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 | 70 |
| Forks | 9 |
| Language | Java |
| Category | AI Tool |
| License | MIT |
| Quality Score | 57/100 |
| Open Issues | 1 |
| Last Updated | 2026-10-06 |
| Created | 2026-09-22 |
| Platforms | java |
| Est. Tokens | ~13k |
JevIntent · 微信消息「意图 / 情绪 / 回复姿态」分析插件 一个 FkWeChat 插件：长按任意微信消息 → 调用 TypeSafe Jev 判定模型 → 几秒后在屏幕上弹出结论。不发任何消息、不改聊天记录，对方完全不知道。 用途：对方这句话到底什么意思？该用什么姿态回？——判定用的，不是自动回复机器人。 ⚡ v1.9 起基本是"点完就出"：长按弹出的那一刻就开始算（预判），你点中「意图」时结果通常已经回来了 —— 实测冷启动第一次 1144ms → 9ms。数字和做法都在下面《有多快》。 🔗 姊妹项目：旁观者 · JevBystander —— 同一个判定口径的安卓无障碍版：不用 root / 不用 Xposed，只读屏 + 固定 3 条 Toast。 装不了 LSPosed、或者怕 hook 微信的话用它；两套实现完全独立，同一台手机也能共存。...
These tools work well together with JevIntent for enhanced workflows:
Looking for a JevIntent alternative? If you're comparing JevIntent with other ai tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Nexus | Take over your Android voice assistant with a custom AI agent — connect any LLM (Claude, GPT, Gemini),
BYOK agent tool built with Material 3 Expressive. Control your device, execute Shell and Python natively with
Android Native Agent that makes screen operations, runs shell commands, uses Skills & MCP tools, and controls
🔍微信聊天数据分析的本地化AI-agent(Docker/Windows/MacOS) · AI分身 / 大模型分析 / 好友排行 / 词云 / 情感趋势 / 群聊画像
Per-turn model & reasoning routing for Codex, driven by Jev (TypeSafe System One): picks the model, thinking d
A community directory of projects built on Jev, TypeSafe AI's System One model.
Explore other popular ai tool 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: