by AndrewNgGirl · Codex Skill · ★ 71
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 | 71 |
| Forks | 7 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 63/100 |
| Open Issues | 2 |
| Last Updated | 2026-05-17 |
| Created | 2026-05-05 |
| Platforms | browser, claude-code, node |
| Est. Tokens | ~1094k |
SkillLens 简体中文 | English 产品演示 https://github.com/user-attachments/assets/8bc9bfce-bfe5-4c3a-a915-9aaf1520969e SkillLens 是一个开源、自托管的 Web 工具，用来评测 Agent Skills。你可以上传一个 、一个 skill 文件夹，或一个 skill 压缩包，SkillLens 会生成量化报告，包括评分细则、证据、SkillLens Deep Review、市场信号和可执行的改进建议。 它面向正在为 Cursor、Claude、OpenClaw 或类似 Agent 生态构建 skill 的开发者，帮助你回答一个核心问题： 这个 skill 是否真的有用、可靠、容易被发现，并且值得发布？ 当前能力地图 SkillLens 的能力由三个正交维度组合而成，按需挑选即可：...
These tools work well together with SkillLens for enhanced workflows:
Looking for a SkillLens alternative? If you're comparing SkillLens 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.
Manage MCP servers, skills and plugins across Claude Code, Codex, Cursor and more. Built-in marketplace, one-c
A collection of AI agent skills for Clawdbot, Claude Code, Codex
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
Zero-config Claude Code setup with enforced task scaffolding, structured memory, persistent context after comp
🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace
Turn feature specs into merged PRs with a self-supervising swarm of coding agents — parallel execution, isolat
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: