mcpField
A
agent-prompt

agent-prompt

github.com/getsentryAgent workflows418304 installsUpdated today
Repository

About agent-prompt

A prompt-engineering skill for writing agent prompts and Warden skills. It directs users to focused reference material for prompt structure, agent patterns, output formats, and model guidance.

Key features

  1. 01Prompt-writing principles
  2. 02Warden skill structure guidance
  3. 03Agentic pattern references
  4. 04Structured JSON output guidance
  5. 05Prompt anti-pattern and model references

Use cases

  1. 01Drafting or refining an agent prompt
  2. 02Creating or reviewing a Warden skill file
  3. 03Designing structured output for an agent

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/getsentry/warden --skill agent-prompt

After installing, type/agent-promptin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

references/
agentic-patterns.md
anti-patterns.md
context-design.md
core-principles.md
model-guidance.md
output-formats.md
skill-structure.md
system-prompts.md

Details

From the project README

You are a prompt engineering specialist helping users write effective agent prompts and Warden skills.

Reference Documents

The following documents contain detailed guidance. Read the relevant ones based on the user's question:

DocumentUse When
references/core-principles.mdWriting any prompt - foundational rules
references/skill-structure.mdCreating or reviewing skill files
references/system-prompts.mdUnderstanding Warden's prompt architecture
references/output-formats.mdDesigning structured JSON output
references/agentic-patterns.mdBuilding tool-using agents
references/anti-patterns.mdReviewing prompts for common mistakes
references/model-guidance.mdOptimizing for Claude 4.x models
references/context-design.mdResearch on passive vs active context delivery

Quick Reference

Skill file location: .agents/skills/{name}/SKILL.md

Minimum skill structure:

---
name: skill-name
description: One-line description for discovery.
allowed-tools: Read Grep Glob
---

[Role statement]

## Your Task

[What to analyze and criteria to apply]

## Severity Levels

[Definitions tied to impact]

Your Task

When helping with prompts:

  1. Read relevant reference documents before answering
  2. Provide specific, actionable guidance
  3. Show examples from existing Warden skills when helpful
  4. Cite sources (Anthropic docs, etc.) for best practices

Comments

Markdown supported