Prompt Architect
Turn a vague request into a reliable, reusable prompt with role, context, task, constraints, and examples. Use when the user keeps re-rolling outputs to get something usable, or wants a repeatable prompt for a task they do often — in any field.
Install
npx skills add DylXBT/claude-orchestrator-skills --skill prompt-architectgit clone --depth 1 https://github.com/DylXBT/claude-orchestrator-skills.git /tmp/claude-orchestrator-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-orchestrator-skills/prompt-architect ~/.claude/skills/prompt-architectPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Prompt Architect
Most weak output isn't a weak model — it's a missing part. A reliable prompt has five: a **role**, **context**, one **task**, **constraints**, and an **example** of good. This skill builds that prompt with the user, then hands them a reusable version.
It is **role-agnostic**. Do not assume the user is a marketer, engineer, or anything else. Ask.
## Step 1 — Interview (always do this first)
Ask the user, briefly and conversationally (don't dump all five at once — ask, then react):
1. **Who should the assistant act as?** Their job/role and the kind of judgement it implies. ("HR business partner", "brand designer", "support lead".)
2. **What's the one task?** A single deliverable. If they name several, pick one and note the rest for later.
3. **What's the context?** Audience, goal, and any house style or rules. Offer to use an existing context pack if they have one (see the `context-brain` skill).
4. **What does "good" look like?** Ask for one or two real examples, or describe the bar.
5. **Constraints?** Length, format, tone, and what to avoid.
If the user is unsure on any answer, propose a sensible default for their stated role and confirm.
## Step 2 — Assemble
Write the prompt in five labelled parts, in this order:Details
- Skill name
prompt-architect- Repository
- DylXBT/claude-orchestrator-skills
- Path
prompt-architect/SKILL.md- License
- MIT
- Repo updated
- 2 June 2026
FAQ
What does the Prompt Architect skill do?
Turn a vague request into a reliable, reusable prompt with role, context, task, constraints, and examples. Use when the user keeps re-rolling outputs to get something usable, or wants a repeatable prompt for a task they do often — in any field.
How do I install the Prompt Architect skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add DylXBT/claude-orchestrator-skills --skill prompt-architect. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Prompt Architect popular?
It lives in DylXBT/claude-orchestrator-skills, which has 114 GitHub stars and 1 forks.
Related skills
Connector Setup
114DylXBT/claude-orchestrator-skills
Plan a safe, least-privilege way to connect the user's real tools (Drive, Slack, a task board, a calendar, etc.) to Claude so it works from live data instead of copy-paste. Use when wiring up connectors/MCP. Works for any stack and any role.
Context Brain
114DylXBT/claude-orchestrator-skills
Build a reusable context pack (a "brain") so Claude reasons from the user's role, audience, voice, and standards every time, instead of generic output. Use when setting up a Project/workspace, or when output is on-topic but off-voice. Works for any role or domain.
Orchestrator
114DylXBT/claude-orchestrator-skills
Assemble the user's context brain, skills, connectors, and pipelines into one system they actually run end-to-end — and document it so a teammate could run it too. The capstone meta-skill. Works for any role.
Agentation
79bamzc/claude-skills-frontend
Add Agentation visual feedback toolbar to any React project
Code Agent Orchestration (OCA)
49goldmar/openclaw-code-agent
Skill for orchestrating coding agent sessions from OpenClaw, including OCA requests such as "let oca do...", "ask oca to...", or "have oca handle...". Covers launching, monitoring, plan approval, lifecycle management, and worktree decisions.
Humanizer
70alexdcd/Mafia-Claude-Skills
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases. Credits: Original skill by @blader - https://github.com/blader/humanizer
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.