prompt-engineering-patterns SKILL.md skillA

prompt-engineering-patterns from gastonchevarria/god-mode is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add gastonchevarria/god-mode/prompt-engineering-patterns@git:20260926.941aa31

Pins git:20260926.941aa31 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
gastonchevarria/god-mode
Path
plugins/god-mode-dev/skills/prompt-engineering-patterns/SKILL.md
Versions recorded
1
Latest version
git:20260926.941aa31, committed Sep 26, 2026
Size
1,554 bytes
Repository stars
3
License
MIT

Master prompt engineering strategies including chain-of-thought, few-shot demonstration calibration, strict JSON schema output constraints, system prompt modularity, and context window optimization.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Prompt Engineering Patterns

## Overview

Prompt engineering is the precision programming of foundation models. `prompt-engineering-patterns` provides systematic structures to eliminate hallucinations, enforce rigid JSON output formats, and minimize token overhead.

## Core Prompting Patterns

### 1. The Role-Context-Constraint-Format Structure
Structure prompts into 4 distinct semantic blocks:
```text
<role>
You are an expert financial analyst specializing in SaaS unit economics.
</role>

<context>
The user operates a B2B SaaS with $45k MRR and 120 paying accounts.
</context>

<instructions>
1. Calculate the ARPU and identify expansion revenue opportunities.
2. Highlight any metric exceeding standard churn benchmarks.
</instructions>

<constraints>
- Do NOT guess or hallucinate missing data; flag it explicitly.
- Output ONLY valid JSON matching the schema below.
</constraints>

<output_schema>
{ ... }
</output_schema>
```

### 2. Calibrated Few-Shot Demonstrations
- Provide 2-3 minimal, representative input/output pairs demonstrating the exact format, edge case handling, and tone desired.

### 3. XML Delimiters for Untrusted Content
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add gastonchevarria/god-mode/prompt-engineering-patterns@sha256:961c7bfa8be9543a

The line at the top of this page pins the label git:20260926.941aa31, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_3whv6yjlfqg3dm6m.svg)](https://markdownregistry.com/a/art_3whv6yjlfqg3dm6m)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Sep 26, 2026.

versioncommittedcommitsizeaudit
git:20260926.941aa31 latest2026-09-26 941aa31 1,554 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (1554 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

gastonchevarria/god-mode · 3 stars · license MIT · pushed 2026-10-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_3whv6yjlfqg3dm6m
GET https://markdownregistry.com/api/v1/resolve?ref=gastonchevarria/god-mode/prompt-engineering-patterns
GET https://markdownregistry.com/api/v1/blob/961c7bfa8be9543a5152f779292f3ec198070e8c3bd03591751b475a921fba50

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from gastonchevarria/god-mode

.cursorrules Cursor rule
gastonchevarria/god-mode · .cursorrules
git:20260925.62022e9 · audit A · 3 stars
AGENTS.md AGENTS.md file
gastonchevarria/god-mode · AGENTS.md
git:20261015.b72c1a6 · audit B · 3 stars
.cursorrules Cursor rule
gastonchevarria/god-mode · config/.cursorrules
git:20261015.b72c1a6 · audit A · 3 stars
AGENTS.md@config AGENTS.md file
gastonchevarria/god-mode · config/AGENTS.md
git:20261015.b72c1a6 · audit A · 3 stars
CLAUDE.md@config CLAUDE.md file
gastonchevarria/god-mode · config/CLAUDE.md
git:20261010.c9cc1c8 · audit A · 3 stars
ai-product-architect SKILL.md skill
gastonchevarria/god-mode · plugins/god-mode-core/skills/ai-product-architect/SKILL.md · Designs production LLM systems: model routing, latency, caching, RAG, schema-checked output, guardrails, evals. Use for…
git:20261014.522e28a · audit A · 3 stars
anti-slop SKILL.md skill
gastonchevarria/god-mode · plugins/god-mode-core/skills/anti-slop/SKILL.md · Cleans AI slop in TypeScript and JavaScript: lazy type assertions, 'as any', empty catches, low-evidence and slow…
git:20261014.522e28a · audit A · 3 stars
archify SKILL.md skill
gastonchevarria/god-mode · plugins/god-mode-core/skills/archify/SKILL.md · Builds validated architecture, sequence, data-flow and state diagrams as interactive HTML from text, Mermaid or code…
v2.17 · audit A · 3 stars
auto-compact SKILL.md skill
gastonchevarria/god-mode · plugins/god-mode-core/skills/auto-compact/SKILL.md · Detects context bloat and, with your OK, compacts the session with a structured summary. Use for 'the session feels…
git:20261014.522e28a · audit A · 3 stars
code-simplification SKILL.md skill
gastonchevarria/god-mode · plugins/god-mode-core/skills/code-simplification/SKILL.md · Simplifies working code for clarity without changing behavior. Use when code is harder to read, maintain or extend than…
git:20261014.522e28a · audit A · 3 stars
context-engineering SKILL.md skill
gastonchevarria/god-mode · plugins/god-mode-core/skills/context-engineering/SKILL.md · Sets up agent context: rules files, CLAUDE.md, what to load per task. Use when starting a project or session, switching…
git:20261014.522e28a · audit A · 3 stars
debugging-and-error-recovery SKILL.md skill
gastonchevarria/god-mode · plugins/god-mode-core/skills/debugging-and-error-recovery/SKILL.md · Finds the root cause of a failure systematically instead of guessing. Use when tests fail, builds break, behavior…
git:20261014.522e28a · audit A · 3 stars

Every file in gastonchevarria/god-mode

Other files named prompt-engineering-patterns

prompt-engineering-patterns SKILL.md skill
wshobson/agents · plugins/llm-application-dev/skills/prompt-engineering-patterns/SKILL.md · This skill should be used when the user asks to "optimize a prompt", "improve prompt performance", "design a prompt…
git:20260707.511f834 · audit A · 41,220 stars
prompt-engineering-patterns SKILL.md skill
dicklesworthstone/pi_agent_rust · tests/ext_conformance/artifacts/agents-wshobson/llm-application-dev/skills/prompt-engineering-patterns/SKILL.md · Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in…
git:20260205.788be98 · audit A · 1,915 stars
prompt-engineering-patterns SKILL.md skill
asymmetric-al/core · .agents/skills/prompt-engineering-patterns/SKILL.md · Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in…
git:20261001.4ae104e · audit A · 379 stars
prompt-engineering-patterns SKILL.md skill
hermeticormus/libreuiux-claude-code · plugins/llm-application-dev/skills/prompt-engineering-patterns/SKILL.md · Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in…
git:20251120.288a379 · audit A · 118 stars
prompt-engineering-patterns SKILL.md skill
hermeticormus/claude-code-game-development · plugins/llm-application-dev/skills/prompt-engineering-patterns/SKILL.md · Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in…
git:20251120.50bf83d · audit A · 72 stars
prompt-engineering-patterns SKILL.md skill
rudycity/superagent · .agents/skills/prompt-engineering-patterns/SKILL.md · This skill should be used when the user asks to "optimize a prompt", "improve prompt performance", "design a prompt…
git:20260626.019dba9 · audit A · 52 stars

Browse by kind, by grade A, or by owner.