by GENEXIS-AI · Codex Skill · ★ 134
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 134 |
| Forks | 15 |
| Language | JavaScript |
| Category | Codex Skill |
| Quality Score | 71/100 |
| Last Updated | 2026-08-28 |
| Created | 2026-08-26 |
| Platforms | claude-code, codex, node |
| Est. Tokens | ~18k |
GPT Image Skill Generate and edit GPT images from Codex, Claude Code, or another compatible local agent through the user's ChatGPT subscription. Direct prompts stay unchanged; when the user delegates several different designs, the agent develops a distinct image-ready prompt for each concept.
These tools work well together with gpt-image-skill for enhanced workflows:
Looking for a gpt-image-skill alternative? If you're comparing gpt-image-skill with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Use your ChatGPT subscription to generate images from the command line — no OPENAI_API_KEY, no gateway, no dae
MCP server for AI image generation and editing with automatic prompt optimization and quality presets. Support
24 cross-platform agent skills for Claude Code, Cursor, Codex & Gemini CLI — databases, messaging, research, T
Odoo MCP for AI agents — 41 tools, gated writes, multi-instance. Free hosted: ERPipe → mcp.erpipe.com
Manage MCP servers, skills and plugins across Claude Code, Codex, Cursor and more. Built-in marketplace, one-c
开源中文配图技能 + IP 角色库:用「挑认知锚点→现编隐喻→反PPT自检」为中文深度文生成固定角色出演的正文配图
Explore other popular codex skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: