prompt-engineer SKILL.md skillA

prompt-engineer from aznatkoiny/zai-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add aznatkoiny/zai-skills/prompt-engineer@git:20261010.5b03da5

Pins git:20261010.5b03da5 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
aznatkoiny/zai-skills
Path
AI-Toolkit/skills/prompt-engineer/SKILL.md
Versions recorded
1
Latest version
git:20261010.5b03da5, committed Oct 10, 2026
Size
16,907 bytes
Repository stars
10
License
MIT

Write, review, debug, and migrate prompts for Claude models (Fable 5.1, Opus 5.5, Sonnet 5.5, Haiku 5.5) using Anthropic's official prompt engineering guidance. Covers system prompts, agent and harness prompts, tool descriptions, few-shot examples, and effort/thinking settings. Use this whenever the user wants to create or improve a prompt or system prompt. Also use it when they ask why Claude is behaving a certain way: too verbose or too terse, stops early or asks permission mid-task…

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 engineer

Help the user get the behavior they want from a Claude model by writing or changing the words, and sometimes the API settings, that the model sees. The guidance here comes from Anthropic's prompt engineering docs (fetched 2026-10-09). It is current for Claude Fable 5.1 / Mythos 5.1, Opus 5.5, Sonnet 5.5, and Haiku 5.5.

## Reference files

Read only what the task needs. The files are long, so grep for the section you want instead of reading top to bottom.

| File | Read when |
|---|---|
| `references/best-practices.md` | Any prompt work. General techniques for all current models, with many ready-to-use sample blocks: clarity, examples, XML, long context, formatting, prefill migration, tool use, parallel calls, thinking, agentic and long-horizon work, overeagerness, hallucination, frontend design. |
| `references/models/fable-5-1.md` | Target is Claude Fable 5.1 or Mythos 5.1 |
| `references/models/opus-5-5.md` | Target is Claude Opus 5.5 |
| `references/models/sonnet-5-5.md` | Target is Claude Sonnet 5.5 |
| `references/models/haiku-5-5.md` | Target is Claude Haiku 5.5 |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add aznatkoiny/zai-skills/prompt-engineer@sha256:ca12edda42647a17

The line at the top of this page pins the label git:20261010.5b03da5, 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_qzw4l6fqfmygd3jt.svg)](https://markdownregistry.com/a/art_qzw4l6fqfmygd3jt)

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

Versions

The registry has recorded 1 version of this file, committed on Oct 10, 2026.

versioncommittedcommitsizeaudit
git:20261010.5b03da5 latest2026-10-10 5b03da5 16,907 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 (16907 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

aznatkoiny/zai-skills · 10 stars · license MIT · pushed 2026-11-07 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_qzw4l6fqfmygd3jt
GET https://markdownregistry.com/api/v1/resolve?ref=aznatkoiny/zai-skills/prompt-engineer
GET https://markdownregistry.com/api/v1/blob/ca12edda42647a17d7ed703ac426293764a787c5ba0b3befeb7eee931d2beb7b

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 aznatkoiny/zai-skills

AGENTS.md AGENTS.md file
aznatkoiny/zai-skills · AGENTS.md
git:20261010.5c5cc81 · audit A · 10 stars
cpp-reinforcement-learning SKILL.md skill
aznatkoiny/zai-skills · AI-Toolkit/skills/cpp-reinforcement-learning/SKILL.md · Reinforcement learning in C++ with LibTorch (the PyTorch C++ frontend) and C++20. Use when the user is implementing…
git:20261010.5b03da5 · audit A · 10 stars
deep-learning SKILL.md skill
aznatkoiny/zai-skills · AI-Toolkit/skills/deep-learning/SKILL.md · Build and train neural networks with Keras 3 on any backend (JAX, TensorFlow or PyTorch). Use when the user is writing…
git:20261010.5b03da5 · audit A · 10 stars
openclaw-setup SKILL.md skill
aznatkoiny/zai-skills · AI-Toolkit/skills/openclaw-setup/SKILL.md · Install, configure, secure and troubleshoot OpenClaw (formerly Clawdbot / Moltbot), the self-hosted personal AI…
git:20261010.5b03da5 · audit B · 10 stars
reinforcement-learning SKILL.md skill
aznatkoiny/zai-skills · AI-Toolkit/skills/reinforcement-learning/SKILL.md · Reinforcement learning in Python with Gymnasium and Stable-Baselines3 (PPO, SAC, DQN, TD3, A2C). Use when the user is…
git:20261010.5b03da5 · audit A · 10 stars
x402-payments SKILL.md skill
aznatkoiny/zai-skills · AI-Toolkit/skills/x402-payments/SKILL.md · Build apps that charge for, or pay for, HTTP requests with the x402 protocol (HTTP 402 "Payment Required" plus…
git:20261010.5b03da5 · audit A · 10 stars
CLAUDE.md CLAUDE.md file
aznatkoiny/zai-skills · CLAUDE.md
git:20261010.edd6f9c · audit A · 10 stars
resume-updater SKILL.md skill
aznatkoiny/zai-skills · career-coach/skills/resume-updater/SKILL.md · Builds and maintains the user's career profile (career-profile.json), the record of experience, achievements, skills…
git:20261010.f1e19c5 · audit A · 10 stars
consulting-frameworks SKILL.md skill
aznatkoiny/zai-skills · consulting-toolkit/skills/consulting-frameworks/SKILL.md · How-to guidance for consulting frameworks: MECE problem structuring, issue trees, hypothesis-driven analysis, the…
git:20261010.01f5c85 · audit A · 10 stars
real-estate-investment SKILL.md skill
aznatkoiny/zai-skills · real-estate-investment/skills/real-estate-investment/SKILL.md · Real estate investment analysis for rental, multifamily, commercial and short-term rental property. Use when the user…
git:20261010.2218872 · audit A · 10 stars

Every file in aznatkoiny/zai-skills

Other files named prompt-engineer

prompt-engineer SKILL.md skill
jeffallan/claude-skills · skills/prompt-engineer/SKILL.md · Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas…
v1.2.0 · audit A · 12,261 stars
prompt-engineer SKILL.md skill
sipyourdrink-ltd/bernstein · templates/skills/prompt-engineer/SKILL.md · LLM prompts - design, evaluate, tune instructions.
git:20260521.b455a7c · audit A · 1,196 stars
prompt-engineer SKILL.md skill
bastani-inc/atomic · packages/workflows/skills/prompt-engineer/SKILL.md · Write, evaluate, migrate, or troubleshoot prompts for GPT and Claude models.
git:20261026.c93636e · audit A · 880 stars
prompt-engineer SKILL.md skill
rjmurillo/ai-agents · src/claude/skills/prompt-engineer/SKILL.md · Optimize system prompts for Claude Code agents using proven prompt engineering patterns. Use when users request prompt…
v1.0.0 · audit A · 49 stars
prompt-engineer SKILL.md skill
joe-qai/qa-skills · prompt-engineer/SKILL.md · Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas…
v1.1.0 · audit A · 30 stars
prompt-engineer SKILL.md skill
felvieira/claude-skills-fv · skills/26-prompt-engineer/SKILL.md · Projeta e avalia prompts reutilizaveis e suas saidas. Trigger em: "prompt engineer", "prompt engineering", "melhorar…
git:20261030.813a629 · audit A · 28 stars
prompt-engineer SKILL.md skill
phuhao00/bony-agent · .agent/skills/prompt-engineer/SKILL.md · 提示词优化专家,负责将简单的用户意图扩写为高保真的多模态模型(Midjourney/Stable Diffusion/Sora/CogVideo)标准长尾 Prompt。
git:20260617.47f66a5 · audit A · 19 stars
prompt-engineer SKILL.md skill
phuhao00/bony-agent · electron/resources/agent-skills/prompt-engineer/SKILL.md · 提示词优化专家,负责将简单的用户意图扩写为高保真的多模态模型(Midjourney/Stable Diffusion/Sora/CogVideo)标准长尾 Prompt。
git:20260617.47f66a5 · audit A · 19 stars

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