agentleFS
BhaskarManamBhaskarManam/pstack/skills/design-brief/SKILL.md

design-brief

Skill4 starsChanged 7 months agoMITView on GitHub

Produce a design brief from a PRD: user & job, primary flow (with error states), screen inventory, interaction principles, visual/voice constraints, accessibility. Writes 03-design-brief.md. Requires PRD score ≥ 2.5.

22 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use brief-to-tasks, design-flow and 7 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • julianoczkowskiSkill

    brief-to-tasks

    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".

    Also in 7 projects that use this

  • julianoczkowskiSkill

    design-flow

    Run the full design-to-build workflow as a guided sequence. Orchestrates all designer skills in order, from grilling through review. Use when user wants to go through the complete design process, start a project from scratch, run the full flow, or mentions "design flow" or "full workflow".

    Also in 6 projects that use this

  • 45ckSkill

    information-architecture

    Define the information architecture for a prototype -- sitemap, navigation model, grouping logic, labeling, and action placement.

    Also in 8 projects that use this

  • ilikescienceSkill

    design-tokens

    Expert in design tokens using the DTCG specification. Use this skill when users ask about design tokens, DTCG format, token validation, formatting, transformation, color spaces (sRGB, Display P3, OKLCH), references and aliasing, resolvers, theming with modifiers/contexts, multi-platform design systems, accessibility, or working with tools like jq, jsonata, and terrazzo. Helps with token file creation, resolver configuration, structure, naming conventions, and best practices.

    Also in 8 projects that use this

  • launchapp-devSkill

    color-system

    Build a comprehensive color system with palette generation, semantic mapping, and accessibility compliance.

    Also in 3 projects that use this

  • dillonluiSkill

    design-review

    Review a view or flow for UX and UI issues. Provides severity-ranked, actionable findings grounded in established design heuristics. Use when the user asks for design feedback, UX review, or UI critique.

    Also in 7 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

17 rules. 0 are common, 11 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 19 edited versions we read keep these.

  • 11

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If 02-prd.md does not exist: stop.

    line 18
  2. Very specific:

    If 02-prd.md exists but rubric_score is below 2.5: stop.

    line 19
  3. Very specific:

    Read pstack-workspace/{slug}/02-prd.md in full.

    line 25
  4. Very specific:

    Read pstack-workspace/{slug}/00-vision.md — especially the JTBD section.

    line 26
  5. Distinctive:

    Ask these four questions, one at a time:

    line 35
  6. Distinctive:

    If the user describes screens rather than decisions, redirect: *"What decision does the user make at each step?"*

    line 38
  7. Distinctive:

    Before drafting, read silently:

    line 50
  8. Distinctive:

    JTBD per screen: every screen's dominant element must be justified by the user's functional, emotional, or social job.

    line 60
  9. Distinctive:

    Primary flow: every step needs a user decision, both paths (happy + edge case), error state, and transition spec if animated.

    line 61
  10. Distinctive:

    Screen inventory: every screen in the flow plus empty states and modal overlays — each with purpose, dominant element, secondary elements, …

    line 62
  11. Very specific:

    Update state to BRIEF_DONE.

    line 90
  12. Very specific:

    Write ~/.config/pstack/last-session.md per knowledge/schemas/last-session.schema.md.

    line 96
  13. Distinctive:

    Ask once: *"One thing you'd change about this design brief?

    line 110
  14. Distinctive:

    Never start if PRD score is below 2.5 — enforce the quality gate

    line 124
  15. Distinctive:

    Every interaction principle must be product-specific and imply a concrete design decision — rewrite generic principles internally

    line 125
  16. Distinctive:

    Every color, type size, and accessibility spec must have a numeric value — "mobile-friendly" is not a constraint

    line 126
  17. Distinctive:

    Never omit error states from the primary flow — if the user didn't mention them, derive them from the stories in the PRD

    line 127

“Common” is measured: kept by at least 6 in 10 of the 19 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/design-brief

You are the pstack design brief generator. You translate a PRD into actionable design direction — specific enough that a designer can begin without a briefing call.


Step 1 — Dependency quality gate

Read pstack-workspace/{slug}/.pstack-meta.json.

  • If 02-prd.md does not exist: stop. "Run /prd first — /design-brief requires a PRD."
  • If 02-prd.md exists but rubric_score is below 2.5: stop. "The PRD scores {score}/5 — below the 2.5 floor. Refine it with /prd or run /critique first."

Step 2 — Read context and frameworks

  1. Read pstack-workspace/{slug}/02-prd.md in full.
  2. Read pstack-workspace/{slug}/00-vision.md — especially the JTBD section.
  3. Read knowledge/INDEX.md.
  4. Load: knowledge/frameworks/jtbd.md — apply it per-screen in Step 5.
  5. Read knowledge/rubrics/design-brief.yaml.

Step 3 — Interview (AskUserQuestion)

Ask these four questions, one at a time:

  1. "Walk me through the primary flow step by step — starting from where the user enters, ending where they achieve the goal. Don't describe screens yet — describe decisions and transitions."
    • If the user describes screens rather than decisions, redirect: "What decision does the user make at each step?"
  2. "What platform(s) and versions are we targeting? Be specific — iOS 16+, Android API 33+, web (Chrome 120+)?"
  3. "Any brand or voice constraints I should know? Color palette, typeface, tone of voice, things that are explicitly off-limits?"
  4. "What's your accessibility bar? WCAG AA minimum? Is Dark Mode required? Reduce Motion support?"

Step 4 — Read calibration set

Before drafting, read silently:

  • knowledge/calibration/design-brief-score-2.md — understand what failure looks like
  • knowledge/calibration/design-brief-score-5.md — internalize what excellence looks like

Step 5 — DRAFT (internal, invisible to user)

Using skills/design-brief/template.md as structure, draft 03-design-brief.md. Apply:

  • JTBD per screen: every screen's dominant element must be justified by the user's functional, emotional, or social job. Screen existence ≠ screen justification.
  • Primary flow: every step needs a user decision, both paths (happy + edge case), error state, and transition spec if animated.
  • Screen inventory: every screen in the flow plus empty states and modal overlays — each with purpose, dominant element, secondary elements, entry points, exit points.
  • Interaction principles: product-specific, not generic ("reduce cognitive load" is not a principle — "one decision per screen, nothing extra" is).
  • Visual constraints: specific values — hex codes for color, pt sizes for type, WCAG level for contrast. No vague adjectives ("clean", "modern").
  • Accessibility: WCAG level, touch targets in pt, VoiceOver label examples, Dynamic Type max size, Reduce Motion check, Dark Mode token mapping.
  • Copy tone: right/wrong example table — removes copy ambiguity for copy review.

Step 6 — SELF-CRITIQUE (internal, invisible to user)

Score the draft against each dimension in knowledge/rubrics/design-brief.yaml.

Compute weighted average.

If < 3.5: revise lowest-scoring dimension(s) once. Re-score.


Step 7 — Present the artifact

Present the final 03-design-brief.md in full. Ask: "Does this capture what you need for design? Anything to adjust before I save?"

Apply corrections. Save to pstack-workspace/{slug}/03-design-brief.md.


Step 8 — Update .pstack-meta.json

Update state to BRIEF_DONE. Add artifact entry with file, type (design-brief), version, rubric_score, and date.


Step 9 — Write last-session.md

Write ~/.config/pstack/last-session.md per knowledge/schemas/last-session.schema.md.

State is BRIEF_DONE. Suggest /cagan-review as primary next; /challenge as alternative.


Step 10 — Append quality-log.yaml

Append one entry to ~/.config/pstack/quality-log.yaml per knowledge/schemas/quality-log.schema.yaml.


Step 11 — Capture feedback

Ask once: "One thing you'd change about this design brief? Press Enter to skip."

Append to feedback/design-brief-log.yaml per knowledge/schemas/feedback-log.schema.yaml.


Step 12 — Suggest next

"Your design brief is saved. The loop is complete — Vision → Strategy → PRD → Design Brief. Next: /cagan-review to stress-test before engineering, or /challenge for a CEO/CPO-level provocation on the full arc."


Rules

  • Never start if PRD score is below 2.5 — enforce the quality gate
  • Every interaction principle must be product-specific and imply a concrete design decision — rewrite generic principles internally
  • Every color, type size, and accessibility spec must have a numeric value — "mobile-friendly" is not a constraint
  • Never omit error states from the primary flow — if the user didn't mention them, derive them from the stories in the PRD
  • Reduce Motion and Dark Mode are required fields — ask if the user hasn't specified

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.