Phil-design-skills — security grade SAFE, quality 56/100

Security audit verdict: SAFE · quality 56/100

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 FANzR-arch · Agent Tool · ★ 69

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is Phil-design-skills safe to install? View the security audit →

About Phil-design-skills

Phil Design Skills 一组给 AI Agent 使用的视觉生成 Skills。可以把文章、主题、城市、产品或现有视觉资产,编译成可直接生图的完整提示词。 全部提示词按 gpt-image-2 编写。 不适用于 Midjourney / Stable Diffusion / Flux——那些模型有 negative 通道、seed 和权重语法,写法不通用。 每个 Skill 提供: :适合 Codex、Claude Code 等支持 Agent Skills 的工具(全部 Skill 都有)。 :单文件复制版,适合直接粘贴给 AI(部分 Skill 提供)。 中文排版的统一写法见 ——衬线/无衬线/手写这些类别按主题选,但拉丁专属属性( / / / )对中文无效。 安装 把下面这段话发给支持 Skills 的 AI Agent: 也可以只安装一个 Skill: 可用 Skills 从主题出发 给一个主题、标题、城市或照片,编译成对应风格的提示词。 [tec

agent-skillsai-designchatgptclaude-codegpt-image-2image-generationprompt-engineering

Quick Facts

Stars69
Forks5
CategoryAgent Tool
Quality Score55.8912645209374/100
Last Updated2026-08-15
Created2026-06-18
Platformsclaude-code
Est. Tokens~19k

Compatible Skills

These tools work well together with Phil-design-skills for enhanced workflows:

  • gpt-image-2-gen-skill — semantic(0.74)+complementary+rare_topics+similar_pop+shared_platform (70%)
  • mcp-image — semantic(0.55)+complementary+rare_topics+similar_pop+shared_platform (64%)
  • codex-gpt-image — semantic(0.52)+complementary+rare_topics+similar_pop+shared_platform (63%)
  • chatgpt-imagegen — semantic(0.50)+complementary+rare_topics+similar_pop+shared_platform (62%)

Phil-design-skills alternative? Top 6 similar tools

Looking for a Phil-design-skills alternative? If you're comparing Phil-design-skills with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • mcp-image by shinpr · ⭐ 161

    MCP server for AI image generation and editing with automatic prompt optimization and quality presets. Support

  • codex-gpt-image by ningzimu · ⭐ 56

    OpenClaw/Claude Code SKILL.md for gpt-image-2 via Codex OAuth, no OPENAI_API_KEY required

  • claude-skills by OneWave-AI · ⭐ 298

    200+ production-ready Claude Code skills for sales, marketing, design, engineering, and AI agent architecture.

  • agent-skills by jdrhyne · ⭐ 241

    A collection of AI agent skills for Clawdbot, Claude Code, Codex

  • claudepro-directory by JSONbored · ⭐ 217

    HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve

  • skill-conductor by smixs · ⭐ 160

    Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-ca

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Frequently Asked Questions

What is Phil-design-skills?

Phil-design-skills is 19 套可直接生图的视觉风格 Skills,为 gpt-image-2 编写。把文章、主题、产品或已有视觉资产编译成完整提示词。/ 19 visual-style prompt skills for gpt-image-2.. It is categorized as a Agent Tool with 69 GitHub stars.

How do I install or use Phil-design-skills?

You can find installation instructions and usage details in the Phil-design-skills GitHub repository at github.com/FANzR-arch/Phil-design-skills. The project has 69 stars and 5 forks, indicating an active community.

What are the best alternatives to Phil-design-skills?

The top alternatives to Phil-design-skills on Agent Skills Hub include mcp-image, codex-gpt-image, claude-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Agent Tool tools