Turn audience comments into reply templates, handling guidelines, and future content ideas. For negative incidents, assess severity and draft responses or statements, shared talking points, actions to avoid, and recommended response timing.
评论区运营与舆情危机应对：为一批评论生成分层回复模板（赞美/提问/求购/杠精/黑粉） 与分级处理规则，从评论中挖掘选题反哺内容，负面事件时做危机分级 + 声明草稿 + 统一口径。
当用户说"回复评论"、"评论区运营"、"评论怎么回"、"钓评论"、"引导互动"、 "评论区选题"、"舆情"、"危机公关"、"差评"、"黑粉"、"被骂了"、"道歉声明"、 "统一口径"、"负面缠上来了"、"翻车了怎么办"时触发。
和 skill-quality-gate 的区别：quality-gate 是发布前合规质检， community-ops 是发布后的评论互动与危机响应。
Review the instructions the agent will receive before you install.
发布后的运营层能力：回复评论、从评论挖选题、负面事件时分级响应。三种模式，命中哪个做哪个。
| 模式 | 触发场景 | 核心产出 |
|---|---|---|
| A 评论回复策略 | 有一批评论要回 / 问"评论怎么回" | 分层回复模板 + 分级处理规则 |
| B 评论区选题反哺 | 问"评论区能挖什么选题" / 给了一堆评论 | 3-5 条下一步选题建议 |
| C 舆情危机应对 | 出现负面事件、差评风波、被黑 | 危机分级 + 声明草稿 + 统一口径 + 红线 + 时效 |
一次请求可能命中多个模式（如"评论区吵起来了，帮我回一下顺便看要不要出声明"）。先判定模式，再按对应流程执行。若输入模糊，先问清"是要回评论、挖选题、还是处理负面"。
| 字段 | 必填 | 说明 |
|---|---|---|
| 评论内容 | 模式 A/B 必填 | 一批真实评论，或"我这类内容常收到 XX 类评论"的场景描述 |
| 负面事件描述 | 模式 C 必填 | 发生了什么、在哪个平台、扩散到什么程度、有无实锤 |
| 目标平台 | 推荐 | 小红书 / 抖音 / B站 / 微博 / 公众号 / 知乎，决定调性 |
| 品牌人设/红线 | 可选 | 无 Profile 时可手动提供，用于定语气和口径 |
references/reply-playbook.md「一、五类评论分层话术库」，按五类归类用户给的评论：普通赞美 / 专业提问 / 求购买求链接 / 杠精抬杠 / 黑粉恶意差评。[占位符] 表示品牌名、产品、链接等，不写死具体 case）。references/reply-playbook.md「二、分级处理规则」给出处置分级：必回 / 引导私信 / 置顶 / 冷处理 / 删除拉黑，并说明每条评论归入哪级、为什么。references/platform-comment-ecology.md 对应平台段（小红书亲和、B站梗感、知乎专业、抖音短平快、微博快节奏、公众号克制）。references/topic-mining.md「一、评论聚类维度」聚类出高频诉求、重复疑问、争议点、许愿、吐槽。references/topic-mining.md「二、评论转选题公式」把高价值聚类转成 3-5 条具体选题建议。references/crisis-grading.md「一、危机三级分级标准」，按事件性质、扩散度、是否有实锤、是否触及安全/法律/伦理底线，判定：🟢 可忽略 / 🟡 需回应 / 🔴 需正式声明。给出判定依据（命中了哪几条标准）。references/crisis-grading.md「三、回应话术框架」出评论区/私信回应话术草稿。references/crisis-grading.md「五、统一口径」）。references/crisis-grading.md「六、危机红线」，如删评控评、甩锅、情绪化对线、大规模拉黑）。references/crisis-grading.md「七、响应时效」）。有 Profile 时：
preferences.md（要做的/不做的/合规底线）→ 回复语气与危机口径贴合品牌人设，不越红线。style.md / identity.md → 回复模板的用词、称呼、梗的尺度对齐账号风格。platforms.md → 自动确定主攻平台的评论调性，无需再问。preferences.md「合规底线」，声明不承诺做不到的事。无 Profile 时：
[占位符]，不写死具体品牌/产品/人名的 case。No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Generate images from written descriptions, transform existing images with editing instructions, or create several variations. Choose image dimensions and quantity, then save the results using an OpenAI-compatible service or apimart with your own API key.
Generate background music for short videos, vlogs, and social posts from descriptions of mood, style, and instruments. Download MP3 audio, optionally include sung lyrics, and use shared scripts to trim tracks, adjust loudness, or add music to videos.
Create new videos from written scene descriptions or still images using external AI services. Set the aspect ratio and duration, animate a character image, and request generated audio when the selected model supports it.
Organize generated images, videos, and text in outputs/ by date, platform, and type. Add tags, search filenames and content, produce asset lists and reports, and preview archive moves before applying them to make past work easier to reuse.
Reduce background noise in audio recordings or video soundtracks with three processing levels. Keep the original file, create a cleaned version, and receive a report of the settings used and file details before and after processing.
Edit audio files by trimming sections, converting formats, matching loudness, or extracting sound from videos. You can also join recordings, add fades, and change playback speed while keeping the original pitch.