GitHub user
Agent skills by zrt-ai-lab
- skills
- 26
- repository
- 1
Repositories by zrt-ai-lab
Skills by zrt-ai-lab, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | This skill should be used when preparing Markdown articles for a WeChat Official Account draft box, selecting wenyan-cli themes, processing article images, or troubleshooting authentication and… | zrt-ai-lab/ | 287 | — | ~465 | Automated safety check: Pass | No licence | 2 mo ago |
| 2 | A skill your agent uses when Codex needs native image generation, editing, or engineered multi-image composition, especially sets, material kits, grids, storyboards, carousels, presentations… | zrt-ai-lab/ | 287 | — | ~2k | Automated safety check: Pass | No licence | 2 mo ago |
| 3 | 智能数据库查询技能。通过SSH隧道连接线上数据库，支持自然语言转SQL、执行查询、表结构探索。当用户需要查询数据库、问数据、看表结构时使用此技能。 | zrt-ai-lab/ | 287 | — | ~484 | Automated safety check: Pass | No licence | 2 mo ago |
| 4 | 视频创作技能。图片+音频合成视频，支持TTS配音、淡入淡出转场、字幕、片尾、BGM。当用户提到「生成视频」「做视频」「教学视频」「图文转视频」「做视频号」「配音视频」「图文结合视频」「古诗视频」「故事视频」时触发。内含生图→配音→合成全流程，无需单独调用image-service。 | zrt-ai-lab/ | 287 | — | ~3.3k | Automated safety check: Pass | No licence | 2 mo ago |
| 5 | 当用户要求"搜索新闻"、"查询AI新闻"、"整理新闻"、"获取某天的新闻"，或提到需要搜索、整理、汇总指定日期的AI行业新闻时，应使用此技能。 | zrt-ai-lab/ | 287 | — | ~1.8k | Automated safety check: Pass | No licence | 2 mo ago |
| 6 | A skill your agent uses when reviewing an agent Skill before sharing, installing, or executing it and when checking a Skill bundle for credentials, dangerous commands, suspicious network behavior… | zrt-ai-lab/ | 287 | — | ~317 | Automated safety check: Pass | No licence | 2 mo ago |
| 7 | 小红书笔记素材创作技能。当用户需要创建小红书笔记素材时使用这个技能。技能包含：根据用户的需求和提供的资料，撰写小红书笔记内容（标题+正文），生成图片卡片（封面+正文卡片），以及发布小红书笔记。 | zrt-ai-lab/ | 287 | — | ~956 | Automated safety check: Pass | No licence | 2 mo ago |
| 8 | A skill your agent uses when a request asks for a Chinese-first AI video script with shot plans, image prompts, narration, subtitles, or handoff contracts for scene generation, image generation… | zrt-ai-lab/ | 287 | — | ~1.7k | Automated safety check: Pass | No licence | 2 mo ago |
| 9 | 抖音视频自动发布技能。当用户需要发布视频到抖音时使用这个技能。技能包含：获取登录Cookie、上传视频、设置标题话题、定时发布等功能。 | zrt-ai-lab/ | 287 | — | ~680 | Automated safety check: Pass | No licence | 2 mo ago |
| 10 | 微信视频号自动发布技能。当用户需要发布视频到微信视频号时使用这个技能。技能包含：获取登录Cookie、上传视频、设置标题话题、定时发布、原创声明等功能。 | zrt-ai-lab/ | 287 | — | ~706 | Automated safety check: Pass | No licence | 2 mo ago |
| 11 | 当用户要求"调研"、"深度调研"、"帮我研究"、"调研下这个"，或提到需要搜索、整理、汇总指定主题的技术内容时，应使用此技能。 | zrt-ai-lab/ | 287 | — | ~1.4k | Automated safety check: Pass | No licence | 2 mo ago |
| 12 | 自更新 skills。记录用户反馈，更新方法论和规则。触发词：更新规则、记录反馈、改进skill. An agent skill from zrt-ai-lab/opencode-skills. | zrt-ai-lab/ | 287 | 2 repos | ~354 | Automated safety check: Pass | No licence | 2 mo ago |
| 13 | 13.Feishu Doc Fetch content from Feishu (Lark) Wiki, Docs, Sheets, and Bitable. | zrt-ai-lab/ | 287 | 1 repo | ~460 | Automated safety check: Pass | No licence | 2 mo ago |
| 14 | Create cron jobs that reliably deliver reminders to Feishu (飞书) chats. | zrt-ai-lab/ | 287 | — | ~562 | Automated safety check: Pass | No licence | 2 mo ago |
| 15 | 15.Log Analyzer 全维度日志分析技能。自动识别日志类型（Java应用/MySQL Binlog/Nginx/Trace/告警），提取关键实体（IP、threadid、traceid、用户、表名等），进行根因定位、告警分析、异常洞察。支持100M+大文件。触发词：分析日志、日志排查、根因定位、告警分析、异常分析。 | zrt-ai-lab/ | 287 | — | ~596 | Automated safety check: Pass | No licence | 2 mo ago |
| 16 | 长文本拆镜批量生图引擎。将故事、课程、连环画脚本智能拆分场景，批量生成风格统一、角色一致的配图。当用户提到「拆镜生图」「故事配图」「批量场景图」「连环画生成」「绘本生成」时使用此技能。 | zrt-ai-lab/ | 287 | — | ~1.6k | Automated safety check: Pass | No licence | 2 mo ago |
| 17 | 17.Uni Agent 统一智能体协议适配层。一套 API 调用所有 Agent 协议（ANP/MCP/A2A/AITP 等）。当用户需要调用 Agent、跨协议通信、连接工具时触发此技能。 | zrt-ai-lab/ | 287 | — | ~1.5k | Automated safety check: Pass | No licence | 2 mo ago |
| 18 | Fetch and summarize Feishu group chat history. An agent skill from zrt-ai-lab/opencode-skills. | zrt-ai-lab/ | 287 | — | ~502 | Automated safety check: Pass | No licence | 2 mo ago |
| 19 | 多模态图像处理技能，支持信息图、封面图、长图、幻灯片、漫画、文章插图、小红书图、营销物料等多场景生图，以及图生图、图生文、长图拼接。 | zrt-ai-lab/ | 287 | — | ~1.1k | Automated safety check: Pass | No licence | 2 mo ago |
| 20 | 短视频文案创作技能。包含爆款公式、黄金结构、三关校验。当需要撰写短视频文案时触发. An agent skill from zrt-ai-lab/opencode-skills. | zrt-ai-lab/ | 287 | — | ~5k | Automated safety check: Pass | No licence | 2 mo ago |
| 21 | 火柴人图片生成技能。使用AI生成粉笔画风格火柴人，并用HSV统一背景色。当需要生成火柴人视频素材时触发. An agent skill from zrt-ai-lab/opencode-skills. | zrt-ai-lab/ | 287 | — | ~1.4k | Automated safety check: Pass | No licence | 2 mo ago |
| 22 | 执行视频剪辑。根据确认的删除任务执行FFmpeg剪辑，循环直到零口误，生成字幕。触发词：执行剪辑、开始剪、确认剪辑. An agent skill from zrt-ai-lab/opencode-skills. | zrt-ai-lab/ | 287 | — | ~569 | Automated safety check: Pass | No licence | 2 mo ago |
| 23 | 口播视频转录和口误识别。生成审查稿和删除任务清单。触发词：剪口播、处理视频、识别口误. An agent skill from zrt-ai-lab/opencode-skills. | zrt-ai-lab/ | 287 | — | ~424 | Automated safety check: Pass | No licence | 2 mo ago |
| 24 | 为项目构建分层式LLM友好文档体系。已有项目：扫描项目结构→架构分类→生成CLAUDE.md主索引→基础模块文档→业务模块API/数据模型/坑点文档→配置文档→git变更日志(含风险评估+回滚指南)→交叉验证。新项目：解析PRD→按脚手架规范设计架构→需求拆解为开发任务→融合代码规范生成CLAUDE.md开发指南→模块级API设计+数据模型+开发清单。当用户需要为项目创建AI编程文档、建立项目索… | zrt-ai-lab/ | 287 | — | ~893 | Automated safety check: Pass | No licence | 2 mo ago |
| 25 | CSV数据分析技能。使用Python和pandas分析CSV文件，生成统计摘要和快速可视化图表。当用户上传或提到CSV文件、需要分析表格数据时自动使用。 | zrt-ai-lab/ | 287 | — | ~577 | Automated safety check: Pass | No licence | 2 mo ago |
| 26 | 环境准备。安装依赖、下载模型、验证环境。触发词：安装、环境准备、初始化 | zrt-ai-lab/ | 287 | — | ~536 | Automated safety check: Notes | No licence | 2 mo ago |
Questions, answered from the data.
What is the best skill by zrt-ai-lab?
Wechat Publisher from zrt-ai-lab/opencode-skills ranks first of the 26 skills by zrt-ai-lab listed here, with the highest score: its repository has 287 GitHub stars, its SKILL.md loads about 465 tokens and it passes the automated safety check with no findings. Next come Codex Image Service and Smart Query.
Are zrt-ai-lab's skills official?
None yet. All 26 skills by zrt-ai-lab listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.