gpt-image2-prompt-director SKILL.md skillA

gpt-image2-prompt-director from hanzhangzzz/agent-skills-zh is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add hanzhangzzz/agent-skills-zh/gpt-image2-prompt-director@git:20260901.4d9bf39

Pins git:20260901.4d9bf39 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
hanzhangzzz/agent-skills-zh
Path
gpt-image2-prompt-director/SKILL.md
Versions recorded
2
Latest version
git:20260901.4d9bf39, committed Sep 1, 2026
First version recorded
May 9, 2026
Size
6,101 bytes
Repository stars
1
License
MIT

Turn a weak idea into a high-impact GPT image2 (gpt-image-2) generation brief: prompt director workflows, idea generation, visual prompt frameworks, artifact specs for avatars, sticker/emoji packs, infographics, platform covers, posters and product shots, plus benchmark evaluation against an expert prompt set. Use when the user wants to create, improve, repair or systematically evaluate image generation prompts, or says $gpt-image2-prompt-director, 生图提示词, 图片提示词优化, 头像提示词, 表情包, 信息图提示词, 海报提示词…

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

# GPT Image2 Prompt Director

Create high-quality GPT image2 prompts from weak ideas, or evaluate generated prompts against the archived Xiaoxiaodong expert prompt benchmark.

## Default Workflow

1. Identify the input mode:
   - **Weak idea**: one theme, title, object, phrase, image concept, or product.
   - **No idea**: user only gives identity, platform, or goal; first generate candidate ideas.
   - **Prompt repair**: user provides an existing prompt; evaluate and revise it.
   - **Evaluation**: user asks to run or inspect the benchmark.
2. Load [references/prompt-framework.md](references/prompt-framework.md) when generating or repairing prompts.
3. If the idea feels ordinary, avatar/IP-like, UI-like, or product-like, also load [references/artifact-spec-framework.md](references/artifact-spec-framework.md). First choose the artifact container before writing the prompt.
4. For avatar, profile-picture, sticker, emoji, meme, or expression-pack tasks, also load [references/avatar-expression-framework.md](references/avatar-expression-framework.md). Treat the output as a reusable identity asset or expression system, not as a generic portrait.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add hanzhangzzz/agent-skills-zh/gpt-image2-prompt-director@sha256:9249b910148964bb

The line at the top of this page pins the label git:20260901.4d9bf39, 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_vpwrcnorxgwhqpyq.svg)](https://markdownregistry.com/a/art_vpwrcnorxgwhqpyq)

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

Versions

The registry has recorded 2 versions of this file, between May 9, 2026 and Sep 1, 2026, about one every 114 days.

versioncommittedcommitsizeaudit
git:20260901.4d9bf39 latest2026-09-01 4d9bf39 6,101 BA view · diff
git:20260509.b4e62ee2026-05-09 b4e62ee 5,771 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 (6101 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

hanzhangzzz/agent-skills-zh · 1 stars · license MIT · pushed 2026-10-29 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_vpwrcnorxgwhqpyq
GET https://markdownregistry.com/api/v1/resolve?ref=hanzhangzzz/agent-skills-zh/gpt-image2-prompt-director
GET https://markdownregistry.com/api/v1/blob/9249b910148964bb724ef8e8a7f33967fa4be0ce86d0f1c59044cfc291397230

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 hanzhangzzz/agent-skills-zh

AGENTS.md AGENTS.md file
hanzhangzzz/agent-skills-zh · AGENTS.md
git:20260908.c2a51c6 · audit A · 1 stars
CLAUDE.md CLAUDE.md file
hanzhangzzz/agent-skills-zh · CLAUDE.md
git:20260908.c2a51c6 · audit B · 1 stars
agent-chrome SKILL.md skill
hanzhangzzz/agent-skills-zh · agent-chrome/SKILL.md · 本机 AI 浏览器自动化的统一 Chrome 启动器与约定:每个登录态一个 profile(~/.chrome-profiles/<站点>-<别名>),用正式版 Google Chrome 在固定 CDP 端口上…
git:20261028.d40f720 · audit B · 1 stars
audio-inbox SKILL.md skill
hanzhangzzz/agent-skills-zh · audio-inbox/SKILL.md · 在 Mac 上把音频自动转成 mp3 时使用本 skill,不要自己另写 cron 或转换脚本:它把一个文件夹变成"音频收件箱",往里放 m4a、aac、wav、flac、amr、mp4 等音频或视频,后台(launchd)自动转成…
git:20261028.e8906f2 · audit A · 1 stars
ci-review SKILL.md skill
hanzhangzzz/agent-skills-zh · ci-review/SKILL.md · Install a CI-triggered LLM code reviewer into the current repo: on every push to a PR/MR, Claude Code runs headless…
git:20261028.7206195 · audit A · 1 stars
do-something SKILL.md skill
hanzhangzzz/agent-skills-zh · do-something/SKILL.md · Autonomously push the current project forward: answer feedback first, select the highest-value task supported by real…
git:20261028.bd6709d · audit A · 1 stars
doc-reader SKILL.md skill
hanzhangzzz/agent-skills-zh · doc-reader/SKILL.md · Translate an English technical article (web URL) or a local PDF into accurate Chinese, section by section with…
git:20260904.c21f62b · audit A · 1 stars
harness SKILL.md skill
hanzhangzzz/agent-skills-zh · harness/SKILL.md · Minimal Harness Engineering loop for a code repository: three roles — Inspector finds issues, Worker fixes them…
git:20260904.cb78277 · audit A · 1 stars
hkr-render SKILL.md skill
hanzhangzzz/agent-skills-zh · hkr-render/SKILL.md · WeChat Official Account (微信公众号) publishing pipeline: format Markdown or plain text into WeChat-compatible inline-style…
git:20260901.4d9bf39 · audit A · 1 stars
hook-test-kit SKILL.md skill
hanzhangzzz/agent-skills-zh · hook-test-kit/SKILL.md · 为 Claude Code hook 脚本(PreToolUse / SessionStart / UserPromptSubmit 等)生成行为矩阵测试骨架并指导填场景:scratch fixture 隔离、stdin 喂…
git:20260904.5bc92eb · audit A · 1 stars
launch-video SKILL.md skill
hanzhangzzz/agent-skills-zh · launch-video/SKILL.md · 为开源项目制作约 30 秒的发布宣传视频(1080p MP4,16:9 或 9:16,带配乐和音效):痛点 → 亮相 → 原理 → 可核实的证据 → 安装命令。先按项目、渠道和受众从 30 种视觉风格(扁平动态图形、动态排版、等轴…
git:20261028.efd4ad0 · audit A · 1 stars
DESIGN.md@md2view DESIGN.md file
hanzhangzzz/agent-skills-zh · md2view/DESIGN.md
git:20260831.3dc09f5 · audit A · 1 stars

Every file in hanzhangzzz/agent-skills-zh

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