude-skills★ 0same name
- taro1037-design/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 repository13 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- application-packSkill
- design-briefSkill
- design-reviewSkill
- design-tokensSkill
- frontend-designSkill
- grill-meSkill
- heuristic-evaluationSkill
- information-architectureSkill
- persona-acid-testSkill
- pick-upSkill
- stuckSkill
- wrap-upSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Start by reading the design brief and the information architecture document if they exist.
“Common” is measured: kept by at least 6 in 10 of the 6 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
You are breaking a design brief into executable work. Vague tasks produce vague output. Every task here must be completable by one person in one focused session.
Start by reading the design brief and the information architecture document if they exist. If neither exists, ask the user to complete /design-brief and /information-architecture first. Tasks cannot be accurate without this foundation.
Produce a task list with these four phases:
Phase 1: Foundation Tasks that must happen before screens can be built. Includes: design tokens (if not done), setting up the file structure, confirming the component library, documenting any existing patterns being reused.
Phase 2: Structure IA and wireframe tasks. Each screen in the inventory gets a wireframe task. Navigation flows get their own task. These are low-fidelity; the goal is structure, not polish.
Phase 3: Build High-fidelity screen and component tasks. One task per major screen or component. Include variant tasks separately (error state, empty state, responsive layout).
Phase 4: Review Critique, accessibility check, edge case review. These are not optional phases; list them as real tasks with time estimates.
For each task, include:
- A clear title starting with a verb (Design, Write, Build, Review, Define)
- A "done when" definition: the specific condition that marks this task complete
- Dependencies: which prior tasks must be complete before this one starts
Format as a markdown checklist. Show dependencies inline as "(requires: Task X)". Order tasks within each phase by dependency, not by importance. A task with no dependencies can run in parallel with others; call that out explicitly.
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.

