Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

brief-to-tasks

skill · julianoczkowski/designer-skillsApache-2.0 licenceAudited 20 Oct 2026 · source 80a50dfcaf5a

★ 590pushed 105 days ago
✓SAFEGrade B · 89/100 · 20 Oct 2026 · 80a50df
590repo stars · whole julianoczkowski/designer-skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 80a50dfcaf5a and found no filesystem, network or shell access and no hard-coded secrets. What it does: Break a design brief into an ordered checklist of independently buildable tasks using vertical slices. Saves as a markdown checklist. Use when user wants to break down work, create tasks from a brief, plan…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “brief-to-tasks (julianoczkowski/designer-skills)”. Retrieved 20 Oct 2026. https://modelsatlas.com/skills/julianoczkowski/brief-to-tasks

Trust audit

Audit 0.4.1 · source read 20 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha 80a50dfcaf5a · 20 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherjulianoczkowski GitHub userOwner of the repository this skill is read from
  • Source folderjulianoczkowski/designer-skills/brief-to-tasksThe exact folder we audited
  • LicenceApache-2.0As the repository states it
  • Commit pinned for this verdict80a50dfcaf5aA new audit runs when the source changes
  • Repository statusNot archivedLast push 105 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Break a design brief into an ordered checklist of independently buildable tasks using vertical slices. Saves as a markdown checklist. Use when user wants to break down work, create tasks from a brief, plan…

---
name: brief-to-tasks
description: Break a design brief into an ordered checklist of independently buildable tasks using vertical slices. Saves as a markdown checklist. Use when user wants to break down work, create tasks from a brief, plan implementation order, or mentions "tasks" or "breakdown".
---

This skill turns a design brief into an ordered, buildable task list. Each task is a vertical slice: a piece of UI that can be built, reviewed, and verified on its own.

## Example prompts

- "Break the brief into tasks"
- "What should I build first?"
- "Create a task list from the design brief"
- "Plan the build order for this feature"

## Process

1. Read the design brief. Look for `.design/*/DESIGN_BRIEF.md`. If multiple subfolders exist, use the most recently modified one, or ask the user which feature they are working on. Also check for `INFORMATION_ARCHITECTURE.md` and a tokens file in the same subfolder. If none exist, ask the user to describe what they are building.

2. Explore the existing codebase to understand what is already built. Scan specifically for:
   - **Component directories**: `components/`, `ui/`, `shared/` and list every component by name
   - **Existing pages/views**: what is already built that this feature must coexist with
   - **Token/theme files**: `tokens.css`, `globals.css`, Tailwind config, theme providers
   - **File naming conventions**: kebab-case, PascalCase, how files are organized (by feature, by type)
   - **Test files**: if tests exist alongside components, new tasks should include test expectations
   - **Package.json dependencies**: what UI libraries, animation libraries, and icon sets are already installed
   - Classify each relevant component as: will be reused as-is, needs modification, or does not exist yet. Only components that need modification or creation get their own tasks.

3. Break the work into vertical slices. Each task should:
   - Be independently buildable (no task should block another unless noted).
   - Include structure, styling, and interaction in a single task (not "build HTML" then "add CSS" then "add JS" as separate tasks).
   - Be verifiable: you can look at the result and confirm it matches the brief.
   - Be small enough to complete in a single session.

4. Order tasks by:
   - **Dependencies first**: foundational elements (tokens, layout shells, shared components) before page-specific work.
   - **Visual priority**: the most prominent UI element early, so the user can validate the aesthetic direction before investing in details.
   - **Risk first**: the hardest or most uncertain piece early, so problems surface before everything else is built around them.

5. Save the task list as `TASKS.md` in the same `.design/<feature-slug>/` subfolder as the design brief.

## Task List Template

```markdown
# Build Tasks: [Feature/Page Name]

Generated from: .design/<feature-slug>/DESIGN_BRIEF.md
Date: [date]

## Foundation
- [ ] **[Task name]**: [One sentence describing what to build and what "done" looks like]. _Reuses: [existing components/tokens if any]._
- [ ] **[Task name]**: [Description]. _New component._

## Core UI
- [ ] **[Task name]**: [Description]. _Depends on: [task name if any]._
- [ ] **[Task name]**: [Description].

## Interactions & States
- [ ] **[Task name]**: [Description]. Covers: [list of states, e.g., hover, loading, error, empty].
- [ ] **[Task name]**: [Description].

## Responsive & Polish
- [ ] **[Task name]**: [Description]. Breakpoints: [which ones].
- [ ] **[Task name]**: Accessibility pass. [Specific checks from the brief].

## Review
- [ ] **Design review**: Run /design-review against the brief.
```

## Rules

- Every task must reference whether it reuses, modifies, or creates components.
- Never create a task that is only "set up the project" or "create the file structure." Those are not vertical slices.
- If the brief specifies an aesthetic philosophy, note it in the first build task so the visual direction is established immediately.
- Group related tasks but do not nest them more than one level deep. Flat lists are easier to work through.

Excerpt, first 4,106 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 80a50df

Download folder ↗
git clone https://github.com/julianoczkowski/designer-skills
git -C designer-skills checkout 80a50dfcaf5a

The author documents no install command, so this uses the repository directly. Our verdict covers commit 80a50dfcaf5a only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 80a50dfcaf5a

Similar skills

Questions about brief-to-tasks

What does the brief-to-tasks skill do?
A collection of agent skills for designers who prototype and build with AI coding tools. These skills encode design process so AI follows a structured path instead of producing random output.
Is brief-to-tasks safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can brief-to-tasks access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (80a50dfcaf5a), read on 2026-10-20. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.