Back to skills
SkillHub ClubAnalyze Data & AIFull StackData / AI

prompt-engineer

Designs and optimizes system prompts for advisory AI and autonomous agent systems using a three-layer architecture (Foundation → Structure → Execution). Integrates evidence-graded techniques with production-proven patterns from Claude Code, Vercel v0, and Manus. Use when designing agentic systems with tool use, building advisory AI with confidence grading, optimizing existing prompts, diagnosing prompt failures, or building a spec to hand off to a prompt engineer. Includes a spec builder knowledge base and modular extensions for RAG grounding, domain calibration, and multi-agent orchestration. Trigger on: "system prompt", "agent", "agentic", "prompt engineering", "write a prompt", "improve my prompt", "AI advisor", "tool use prompt", "multi-agent", "build me a spec", "write a spec", "spec for", "tool specification", "system prompt build request".

Packaged view

This page reorganizes the original catalog entry around fit, installability, and workflow context first. The original raw source lives below.

Stars
3,131
Hot score
99
Updated
March 20, 2026
Overall rating
C0.0
Composite score
0.0
Best-practice grade
F37.6

Install command

npx @skill-hub/cli install openclaw-skills-prompt-engineer-agentic

Repository

openclaw/skills

Skill path: skills/iops/prompt-engineer-agentic

Designs and optimizes system prompts for advisory AI and autonomous agent systems using a three-layer architecture (Foundation → Structure → Execution). Integrates evidence-graded techniques with production-proven patterns from Claude Code, Vercel v0, and Manus. Use when designing agentic systems with tool use, building advisory AI with confidence grading, optimizing existing prompts, diagnosing prompt failures, or building a spec to hand off to a prompt engineer. Includes a spec builder knowledge base and modular extensions for RAG grounding, domain calibration, and multi-agent orchestration. Trigger on: "system prompt", "agent", "agentic", "prompt engineering", "write a prompt", "improve my prompt", "AI advisor", "tool use prompt", "multi-agent", "build me a spec", "write a spec", "spec for", "tool specification", "system prompt build request".

Open repository

Best for

Primary workflow: Analyze Data & AI.

Technical facets: Full Stack, Data / AI.

Target audience: Development teams looking for install-ready agent workflows..

License: Unknown.

Original source

Catalog source: SkillHub Club.

Repository owner: openclaw.

This is still a mirrored public skill entry. Review the repository before installing into production workflows.

What it helps with

  • Install prompt-engineer into Claude Code, Codex CLI, Gemini CLI, or OpenCode workflows
  • Review https://github.com/openclaw/skills before adding prompt-engineer to shared team environments
  • Use prompt-engineer for development workflows

Works across

Claude CodeCodex CLIGemini CLIOpenCode

Favorites: 0.

Sub-skills: 0.

Aggregator: No.

prompt-engineer | SkillHub