SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-17 UTC

No new commits yet today

Open the update feed

image-prompt-reverseLunarXuan/image-prompt-reverse

Reverse-engineers a reference image into reusable, high-quality AI art prompts, solving the problem of seeing a great im…

No ratings yet Rate this skill
Stars470
Forks37
Watchers470
Open Issues1

InstallOne-line install

Installable

This repository follows the Agent Skills spec, so one command installs it into your AI client — works across Claude Code, Codex, Cursor, Copilot, Windsurf, and 18+ other clients.

npx skills@latest add LunarXuan/image-prompt-reverse

Add -g install globally (available in every project) · add --agent claude-code to target a client · add --yes to skip the prompts. Restart your AI client afterward and it will pick it up.

OverviewOverview

Key Features

Reverse-engineers a reference image into reusable, high-quality AI art prompts, solving the problem of seeing a great image but being unable to write its prompt. Key capabilities include: 1. Image element decomposition: identifies subject, composition, camera angle, lighting, color and material layer by layer, outputting a structured list of visual elements; 2. Prompt reconstruction: converts the decomposition into English prompts matching the target model's syntax, including style terms, quality terms and negative prompts; 3. High-fidelity replication: packaged as a callable skill following the Codex skill spec, letting an agent reverse-engineer images directly in conversation and produce prompt sets that reproduce the original image's effect.

Use Cases

Reverse-engineering prompts from reference images, replicating AI art styles, tuning Midjourney/Stable Diffusion outputs, deconstructing competitor visual styles, converting design mockups into prompts.

Target Roles

AI / Algorithm Engineer, UI/UX / Visual Designer, Content Creator / Social Media Operator, Product Manager (PM).

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID605
Data sourceGitHub
RepositoryLunarXuan/image-prompt-reverse
CategoryAI & Agent Tools / Prompt Engineering & Image Generation
Primary languageOther
LicenseGNU General Public License v3.0
Default branchmain
GitHub repository ID1353853430
Node IDR_kgDOULIp9g
Rank#1332 (position within the source ranking)
Site-wide popularity rank#1511 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

02004006002026-09-302026-10-112026-09-30 · 4542026-10-11 · 470
  • Now470
  • Previous point · 09-30 454
  • vs previous point +16
  • 2 data points 11 days
0102030402026-09-302026-10-112026-09-30 · 342026-10-11 · 37
  • Now37
  • Previous point · 09-30 34
  • vs previous point +3
  • 2 data points 11 days

TimelineTimeline

Repository created2026-09-01 17:36:222 months ago
Data last updated2026-10-26 12:12:3721 days ago
Last commit2026-09-06 07:16:552 months ago

CommitLatest commit

Version [latest] committed by LunarXuan. Update Category: Codebase Iteration & Routine Maintenance. Commit details: Update LICENSE. This update updates core functional modules and advances project iteration.

4dead0a vlatest LunarXuan 2026-09-06

Next stepsNext steps