No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by GordenSun · AI Tool · ★ 2.0k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is GordenSuperPPTSkills safe to install? View the security audit →
Gorden Super PPT Skills(技能包) AI PPT赛道终结者,史上最最最强 PPT Skill!!! 使用GPT生成豪华的图片格式PPT,然后转换为完全可编辑的PPTX文件。 Skill全流程已拆成 3 个独立技能,可以拆分使用和优化: 只要做图片版 PPT → GordenImagePPTGen 只把图片转可编辑 → GordenImage2PPTX 一键"先出图再转可编辑" / 未指定 → GordenSuperPPTSkill(A→B 串联) 效果展示 1、GordenImagePPTGen(Gorden的图片PPT生成技能)生成图片格式的PPT 2、GordenImage2PPTX(Gorden的图片转PPTX技能)把图片转换为完全可编辑的PPTX文件 如何使用 仅限Codex使用。 第1步:把Github仓库地址发给Codex让他安装技能; 第2步:按需使用。GPT 5.5模型,推理强度选"中"即可。 如果只生成图片格式PPT,提示词: 如果只想把图片PPT转换成可编辑的PPTX文件,提示词: 说明: 本技能仅适用于Codex,因为必须使用GPT生成图片和GPT的视觉能力,理论上Opus+GPT生图接口也可以实现,但是本技能没有做专门的适配。 图片转可编辑PPTX文件,比较费额度,转换1张图片大概耗费Plus订阅5小时额度的10%。 框架图默认是整体的一张图,也支持拆分成一个个独立的框架模块图,提示词里明确告诉Codex即可。 原理讲解 核心使用的是GPT的生图能力和视觉解析能力。 大致步骤是:依次提取PPT图片的背景图、框架图、图标和装饰图、文本。最后在PPT里按坐标拼装起来。当然为了实现完美的效果,做了很多细节验证和约束规则。 使用过程中,你能看到GPT生成的过程图片。 背景图  to block Endpoint Detection and Response (EDR) agents from report
A java agent to generate method mappings to use with the linux `perf` tool
Explore other popular ai tool tools:
GordenSuperPPTSkills is AI PPT赛道终结者,史上最最最强 PPT Skill!!! 使用GPT生成豪华的图片格式PPT,然后转换为完全可编辑的PPTX文件。. It is categorized as a AI Tool with 2.0k GitHub stars.
GordenSuperPPTSkills is primarily written in Python.
You can find installation instructions and usage details in the GordenSuperPPTSkills GitHub repository at github.com/GordenSun/GordenSuperPPTSkills. The project has 2.0k stars and 172 forks, indicating an active community.
The top alternatives to GordenSuperPPTSkills on Agent Skills Hub include claude-code-infrastructure-showcase, vision-agent, axton-obsidian-visual-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: