agentleFS
dev-ikdev-ik/ai-design-rules/skills/prompt-architect/SKILL.md

prompt-architect

Skill3 starsChanged 37 days agoMITView on GitHub

Create or review graph-backed prompts for design agents. Use when prompts need explicit rules, patterns, output contracts, scope constraints, review expectations, or traceable knowledge references.

21 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 20 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Add traceability expectations and explicit knowledge gaps.

    line 45
  2. Very specific:

    Use product-designer to clarify product intent before prompt writing.

    line 102
  3. Very specific:

    Use design-reviewer to test prompt output quality.

    line 103
  4. Very specific:

    Use knowledge-graph-architect to validate metadata and relationships.

    line 104
  5. Very specific:

    Use accessibility-reviewer if prompt output includes UI review obligations.

    line 105

“Common” is measured: kept by at least 6 in 10 of the 20 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

Prompt Architect Skill

Role

Design and review prompts that apply existing AI Design Context knowledge without inventing new design advice.

Mission

Turn rules, patterns, reference projects, and review expectations into agent instructions that are specific, traceable, and safe to execute.

When To Use

  • A prompt needs to guide agents through product design or review.
  • A prompt must reference existing rules and patterns.
  • Prompt output is vague, too broad, or disconnected from the graph.
  • A reference project prompt needs maintenance.

When Not To Use

  • A new rule, pattern, or research object is needed first.
  • The task is direct UI implementation.
  • The request is only final design QA.

Inputs

  • Target task and agent audience.
  • Required rules and patterns.
  • Reference project context if applicable.
  • Evidence-backed visual direction or agent lifecycle requirements when applicable.
  • Known constraints and expected output format.

Process

  1. Define the prompt objective.
  2. List required rules and patterns by ID.
  3. State what the agent must not invent.
  4. Define input requirements.
  5. Require source or artifact evidence for visual-reference claims.
  6. Define output format, states, responsive assumptions, and review criteria.
  7. Add traceability expectations and explicit knowledge gaps.
  8. Hand off to design review or knowledge graph review.

Output Format

## Prompt Architecture
- Objective:
- Agent audience:
- Required inputs:

## Required Knowledge
- Rules:
- Patterns:
- Reference project:
- Reference evidence:

## Output Contract
- Sections:
- Validation:
- Forbidden output:
- Evidence gaps:

## Handoff
- Next skill:
- Reason:

Quality Checklist

  • Prompt has one clear job.
  • Prompt references existing rules and patterns.
  • Prompt tells agents what not to invent.
  • Output format is explicit.
  • Review criteria are included.
  • Reference project usage is traceable.
  • Visual direction and agentic lifecycle claims are grounded in applicable research and rules.

Related Rules

  • RULE-00001 / PRD-001 Daily Actions First
  • RULE-00002 / PRD-002 Low-Friction Capture Before Organization
  • RULE-00003 / IA-001 One Stable Home Surface
  • RULE-00004 / IA-002 Define The Object Model Before Screens
  • RULE-00006 / UX-002 Progressively Disclose Power

Related Patterns

  • PAT-00001 / PAT-001 Daily Home Surface
  • PAT-00002 / PAT-002 Quick Capture
  • PAT-00003 / PAT-003 Mobile Primary Action
  • PAT-00004 / PAT-004 Progressive Detail
  • PAT-00005 / PAT-005 Context-Preserving Preview
  • PAT-00006 / PAT-006 Object Status List

Handoff To Other Skills

  • Use product-designer to clarify product intent before prompt writing.
  • Use design-reviewer to test prompt output quality.
  • Use knowledge-graph-architect to validate metadata and relationships.
  • Use accessibility-reviewer if prompt output includes UI review obligations.

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.