@43622283

li-photoindexwithllm indexes photos via vision-language models and supports semantic search with json output. command-line invocation from agents, but documentation conflates skill design with deployment mechanics and lacks rigorous failure handling.

feishu audio skill chains faster-whisper speech recognition, edge tts synthesis, and opus conversion for voice message handling. pipeline is documented with scripts and configuration details but lacks clear intent definitions and explicit failure recovery paths.

li-itil-manager provides itil 5 advisory framed around digital product and service management, but lacks executable procedures. triggers and domain coverage are broad, yet core guidance remains strategic rather than step-by-step actionable.

li-git1-1-checker provides a two-phase document validation framework against gb/t 1.1-2020 standards, combining checklist scanning with vision-based pdf analysis. the skill documents extensive structural requirements and edge cases but lacks concrete execution clarity and assumes vision_analyze availability without fallback.

基于大模型的安全事件日志分析工具，支持快速提取关键信息和深度攻击链细节分析。

Multi-platform server inspection and health check skill. SSH into remote Linux servers using key-based authentication, run read-only inspection commands (CPU...

NVIDIA AV1视频批量压缩工具，使用FFmpeg调用NVIDIA NVENC硬件编码，支持智能压缩验证和多方案选择

基于视觉-语言模型，扫描与索引指定目录照片，支持自然语言语义搜索及标签自定义并输出结构化结果。

Node.js-based Excel automation for reading, writing, cleaning, transforming, merging .xlsx/.xls/.csv files with joins, analysis, flow control, and JS scripti...

安全处理Excel和CSV文件，支持读取、写入、清洗、转换和合并数据，禁止任意代码执行，保障数据安全。

飞书语音交互技能。支持语音消息自动识别、AI 处理、语音回复全流程。需要配置 FEISHU_APP_ID 和 FEISHU_APP_SECRET 环境变量。使用 faster-whisper 进行语音识别，Edge TTS 进行语音合成，自动转换 OPUS 格式并通过飞书发送。适用于飞书平台的语音对话场景。

CodeQL 安全扫描与 LLM 智能分析融合工具。自动检测 CodeQL 安装、扫描指定目录、生成漏洞报告、LLM 分析、Jenkins 集成、输出验证 Checklist。

提供任务与泳道管理、批量操作、AI分析和语义搜索的看板系统，支持Web界面、REST API及MCP工具调用。