by GF007
AI-assisted game analysis and reconstruction, working toward one-click workflows for any game.
# Add to your Claude Code skills
git clone https://github.com/GF007/game-rebuild-kitGuides for using ai agents skills like game-rebuild-kit.
See how game-rebuild-kit compares with popular alternatives.
game-rebuild-kit is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by GF007. AI-assisted game analysis and reconstruction, working toward one-click workflows for any game. It has 52 GitHub stars.
game-rebuild-kit's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/GF007/game-rebuild-kit" and add it to your Claude Code skills directory (see the Installation section above).
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 game-rebuild-kit against similar tools.
No comments yet. Be the first to share your thoughts!
Available after the catalog security scan passes.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM lists this project for discovery 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.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
Vision: analyze any game in one click and reconstruct its full implementation.
This release provides an agent skill and a worked example. Universal one-click automation and complete reconstruction remain project goals.
Open the interactive preview (no sign-in required)
16 seconds, 1920 x 1080, 30 fps, silent. The views share one animation state and camera. Buffer views use actual outputs from the reconstructed renderer; display transforms are labeled.
The example traces character resources into animation, secondary motion and rendering. The recording shows:
This is a package-based reconstruction with fitted parameters, not verified native-game equivalence.
Use game-analysis to investigate this game behavior. State the question, choose the smallest useful evidence path, and explain what is established and what could change the conclusion.
For reuse, copy the entire skills/game-analysis/ directory into a skill directory supported by your agent. Load the field guide when selecting tools, designing checks or reporting results.
The skill and field guide are maintained in English.
| Item | Scope |
|---|---|
| Focus | Game logic, animation, physics, rendering and reconstruction audits |
| Requirements | No runtime dependencies for the skill itself; analysis tools depend on the target and question |
| Included | Analysis instructions, a field guide and representative media |
| Not included | Extracted game assets, format decoders, a viewer runtime or an automated reconstruction system |
| Current evidence | Distilled from one Android / Unity investigation; usefulness across games needs further evaluation |
Keep samples and task-specific scripts in local case directories. Select existing tools as needed; add shared code only when repeated use justifies it.
The game-specific focus is on resource references, state over time, and downstream use of computed results.
Inspired by the direct-CLI approach in leanrea, reviewed at commit 09ba4aa. Upstream benchmark results are not performance claims for this repository.
The skill text is MIT licensed. Third-party game content shown in the media and external tools retain their respective rights and licenses.