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 AndrewNgGirl · Codex Skill · ★ 71
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is SkillLens safe to install? View the security audit →
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： 评什么（评测视角） 通用评测：5 大支柱、100 分制；按 skill 结构（atomic / pipeline / composite）启用差异化子维度 金融专家版（可叠加）：在通用总分之外，针对金融场景额外输出 专家分，覆盖投融资、量化、炒股、证券、银行、投教等 多深（评测深度） 规则分预览：确定性检查（pass / partial / fail / notapplicable），秒级返回，不耗 LLM 额度 SkillLens Deep Review：在规则分之上，由 LLM 评估主观维度；规则项仍由官方 scorer 决定，避免 LLM 自由发挥 谁来用（调用入口） Web UI：给人用——浏览器拖拽上传，可视化报告 Agent CLI：给 code agent 用（Cursor / WorkBuddy / Hermes 等）—— 引导选择，并通过 证书校验避免 agent 编造分数 三个维度可任意组合。例如 CLI + 金融专家版 + Deep Review：跑 选择金融并指定场景，由 code agent 自己的模型完成完整的 agent-side 金融专家深度评测，最终 JSON 含 与 verified 证书。 最值得一试的地方 SkillLens 不只是检查 写没写对，而是把一个 skill 当成“可发布的 AI 产品雏形”来评估。它会同时看清晰度、真实需求、商业价值、差异化、运行成本、稳定性和可维护性，帮你判断这个 skill 是“格式合格”，还是“真的值得别人安装和反复使用”。 从“写得规范”提升到“值不值得做”：不仅看 frontmatter、章节和示例，也会评估目标用户、使用频率、价值主张和沉淀潜力。 把主观评审变成可调权重的量化报告：5 大支柱的默认权重透明，子维度按 skill 类型自动启用，并可以按你的团队标准自定义。...
| Stars | 71 |
| Forks | 7 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 63.0583915570564/100 |
| Open Issues | 2 |
| Last Updated | 2026-05-17 |
| Created | 2026-05-05 |
| Platforms | browser, claude-code, node |
| Est. Tokens | ~1094k |
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.
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
Evaluate agent skill quality. Find the weakest link. Fix it. Prove it worked.
Explore other popular codex skill tools:
SkillLens is Open-source self-hosted web tool for evaluating Agent Skills with rubric scores, Deep Review, and improvement suggestions.. It is categorized as a Codex Skill with 71 GitHub stars.
SkillLens is primarily written in TypeScript. It covers topics such as agent-skills, ai-agents, claude.
You can find installation instructions and usage details in the SkillLens GitHub repository at github.com/AndrewNgGirl/SkillLens. The project has 71 stars and 7 forks, indicating an active community.
SkillLens is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to SkillLens on Agent Skills Hub include agent-skills, claudepro-directory, meridian. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.