photo-abstract-editorial

Name: photo-abstract-editorial
Author: kwhi6693-web

Verified

Turn photos into source-faithful editorial artworks with an Agent Skill — adaptive layouts, controlled abstraction, and a Strict Fidelity composition path.

96stars

4forks

Python

Installation

# Add to your Claude Code skills
git clone https://github.com/kwhi6693-web/photo-abstract-editorial

Getting Started

Guides for using ai agents skills like photo-abstract-editorial.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

SKILL.md

Security ReportVerified

Last scanned: 8/27/2026

{
  "issues": [],
  "status": "PASSED",
  "scannedAt": "2026-08-27T15:02:56.221Z",
  "npmAuditRan": true,
  "pipAuditRan": true,
  "promptInjectionRan": true
}

Compare with similar skills

See how photo-abstract-editorial compares with popular alternatives.

photo-abstract-editorial vs hermes agent

See comparison

photo-abstract-editorial vs anthropics skills

See comparison

README.md

Frequently Asked Questions

What is photo-abstract-editorial?

photo-abstract-editorial is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by kwhi6693-web. Turn photos into source-faithful editorial artworks with an Agent Skill — adaptive layouts, controlled abstraction, and a Strict Fidelity composition path. It has 96 GitHub stars.

Is photo-abstract-editorial safe to use?

Yes. photo-abstract-editorial passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install photo-abstract-editorial?

Clone the repository with "git clone https://github.com/kwhi6693-web/photo-abstract-editorial" and add it to your Claude Code skills directory (see the Installation section above). photo-abstract-editorial ships a SKILL.md manifest, so compatible agents can discover and load it automatically.

What programming language is photo-abstract-editorial written in?

photo-abstract-editorial is primarily written in Python. It is open-source under kwhi6693-web on GitHub, so you can review or fork the full source.

Are there alternatives to photo-abstract-editorial?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh photo-abstract-editorial against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

ECC

by affaan-m

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

257,289

orchestrator session-migrate

⚠️ Third-Party Software Notice

This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.

Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.

Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.

Read the Terms of Service

name: photo-abstract-editorial description: Use when one or more photographs must become adaptive photo-plus-abstraction editorial compositions while source facts, spatial relationships, and strict photo preservation remain controlled.

Photo Abstract Editorial

Create a lightweight editorial composition from a supplied photograph. The photograph remains the sole factual source; generated content is an abstract motif, never a replacement for the final photo region or exact title.

Capability routing

Choose the highest-fidelity mode the host can actually execute:

Strict Fidelity: host visual-understanding capability, host image-generation capability, local filesystem access, local Python/script execution, Pillow-compatible image processing, and a usable serif font. This mode deterministically assembles photo, panel, motif, and typography, then runs machine validation.
Native Image Edit: host visual-understanding capability plus host image-editing/composition capability, without the complete local Strict toolchain. Use the source as the edit/reference image and disclose that pixel-exact, deterministic, machine-verified photo preservation is unavailable.
Reference Generation: host visual-understanding capability, host image-generation capability, and reference-image support. Use the source as the sole factual reference, perform best-effort fidelity, and disclose the same Strict guarantees are unavailable.

If visual understanding or every image-generation/editing capability is absent, stop rather than fabricate a result.

Workflow

Validate the required image input and inspect the source.
Classify the scene and resolve the four controls in control-system.md using scene-profiles.md.
Select a layout from layout-profiles.md using scene facts, orientation, dominant axis, subject location, center of gravity, and negative space. Omitted layout falls back to Lower Editorial.
Read art-direction.md. Generate or edit only what the selected mode permits; keep the motif sparse, traceable, text-free, and source-derived. When the source supports a decisive vertical structure, use one primary and one subordinate irregular vertical stroke, unequal in height and width.
In Strict Fidelity, run remove_chroma_key.py, compose_editorial.py, and validate_editorial.py. Never overwrite source, motif, output, or manifest.
Run the structured eight-dimension QA in quality-check.md. Strict machine validation is necessary but not sufficient; visual/editorial QA is also required.
Apply at most one targeted correction. Re-run the relevant generation/composition, machine validation, and QA; stop after the second attempt if a critical HARD FAIL remains.
For an explicitly requested multi-image series only, load series-style.md and lock the visual family while re-analyzing each new source.

The validated example pair demonstrates package structure and regression expectations; do not copy its subject, palette, title, or coordinates.

Return the final artifact, saved path, selected mode, and concise QA result. Do not claim Strict guarantees for Native Image Edit or Reference Generation.

🎨 Photo Abstract Editorial

A source-faithful Agent Skill that turns photographs into editorial artworks with adaptive layouts, controlled abstraction, and a deterministic composition path.

English · 简体中文 · 繁體中文

Photo Abstract Editorial keeps the source photograph factual, turns source-derived relationships into a restrained abstraction panel, and renders the editorial title locally where the verified path supports it.

Before → After

Same source · Actual V3 output · Strict Fidelity / validator PASS

The source is shown unchanged. The result is the existing V3 same-source artifact in this repository; its manifest records a pixel-exact photographic region, and the published same-source check reports validator PASS.

Before	After

Jump to: Quick Start · Gallery · Choose an Edition · Compatibility · Validation · Releases · Environment Contract

⚡ 30-Second Quick Start

V3 Adaptive is the recommended starting point for most new users.

Install

Download the v3.0.0 release ZIP and install the included Skill, or use the existing installer method:

Use $skill-installer to install the root photo-abstract-editorial Skill from https://github.com/kwhi6693-web/photo-abstract-editorial.

Run

Use $photo-abstract-editorial to create an adaptive, source-faithful photo-and-abstract editorial from this image.

Optional Controls

Use $photo-abstract-editorial. Set Abstraction to 60, Creative Freedom to 45, Identity Preservation to 80, and Spatial Fidelity to 70.

🖼️ Gallery

These five images are actual V3 outputs from the RC evaluation corpus. They are Codex Strict Fidelity results with validator PASS, not promotional reconstructions.

Pure Portrait	Landscape	Architecture

Still Life	Minimal / Light

Scene	Layout	Validation
Pure Portrait	Vertical Monument	Strict Fidelity · validator PASS
Landscape	Wide Horizon	Strict Fidelity · validator PASS
Architecture	Centered Archive	Strict Fidelity · validator PASS
Still Life	Sparse Object	Strict Fidelity · validator PASS
Minimal / Light	Sparse Object	Strict Fidelity · validator PASS

The full corpus and manifests are in assets/evals/v3.0-rc1 and the RC evaluation report.

If this workflow is useful to you, a ⭐ helps more people discover the project.

Why Photo Abstract Editorial?

Preserves the source photograph in the verified Strict Fidelity path.
Chooses a scene-aware layout instead of forcing every source into one frame.
Keeps abstraction controlled and traceable to the photograph.
Renders exact local typography under Strict Fidelity.
Uses structured QA before delivery.
Provides a reproducible deterministic path where the required capabilities are available.

Generic image prompts may redraw the source photograph, lose subject identity, invent unsupported facts, produce inconsistent abstraction levels, or render unreliable typography. This project separates the factual photograph from the generated abstract motif, makes layout and creative decisions explicit, and adds a quality gate before delivery.

🧭 Choose Your Edition

Recommended for most new users: V3 Adaptive.

	Original	V3 Adaptive
Runtime	Codex only	Capability-based; validated on Codex and the tested DeepSeek Harness path
Layout	Fixed	Adaptive
Controls	Manual	Four creative controls
QA	Original validator	Structured V3 QA
Best for	Historical Codex workflow	Current recommended workflow

Original remains supported for users who want the preserved fixed Codex workflow. V3 is the current formal stable release for scene adaptation, explicit controls, adaptive layouts, structured QA, and series work. The two editions can remain available side by side.

🔍 Original vs V3 Comparison

Dimension	Original Edition	V3 Adaptive Edition
Positioning	Preserved pre-V3 workflow	Adaptive photo-plus-abstraction Skill
Runtime environment	Codex only	Codex and the tested DeepSeek Harness capability path validated; capability-based compatibility designed
Complexity	Smaller, fixed workflow	More inputs, profiles, and verification boundaries
Art direction	Warm-ivory panel, muted source-derived motif, optical editorial spacing	Same editorial foundation plus scene-aware art direction and control resolution
Source fidelity	Pixel-exact photo region validated in the Original example	Strict Fidelity pixel-exact photo region validated in Codex and the tested DeepSeek Harness path
Creative controls	Manual title, panel, motif, alignment, and font overrides	Abstraction, Creative Freedom, Identity Preservation, Spatial Fidelity, each 0–100
Scene Profiles	None	7: Pure Portrait, Environmental Portrait, Landscape, Architecture, Street/Crowd, Still Life, Minimal/Light
Portrait adaptation	Source-derived unequal vertical anchors when appropriate	Portrait-aware scene profile and identity-preservation resolution
Layout system	Lower Editorial predecessor: lower-left or bottom-center	5 canonical profiles: Lower Editorial, Wide Horizon, Vertical Monument, Centered Archive, Sparse Object
QA	Machine validator plus visual QA; Original example has 9 validator checks	Structured 8-dimension QA, machine validator, and explicit HARD FAIL rules
Retry	One targeted motif correction; stop after two motif attempts	One targeted correction after a complete attempt; stop on a remaining critical HARD FAIL
Series	No Series Style Lock contract	Optional Series Style Lock process
Agent compatibility	Codex only	Codex and the tested DeepSeek Harness capability path are validated; other hosts remain capability-dependent
Installation	Historical Original package	V3 Adaptive package and current stable release
Best use cases	Stable, familiar, Codex-specific original behavior	Different scenes, explicit controls, layout adaptation, and series work
Main trade-off	Less adaptive and not portable beyond Codex	More process and capability requirements; native tools still vary by host

🎯 Scope, Limitations & Guarantees

Original Edition

Best suited for one photograph, one text-free motif, and one fixed editorial composition in Codex. It provides deterministic local assembly and the Original validator's source/panel checks. It does not provide the V3 control system, scene profiles, canonical auto-layout, Series Style Lock, or cross-Agent contract. It is not supported outside Codex.

V3 Adaptive Edition

Best suited for photographs that benefit from explicit scene reasoning, identity and spatial controls, adaptive layouts, or a series-level visual family. V3 does not invent unsupported people, buildings, objects, geography, text, logos, watermarks, swatches, or decorative facts. Image generation can vary across hosts and runs; current public evidence includes Codex Strict Fidelity and the independently tested DeepSeek Harness capability path.

Guarantee Matrix

Capability	Original	V3 Strict Fidelity	V3 Native Image Edit	V3 Reference Generation
Source-aware behavior	Implemented and Codex-validated	Implemented and validated on Codex and the tested DeepSeek Harness path	Best effort	Best effort
Scene adaptation	Fixed original behavior	Implemented and Codex-evaluated	Art-direction contract only	Art-direction contract only
Creative controls	Manual overrides	4 controls, 0–100	Host-dependent best effort	Host-dependent best effort
Pixel-exact photo region	Validated for Original example	Machine-validated when Strict conditions hold	Not guaranteed	Not guaranteed
Exact local typography	Original compositor path	Loca