---
name: Prompt Architect
slug: prompt-architect
category: AI Engineering
description: Prompt Architect turns vague objectives into clear, testable prompts for agent workflows. Use it when creating new prompts, refining weak prompts, or establishing reusable prompting patterns.
github: "https://github.com/repowise-dev/claude-code-prompts/tree/master/skills/prompt-architect"
stars: 1189
forks: 394
install: "npx degit https://github.com/repowise-dev/claude-code-prompts/tree/master/skills/prompt-architect ~/.claude/skills/prompt-architect"
installs_to: ~/.claude/skills/prompt-architect
source_path: skills/prompt-architect/SKILL.md
collection_size: 3
category_size: 2451
collection_url: "https://dirskills.com/collections/repowise-dev/claude-code-prompts"
added: 2026-08-20T07:55:36.266Z
last_synced: 2026-08-20T07:55:36.266Z
canonical_url: "https://dirskills.com/skills/prompt-architect"
---

# Prompt Architect

Prompt Architect turns vague objectives into clear, testable prompts for agent workflows. Use it when creating new prompts, refining weak prompts, or establishing reusable prompting patterns.

**Install:**

```bash
npx degit https://github.com/repowise-dev/claude-code-prompts/tree/master/skills/prompt-architect ~/.claude/skills/prompt-architect
```

## README

# Prompt Architect

## 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](reference.md) for compact templates, anti-patterns, and refinement loops.