Prompt Architect

SkillAI & models

Designs clear, testable prompts for agent workflows. Use when creating new prompts, refining weak prompts, or establishing reusable prompting patterns.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Prompt Architect skill

What this skill tells your AI

The instructions your AI receives, as published by repowise-dev/claude-code-prompts in skills/prompt-architect/SKILL.md and read by ahel’s review.

Purpose

Use this skill to turn vague intent into reliable prompt instructions.

Build Sequence

  1. Define objective, audience, and success criteria.
  2. Capture hard constraints (format, tools, safety, style).
  3. Specify required reasoning boundaries and output structure.
  4. Add verification instructions and failure handling.
  5. Iterate using concrete examples and observed errors.

Prompt Quality Checks

  • Is the task scope explicit and bounded?
  • Are required outputs unambiguous?
  • Are constraints actionable (not aspirational)?
  • Is there a clear fallback when information is missing?

Reference

Use reference.md for compact templates, anti-patterns, and refinement loops.

Signals

GitHub stars
1k
Forks
395
Last commit
May 2026
Advanced
Catalog kind
skill
Gateway key
prompt-architect-repowise-dev
Source
github.com/repowise-dev/claude-code-prompts