@remixmate/cli 0.9.69 → 0.9.71

package/README.md

@@ -187,6 +187,7 @@ This project contains 13 AI media generation skills covering the full pipeline f
 │  web-screenshot    Web page screenshot (png / jpg)          │
 │  web-record        Web page recording / storyboard video    │
 │  web-read          Web page text extraction (markdown/json) │
+│  gen-post          Post copy: Douyin / XHS / TikTok         │
 └─────────────────────────────────────────────────────────────┘
 ```
 
@@ -207,6 +208,7 @@ This project contains 13 AI media generation skills covering the full pipeline f
 │   ├── render-video/           # orchestration: Phase 3 Remotion render (canonical render_video.py)
 │   ├── export-jianying/        # orchestration: export Jianying draft ZIP
 │   ├── video-parser/           # tool: video deconstruction & analysis
+│   ├── gen-post/               # tool: social post copy per platform (http handler)
 │   ├── web-screenshot/         # tool: headless-browser screenshot (also hosts record.py)
 │   ├── web-record/             # tool: headless-browser recording (entry -> web-screenshot/scripts/record.py)
 │   └── web-read/               # tool: headless-browser text extraction (entry -> web-screenshot/scripts/read_page.py)
@@ -227,6 +229,7 @@ This project contains 13 AI media generation skills covering the full pipeline f
 | render-video | orchestration | job_id → Remotion render → upload | python `scripts/render_video.py` |
 | export-jianying | orchestration | Asset URLs → Jianying draft ZIP (auto-converts from RenderPlan) | python `scripts/gen_jianying_draft.py` |
 | video-parser | tool | Video → audio + ASR + keyframes + scene segmentation | python `scripts/parse_via_render.py` |
+| gen-post | tool | Post text for a finished video — title / description / hashtags for Douyin, Xiaohongshu, TikTok | http handler |
 | web-screenshot | tool | Web page screenshot (png / jpg) | python `scripts/screenshot.py` |
 | web-record | tool | Web page recording / scroll-through / storyboard video (webm -> mp4 -> VOD) | python `../web-screenshot/scripts/record.py` |
 | web-read | tool | Web page → main text (markdown / plain text / structured JSON) | python `../web-screenshot/scripts/read_page.py` |

package/README.zh-CN.md

@@ -141,6 +141,7 @@ Python 技能（13 个中的 9 个）需要 `python3 >= 3.10`。`web-screenshot`
 │  web-screenshot    网页截图（png / jpg）                     │
 │  web-record        网页录屏 / 滚动录屏 / 分镜视频            │
 │  web-read          网页正文抽取（markdown / 纯文本 / JSON）  │
+│  gen-post          发布文案（抖音 / 小红书 / TikTok）        │
 └─────────────────────────────────────────────────────────────┘
 ```
 
@@ -161,6 +162,7 @@ Python 技能（13 个中的 9 个）需要 `python3 >= 3.10`。`web-screenshot`
 │   ├── render-video/           # 编排: Phase 3 Remotion 渲染（含 render_video.py 实现）
 │   ├── export-jianying/        # 编排: 导出剪映草稿 ZIP
 │   ├── video-parser/           # 工具: 视频解构与分析
+│   ├── gen-post/               # 工具: 按平台生成发布文案（http handler）
 │   ├── web-screenshot/         # 工具: 无头浏览器截图（record.py 也放在这里）
 │   ├── web-record/             # 工具: 无头浏览器录屏（入口指向 web-screenshot/scripts/record.py）
 │   └── web-read/               # 工具: 无头浏览器正文抽取（入口指向 web-screenshot/scripts/read_page.py）
@@ -181,6 +183,7 @@ Python 技能（13 个中的 9 个）需要 `python3 >= 3.10`。`web-screenshot`
 | render-video | 编排 | job_id → Remotion 渲染 → 上传 | python `scripts/render_video.py` |
 | export-jianying | 编排 | 素材 URL → 剪映草稿 ZIP（支持从 RenderPlan 自动转换） | python `scripts/gen_jianying_draft.py` |
 | video-parser | 工具 | 视频 → 音频 + ASR + 关键帧 + 场景分段 | python `scripts/parse_via_render.py` |
+| gen-post | 工具 | 成片的发布文案：抖音 / 小红书 / TikTok 的标题、描述、话题标签 | http handler |
 | web-screenshot | 工具 | 网页截图（png / jpg） | python `scripts/screenshot.py` |
 | web-record | 工具 | 网页录屏 / 滚动录屏 / 分镜视频（webm → mp4 → VOD） | python `../web-screenshot/scripts/record.py` |
 | web-read | 工具 | 网页正文抽取（markdown / 纯文本 / 结构化 JSON） | python `../web-screenshot/scripts/read_page.py` |

package/dist/handlers/gen-post.d.ts

@@ -0,0 +1,21 @@
+/**
+ * gen-post handler — POST ab-api /publish/caption/generate.
+ *
+ * Generates the text of a social post — per-platform title / description / tags —
+ * for a finished video (the video itself is not touched or uploaded): the same endpoint and prompts the web studio's 「发布文案」
+ * panel uses. Prompt wording, compliance rules and the platform roster all live
+ * in ab-api (publish_prompts.go + the user's saved prompt overrides); this
+ * handler only collects context and forwards it.
+ *
+ * Behavior:
+ *   - --platform is repeatable and/or comma-separated; `all` (the default) expands
+ *     to the three platforms the web panel shows. Each platform is one backend
+ *     call (one LLM run, billed separately), issued concurrently.
+ *   - --render-id links the result to a studio take so it shows up in the web
+ *     panel; without it the backend generates without persisting anything.
+ *   - --instruction rewrites an existing caption (--title / --description / --tag
+ *     are the draft) instead of generating from scratch; single platform only,
+ *     since the draft belongs to one platform.
+ */
+import type { HandlerContext, HandlerInput } from './index.js';
+export declare function genPost(input: HandlerInput, ctxIn: HandlerContext): Promise<void>;

package/dist/handlers/gen-post.js

@@ -0,0 +1,188 @@
+/**
+ * gen-post handler — POST ab-api /publish/caption/generate.
+ *
+ * Generates the text of a social post — per-platform title / description / tags —
+ * for a finished video (the video itself is not touched or uploaded): the same endpoint and prompts the web studio's 「发布文案」
+ * panel uses. Prompt wording, compliance rules and the platform roster all live
+ * in ab-api (publish_prompts.go + the user's saved prompt overrides); this
+ * handler only collects context and forwards it.
+ *
+ * Behavior:
+ *   - --platform is repeatable and/or comma-separated; `all` (the default) expands
+ *     to the three platforms the web panel shows. Each platform is one backend
+ *     call (one LLM run, billed separately), issued concurrently.
+ *   - --render-id links the result to a studio take so it shows up in the web
+ *     panel; without it the backend generates without persisting anything.
+ *   - --instruction rewrites an existing caption (--title / --description / --tag
+ *     are the draft) instead of generating from scratch; single platform only,
+ *     since the draft belongs to one platform.
+ */
+import { EXIT, mmPost, resolveHttpContext, SkillError } from '../http.js';
+import { emitProgress } from '../progress.js';
+import { isTrue, toNumber, toStringArray } from './shared.js';
+/** Platforms the web panel enables by default; `all` expands to these. */
+const DEFAULT_PLATFORMS = ['douyin', 'xiaohongshu', 'tiktok'];
+/** Friendly aliases → backend platform codes. Unknown values pass through for ab-api to validate. */
+const PLATFORM_ALIASES = {
+    dy: 'douyin',
+    抖音: 'douyin',
+    xhs: 'xiaohongshu',
+    rednote: 'xiaohongshu',
+    小红书: 'xiaohongshu',
+    tt: 'tiktok',
+};
+/** Display names for human-readable output only. */
+const PLATFORM_LABELS = {
+    douyin: '抖音 Douyin',
+    xiaohongshu: '小红书 Xiaohongshu',
+    tiktok: 'TikTok',
+};
+/** Backend waits on a non-streaming LLM call (80s server-side cap); leave headroom. */
+const GENERATE_TIMEOUT_MS = 90_000;
+function resolvePlatforms(value) {
+    const raw = toStringArray(value)
+        .flatMap((v) => v.split(/[,，\s]+/))
+        .map((v) => v.trim())
+        .filter(Boolean);
+    if (raw.length === 0)
+        return [...DEFAULT_PLATFORMS];
+    const out = [];
+    for (const item of raw) {
+        const key = item.toLowerCase();
+        const codes = key === 'all' ? [...DEFAULT_PLATFORMS] : [PLATFORM_ALIASES[item] ?? PLATFORM_ALIASES[key] ?? key];
+        for (const code of codes)
+            if (!out.includes(code))
+                out.push(code);
+    }
+    return out;
+}
+function optString(value) {
+    if (typeof value !== 'string')
+        return undefined;
+    const trimmed = value.trim();
+    return trimmed || undefined;
+}
+/** Tags may arrive as `--tag a --tag b`, `--tag "a,b"`, or with a leading `#`. */
+function normalizeTags(value) {
+    return toStringArray(value)
+        .flatMap((v) => v.split(/[,，]+/))
+        .map((v) => v.trim().replace(/^#+/, ''))
+        .filter(Boolean);
+}
+async function generateOne(ctx, platform, base) {
+    emitProgress({ phase: 'gen-post:request', platform });
+    try {
+        const caption = await mmPost(ctx, '/publish/caption/generate', { ...base, platform }, { timeoutMs: GENERATE_TIMEOUT_MS });
+        if (!caption || (!caption.title && !caption.description)) {
+            return { platform, error: 'backend returned an empty caption' };
+        }
+        emitProgress({ phase: 'gen-post:done', platform });
+        return { platform, caption: { ...caption, platform, tags: caption.tags ?? [] } };
+    }
+    catch (err) {
+        // Auth failures abort the whole run: every other platform would fail the same way.
+        if (err instanceof SkillError && err.exitCode === EXIT.NOT_AUTHENTICATED)
+            throw err;
+        return { platform, error: err instanceof Error ? err.message : String(err) };
+    }
+}
+function printHuman(results) {
+    for (const r of results) {
+        const label = PLATFORM_LABELS[r.platform] ?? r.platform;
+        process.stdout.write(`\n━━━━━━━━ ${label} ━━━━━━━━\n`);
+        if (!r.caption) {
+            process.stdout.write(`❌ ${r.error ?? 'generation failed'}\n`);
+            continue;
+        }
+        const { title, description, tags } = r.caption;
+        process.stdout.write(`标题 / Title:\n${title}\n\n`);
+        process.stdout.write(`描述 / Description:\n${description}\n\n`);
+        process.stdout.write(`标签 / Tags:\n${tags.map((t) => `#${t}`).join(' ')}\n`);
+    }
+    const ok = results.filter((r) => r.caption).length;
+    process.stdout.write(`\n🎉 Generated publish copy for ${ok}/${results.length} platform(s)\n`);
+}
+export async function genPost(input, ctxIn) {
+    const topic = optString(input.topic);
+    const hook = optString(input.hook);
+    const instruction = optString(input.instruction);
+    const renderId = optString(input.render_id);
+    const platforms = resolvePlatforms(input.platform);
+    const current = {
+        title: optString(input.title) ?? '',
+        description: optString(input.description) ?? '',
+        tags: normalizeTags(input.tag),
+    };
+    const hasDraft = !!(current.title || current.description || current.tags.length);
+    if (instruction) {
+        if (platforms.length !== 1) {
+            throw new SkillError('❌ --instruction rewrites one platform\'s caption; pass exactly one --platform');
+        }
+        if (!hasDraft) {
+            throw new SkillError('❌ --instruction needs the caption to rewrite: pass --title / --description / --tag');
+        }
+        if (instruction.length > 500) {
+            throw new SkillError('❌ --instruction must be at most 500 characters');
+        }
+    }
+    else if (!topic && !hook) {
+        throw new SkillError('❌ Please provide --topic (what the video is about); --hook is optional extra context');
+    }
+    const durationSec = toNumber(input.duration, 'duration');
+    if (durationSec !== undefined && durationSec < 0) {
+        throw new SkillError('❌ --duration must be a non-negative number of seconds');
+    }
+    const base = {};
+    if (renderId)
+        base.renderId = renderId;
+    const videoProjectId = optString(input.video_project_id);
+    if (videoProjectId)
+        base.videoProjectId = videoProjectId;
+    if (topic)
+        base.topic = topic;
+    if (hook)
+        base.hook = hook;
+    const sourceUrl = optString(input.source_url);
+    if (sourceUrl)
+        base.sourceUrl = sourceUrl;
+    if (durationSec !== undefined)
+        base.durationSec = durationSec;
+    const aspectRatio = optString(input.aspect_ratio);
+    if (aspectRatio)
+        base.aspectRatio = aspectRatio;
+    const language = optString(input.language);
+    if (language)
+        base.language = language;
+    const promptOverride = optString(input.prompt);
+    if (promptOverride)
+        base.promptOverride = promptOverride;
+    if (instruction) {
+        base.instruction = instruction;
+        base.current = current;
+    }
+    const ctx = await resolveHttpContext(ctxIn.skillName, {
+        apiBaseUrl: input.api_base_url,
+        privateToken: input.priv_token,
+        preflightToken: ctxIn.auth?.token,
+    });
+    const results = await Promise.all(platforms.map((p) => generateOne(ctx, p, base)));
+    const succeeded = results.filter((r) => r.caption);
+    if (isTrue(input.json_output)) {
+        process.stdout.write(JSON.stringify({
+            captions: succeeded.map((r) => ({
+                platform: r.platform,
+                title: r.caption.title,
+                description: r.caption.description,
+                tags: r.caption.tags,
+            })),
+            errors: results.filter((r) => !r.caption).map((r) => ({ platform: r.platform, error: r.error })),
+            persisted: !!renderId,
+        }) + '\n');
+    }
+    else {
+        printHuman(results);
+    }
+    if (succeeded.length === 0) {
+        throw new SkillError(`❌ publish copy generation failed for every platform: ${results.map((r) => `${r.platform}: ${r.error}`).join('; ')}`);
+    }
+}

package/dist/handlers/index.js

@@ -9,10 +9,12 @@ import { genVoice } from './gen-voice.js';
 import { genVideo } from './gen-video.js';
 import { genDigitalHuman } from './gen-digital-human.js';
 import { templateInit } from './template-init.js';
+import { genPost } from './gen-post.js';
 export const HANDLERS = {
     'gen-image': genImage,
     'gen-voice': genVoice,
     'gen-video': genVideo,
     'gen-digital-human': genDigitalHuman,
     'template-init': templateInit,
+    'gen-post': genPost,
 };

package/dist/manifest.json

@@ -1,7 +1,7 @@
 {
   "schemaVersion": 1,
-  "version": "0.9.69",
-  "generatedAt": "2026-10-05T15:20:28.516Z",
+  "version": "0.9.71",
+  "generatedAt": "2026-10-08T03:44:04.976Z",
   "skills": [
     {
       "id": "doc-parse",
@@ -411,6 +411,124 @@
         ]
       }
     },
+    {
+      "id": "gen-post",
+      "toolName": "gen_post",
+      "tier": "tool",
+      "category": "consuming",
+      "title": "Social Post Copy",
+      "summary": "Write the text of a social post for a finished video — title, description and hashtags — per platform (text only; it does not upload or publish the video): Douyin (抖音), Xiaohongshu (小红书) and TikTok. Same prompts as the web studio's publish panel, including the platform's length limits and ad-law / community-guideline compliance rules, and the user's saved prompt overrides. Generates all three platforms by default; pass `platform` to pick. Give it the video's topic plus any hook, source URL, duration and aspect ratio you know — it only writes from what it is given. With `instruction` plus the current title/description/tags it rewrites an existing caption instead. Each platform is one LLM call and costs credits.",
+      "triggers": [
+        "Publish copy / caption / title + description + hashtags for a video",
+        "发布文案、视频标题、话题标签、抖音文案、小红书笔记文案、TikTok caption",
+        "Rewrite or polish an existing video caption for a platform"
+      ],
+      "entry": {
+        "type": "http",
+        "handler": "gen-post"
+      },
+      "runtime": "node",
+      "envVars": [
+        "PRIV_TOKEN",
+        "MM_API_BASE_URL",
+        "AGENT_NAME"
+      ],
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "topic": {
+            "type": "string",
+            "description": "What the video is about — the main input for the copy (required unless rewriting with `instruction`)"
+          },
+          "platform": {
+            "type": "array",
+            "items": {
+              "type": "string"
+            },
+            "description": "Target platforms: douyin / xiaohongshu / tiktok, or all (default: all three). Repeatable or comma-separated."
+          },
+          "hook": {
+            "type": "string",
+            "description": "The video's opening hook line, if known"
+          },
+          "source_url": {
+            "type": "string",
+            "description": "Project / source URL the video is about, if any (used as context; never written into the copy as a link)"
+          },
+          "duration": {
+            "type": "number",
+            "description": "Video duration in seconds"
+          },
+          "aspect_ratio": {
+            "type": "string",
+            "description": "Video aspect ratio, e.g. 9:16 (default 9:16)"
+          },
+          "language": {
+            "type": "string",
+            "description": "Output language. Default: English for tiktok, 简体中文 for the others."
+          },
+          "instruction": {
+            "type": "string",
+            "description": "Rewrite request for an existing caption, e.g. 'shorter title, drop the emoji'. Requires exactly one platform plus the current title / description / tag. Max 500 characters."
+          },
+          "title": {
+            "type": "string",
+            "description": "Current title to rewrite (only with `instruction`)"
+          },
+          "description": {
+            "type": "string",
+            "description": "Current description to rewrite (only with `instruction`)"
+          },
+          "tag": {
+            "type": "array",
+            "items": {
+              "type": "string"
+            },
+            "description": "Current tags to rewrite (only with `instruction`). Repeatable or comma-separated; a leading # is stripped."
+          },
+          "prompt": {
+            "type": "string",
+            "description": "Replace the platform prompt for this run only. Placeholders: {{topic}} {{hook}} {{sourceUrl}} {{durationSec}} {{aspectRatio}} {{language}}. The output must still be a JSON object with title / description / tags."
+          },
+          "render_id": {
+            "type": "string",
+            "description": "Studio render (take) id. When given, the result is saved to that take and shows up in the web publish panel; otherwise nothing is saved."
+          },
+          "video_project_id": {
+            "type": "string",
+            "description": "Studio video project id of the take (only with `render_id`)"
+          },
+          "json_output": {
+            "type": "boolean",
+            "description": "Emit a JSON result ({ captions: [{ platform, title, description, tags }], errors, persisted }) instead of human-readable output"
+          }
+        },
+        "required": []
+      },
+      "ui": {
+        "primary": [
+          "topic",
+          "platform",
+          "hook"
+        ],
+        "advanced": [
+          "source_url",
+          "duration",
+          "aspect_ratio",
+          "language",
+          "instruction",
+          "title",
+          "description",
+          "tag",
+          "prompt"
+        ],
+        "hidden": [
+          "render_id",
+          "video_project_id",
+          "json_output"
+        ]
+      }
+    },
     {
       "id": "gen-script",
       "toolName": "gen_script",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@remixmate/cli",
-  "version": "0.9.69",
+  "version": "0.9.71",
   "description": "AI media generation skills for Claude Code / Codex — 12 skills covering image, video, voice, digital human, web screenshot, web recording, script, template registry, rendering, Jianying export, and video deconstruction.",
   "type": "module",
   "main": "dist/index.js",

package/skills/gen-post/SKILL.md

@@ -0,0 +1,104 @@
+---
+name: gen-post
+description: |
+  Social-post skill: write the post text — title, description and hashtags — for a finished video, per platform: Douyin (抖音), Xiaohongshu (小红书) and TikTok. Text only; it does not upload or publish the video. Backed by ab-api's `/publish/caption/generate`, the same prompts the web studio's publish panel uses.
+
+  Use this skill immediately whenever the user asks for any of:
+  - Publish copy / caption / title + description + hashtags for a video
+  - 发布文案、视频标题、话题标签、抖音文案、小红书笔记文案、TikTok caption
+  - Rewrite or polish an existing video caption for a platform
+triggers:
+  - Publish copy / caption / title + description + hashtags for a video
+  - 发布文案、视频标题、话题标签、抖音文案、小红书笔记文案、TikTok caption
+  - Rewrite or polish an existing video caption for a platform
+---
+
+# Social Post Skill
+
+Wraps ab-api's `POST /publish/caption/generate`. Platform prompts (length limits, tone, and
+the ad-law / community-guideline compliance rules) live in the backend, and a user's saved
+prompt overrides from the web panel apply here too.
+
+| `--platform` | Default language | Shape |
+|--------------|------------------|-------|
+| `douyin` (`dy`) | 简体中文 | short hook title, 60-150 字 description, 3-5 tags |
+| `xiaohongshu` (`xhs`) | 简体中文 | note-style title ≤ 20 字, 200-400 字 body, 5-8 tags |
+| `tiktok` (`tt`) | English | first-line title, short caption, 3-5 hashtags |
+
+Default is all three. Each platform is one LLM call, run concurrently, charged separately.
+
+## Generate
+
+The copy is written only from what you pass — anything missing is treated as "not provided",
+never invented. So pass what you know about the video: `--topic` is the main input, and
+`--hook` / `--source-url` / `--duration` / `--aspect-ratio` sharpen it.
+
+```bash
+remixmate gen-post \
+  --topic "<what the video is about>" \
+  --hook "<opening line>" \
+  --duration 45 --aspect-ratio 9:16
+```
+
+```bash
+# One platform, machine-readable
+remixmate gen-post --topic "<topic>" --platform xhs --json-output
+```
+
+After running `render-video` in the same session, you already know the topic, hook, duration
+and aspect ratio from the script — reuse them rather than asking the user again.
+
+## Rewrite
+
+`--instruction` rewrites an existing caption instead of starting over. One platform only;
+pass the current caption as the draft. Fields the instruction doesn't mention are kept.
+Compliance rules still win: asking for superlatives, guarantees or off-platform links gets a
+compliant rewording, not a literal one.
+
+```bash
+remixmate gen-post --platform douyin \
+  --instruction "标题去掉 emoji，再短一点" \
+  --title "<current title>" --description "<current description>" \
+  --tag tagA --tag tagB
+```
+
+## Flags
+
+| Flag | Description | Default |
+|------|-------------|---------|
+| `--topic` | What the video is about (required unless `--instruction`) | — |
+| `--platform` | `douyin` / `xiaohongshu` / `tiktok` / `all`; repeatable or comma-separated | `all` |
+| `--hook` | Opening hook line | none |
+| `--source-url` | Project/source URL, context only | none |
+| `--duration` | Seconds | none |
+| `--aspect-ratio` | e.g. `9:16` | `9:16` |
+| `--language` | Output language | per platform (see table) |
+| `--instruction` | Rewrite request, ≤ 500 chars | none |
+| `--title` / `--description` / `--tag` | Current caption to rewrite | none |
+| `--prompt` | Replace the platform prompt for this run; placeholders `{{topic}}` `{{hook}}` `{{sourceUrl}}` `{{durationSec}}` `{{aspectRatio}}` `{{language}}` | saved/default prompt |
+| `--render-id` / `--video-project-id` | Save the result to a studio take (shows in the web publish panel) | not saved |
+| `--json-output` | `{ captions: [{ platform, title, description, tags }], errors, persisted }` | off |
+| `--api-base-url` / `--priv-token` | Override API root / token | env |
+
+Tags come back without `#`; the human-readable output adds it.
+
+## Output
+
+Show the user each platform's title, description and tags as-is so they can copy them. If
+some platforms failed, the rest still print; the run exits non-zero only when every platform
+failed.
+
+## Credits
+
+Each platform charges credits. Relay the footer when it appears:
+
+```
+💳 Charged <credits> credits · balance <balance>
+```
+
+## Error handling
+
+- **Token missing / 401**: set `PRIV_TOKEN` or run `remixmate login`.
+- **`不支持的平台`**: the platform code is not one the backend knows.
+- **`模型响应超时` / timeout**: retry; generating fewer platforms at once also helps.
+- **`--instruction` errors**: pass exactly one `--platform` and the current caption.

package/skills/gen-post/skill.json

@@ -0,0 +1,113 @@
+{
+  "name": "gen-post",
+  "toolName": "gen_post",
+  "tier": "tool",
+  "category": "consuming",
+  "title": "Social Post Copy",
+  "description": "Write the text of a social post for a finished video — title, description and hashtags — per platform (text only; it does not upload or publish the video): Douyin (抖音), Xiaohongshu (小红书) and TikTok. Same prompts as the web studio's publish panel, including the platform's length limits and ad-law / community-guideline compliance rules, and the user's saved prompt overrides. Generates all three platforms by default; pass `platform` to pick. Give it the video's topic plus any hook, source URL, duration and aspect ratio you know — it only writes from what it is given. With `instruction` plus the current title/description/tags it rewrites an existing caption instead. Each platform is one LLM call and costs credits.",
+  "auth": "required",
+  "envVars": [
+    "PRIV_TOKEN",
+    "MM_API_BASE_URL",
+    "AGENT_NAME"
+  ],
+  "entry": {
+    "type": "http",
+    "handler": "gen-post"
+  },
+  "parameters": {
+    "type": "object",
+    "properties": {
+      "topic": {
+        "type": "string",
+        "description": "What the video is about — the main input for the copy (required unless rewriting with `instruction`)"
+      },
+      "platform": {
+        "type": "array",
+        "items": {
+          "type": "string"
+        },
+        "description": "Target platforms: douyin / xiaohongshu / tiktok, or all (default: all three). Repeatable or comma-separated."
+      },
+      "hook": {
+        "type": "string",
+        "description": "The video's opening hook line, if known"
+      },
+      "source_url": {
+        "type": "string",
+        "description": "Project / source URL the video is about, if any (used as context; never written into the copy as a link)"
+      },
+      "duration": {
+        "type": "number",
+        "description": "Video duration in seconds"
+      },
+      "aspect_ratio": {
+        "type": "string",
+        "description": "Video aspect ratio, e.g. 9:16 (default 9:16)"
+      },
+      "language": {
+        "type": "string",
+        "description": "Output language. Default: English for tiktok, 简体中文 for the others."
+      },
+      "instruction": {
+        "type": "string",
+        "description": "Rewrite request for an existing caption, e.g. 'shorter title, drop the emoji'. Requires exactly one platform plus the current title / description / tag. Max 500 characters."
+      },
+      "title": {
+        "type": "string",
+        "description": "Current title to rewrite (only with `instruction`)"
+      },
+      "description": {
+        "type": "string",
+        "description": "Current description to rewrite (only with `instruction`)"
+      },
+      "tag": {
+        "type": "array",
+        "items": {
+          "type": "string"
+        },
+        "description": "Current tags to rewrite (only with `instruction`). Repeatable or comma-separated; a leading # is stripped."
+      },
+      "prompt": {
+        "type": "string",
+        "description": "Replace the platform prompt for this run only. Placeholders: {{topic}} {{hook}} {{sourceUrl}} {{durationSec}} {{aspectRatio}} {{language}}. The output must still be a JSON object with title / description / tags."
+      },
+      "render_id": {
+        "type": "string",
+        "description": "Studio render (take) id. When given, the result is saved to that take and shows up in the web publish panel; otherwise nothing is saved."
+      },
+      "video_project_id": {
+        "type": "string",
+        "description": "Studio video project id of the take (only with `render_id`)"
+      },
+      "json_output": {
+        "type": "boolean",
+        "description": "Emit a JSON result ({ captions: [{ platform, title, description, tags }], errors, persisted }) instead of human-readable output"
+      }
+    },
+    "required": []
+  },
+  "ui": {
+    "primary": [
+      "topic",
+      "platform",
+      "hook"
+    ],
+    "advanced": [
+      "source_url",
+      "duration",
+      "aspect_ratio",
+      "language",
+      "instruction",
+      "title",
+      "description",
+      "tag",
+      "prompt"
+    ],
+    "hidden": [
+      "render_id",
+      "video_project_id",
+      "json_output"
+    ]
+  }
+}

package/skills/gen-post/version.json

@@ -0,0 +1,7 @@
+{
+  "skillName": "gen-post",
+  "repoName": "agent-skill-media-maker",
+  "skillId": "pending-gen-post",
+  "version": "V1",
+  "skillDescription": "Social-post skill: write the post text — title, description and hashtags — for a finished video, per platform: Douyin (抖音), Xiaohongshu (小红书) and TikTok. Text only; it does not upload or publish the video. Backed by ab-api's `/publish/caption/generate` (the same prompts as the web studio's publish panel).\n\nUse this skill immediately whenever the user asks for any of:\n- Publish copy / caption / title + description + hashtags for a video\n- 发布文案、视频标题、话题标签、抖音文案、小红书笔记文案、TikTok caption\n- Rewrite or polish an existing video caption for a platform"
+}

package/skills/web-read/SKILL.md

@@ -110,6 +110,8 @@ python3 <ReadScript> --url "https://example.com/x" --user-agent "Mozilla/5.0 (Ma
 
 The stderr diagnostics tell you which case you are in: `⚠️ 整页有 N 字符，却只抽到 M` means the wrong container was chosen (→ `--selector`), while `⚠️ 这个页面几乎没有文本` means the page itself never rendered text (→ waiting, cookies, or user-agent).
 
+Slow or unreachable sub-resources do not fail the read: images / fonts / media / stylesheets are never fetched, every other sub-resource is cut off after 8s, and extraction runs on whatever DOM has loaded (stderr says `[web_read] N 个子资源…已跳过`). A non-zero `打开页面失败` therefore means the server never returned the page itself — retrying the same URL with a bigger timeout, another user-agent, device or browser will not help; ask for the text or a different URL.
+
 ## Links and images
 
 Both are dropped by default, because they are noise for a summarize/rewrite task and they inflate the character budget.

package/skills/web-screenshot/scripts/_media_screenshot/bootstrap.py

@@ -21,11 +21,15 @@ def _ensure_playwright_pkg() -> None:
     _pip_install("playwright")
 
 
-def ensure_chromium() -> None:
-    """Install the chromium browser via `playwright install`."""
-    print("[bootstrap] playwright install chromium ...", file=sys.stderr)
+def ensure_browser(name: str = "chromium") -> None:
+    """Install the given browser engine via `playwright install <name>`.
+
+    Must install the engine that is about to be launched: installing chromium
+    and then relaunching firefox fails the same way a second time.
+    """
+    print(f"[bootstrap] playwright install {name} ...", file=sys.stderr)
     subprocess.check_call(
-        [sys.executable, "-m", "playwright", "install", "chromium"]
+        [sys.executable, "-m", "playwright", "install", name]
     )
 
 

package/skills/web-screenshot/scripts/_media_screenshot/browser.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 from typing import Any
 
 from . import js_loader
-from .bootstrap import ensure_chromium
+from .bootstrap import ensure_browser
 
 
 def pick_browser_type(p, name: str | None):
@@ -42,15 +42,35 @@ def build_context_options(p, cfg: dict, record_video_dir: str | None) -> dict:
     return opts
 
 
+def _is_missing_executable(e: Exception) -> bool:
+    msg = str(e)
+    return "Executable doesn't exist" in msg or "playwright install" in msg.lower()
+
+
 def launch_with_browser_install(p, browser_name: str | None, launch_kwargs: dict | None = None):
     btype = pick_browser_type(p, browser_name)
+    engine = btype.name  # "chromium" | "firefox" | "webkit"
+    try:
+        return btype.launch(**(launch_kwargs or {}))
+    except Exception as e:
+        if not _is_missing_executable(e):
+            raise
+    # 引擎没装：装「这次要启动的那个」引擎再试一次。装不上 / 装了仍起不来时给一句
+    # 能据以行动的话，而不是 30 行 Playwright traceback。
+    hint = (
+        f"浏览器引擎 {engine} 在当前环境不可用。"
+        + ("去掉 browser 参数改用默认的 chromium 即可。" if engine != "chromium"
+           else "请运行 `python3 -m playwright install chromium`。")
+    )
+    try:
+        ensure_browser(engine)
+    except Exception as e:
+        raise SystemExit(f"{hint}\n（自动安装失败：{type(e).__name__}: {str(e).splitlines()[0] if str(e) else ''}）")
     try:
         return btype.launch(**(launch_kwargs or {}))
     except Exception as e:
-        msg = str(e)
-        if "Executable doesn't exist" in msg or "playwright install" in msg.lower():
-            ensure_chromium()
-            return btype.launch(**(launch_kwargs or {}))
+        if _is_missing_executable(e):
+            raise SystemExit(hint)
         raise
 
 

package/skills/web-screenshot/scripts/_media_screenshot/reader.py

@@ -12,12 +12,74 @@ disk so nothing is actually lost.
 from __future__ import annotations
 
 import json
+import sys
 from pathlib import Path
+from urllib.parse import urlsplit
 
 from . import js_loader
 from .bootstrap import ensure_runtime
 from .browser import apply_pre_action_waits, build_context_options, launch_with_browser_install
 
+# 读正文只需要 HTML 和（SPA 场景下）脚本 / 接口；图片、字体、媒体、样式表一律不拉。
+# 抽取逻辑只读 DOM 文本与属性（img 的 src 照样在），不依赖布局。
+_SKIPPED_RESOURCE_TYPES = {"image", "media", "font", "stylesheet"}
+# 单个子资源的拉取上限。浏览器要等 defer 脚本 / 阻塞样式表下载完才触发
+# DOMContentLoaded，一个从本机出口挂死的 CDN 就能让整页永远「打不开」
+# （2026-10-06：新加坡出口读腾讯云社区文章，_next chunk 与广州 COS 资源全部挂起）。
+# 超过上限的请求被 abort，浏览器跳过它继续解析。
+_SUBRESOURCE_TIMEOUT_MS = 8000
+# 拿到主文档响应头之后，最多再等这么久的 DOMContentLoaded；到点不报错，按当前 DOM 抽取。
+_DOM_READY_TIMEOUT_MS = 15000
+
+
+class _SubresourceGate:
+    """page.route 处理器：丢弃不需要的资源，给其余子资源加单请求超时。"""
+
+    def __init__(self) -> None:
+        self.stalled: list[str] = []
+
+    def __call__(self, route) -> None:
+        req = route.request
+        if req.is_navigation_request():
+            route.continue_()
+            return
+        if req.resource_type in _SKIPPED_RESOURCE_TYPES:
+            route.abort()
+            return
+        try:
+            resp = route.fetch(timeout=_SUBRESOURCE_TIMEOUT_MS)
+        except Exception:
+            self.stalled.append(urlsplit(req.url).hostname or "?")
+            try:
+                route.abort()
+            except Exception:
+                pass  # 页面已关闭 / 已导航走
+            return
+        try:
+            route.fulfill(response=resp)
+        except Exception:
+            pass
+
+    def summary(self) -> str:
+        hosts = sorted(set(self.stalled))
+        shown = ", ".join(hosts[:5]) + (" …" if len(hosts) > 5 else "")
+        return f"{len(self.stalled)} 个子资源超过 {_SUBRESOURCE_TIMEOUT_MS // 1000}s 未返回已跳过（{shown}）"
+
+
+def _navigation_error(url: str, e: Exception) -> SystemExit:
+    # 一条模型能据以行动的错误，胜过 30 行 Playwright traceback。
+    # 走到这里说明连主文档的响应头都没拿到（子资源挂死已由 _SubresourceGate 兜住），
+    # 问题在网络层或对方服务器；换参数重试几乎不可能有不同结果，要明确告诉调用方别再试。
+    first = str(e).splitlines()[0] if str(e) else ""
+    kind = "超时未响应" if type(e).__name__ == "TimeoutError" else "连接失败"
+    return SystemExit(
+        f"打开页面失败（{kind}）：{url}\n"
+        f"{type(e).__name__}: {first}\n"
+        "服务器没有返回页面：多半是从当前网络出口无法访问该站点，或站点拒绝了本机 IP。"
+        "加大 timeout、换 user_agent / device / browser 通常不会有不同结果，不要对同一 URL 反复重试；"
+        "请让用户直接粘贴正文，或换一个可访问的链接。"
+    )
+
 
 def extract(cfg: dict) -> dict:
     """Load cfg['url'] and return the raw extraction dict from the page."""
@@ -38,19 +100,24 @@ def extract(cfg: dict) -> dict:
             if cfg.get("timeout"):
                 context.set_default_timeout(cfg["timeout"])
             page = context.new_page()
+            gate = _SubresourceGate()
+            page.route("**/*", gate)
             try:
                 try:
-                    response = page.goto(cfg["url"], wait_until="domcontentloaded")
+                    # commit = 拿到主文档响应头即返回，不让任何子资源决定「页面打不打得开」。
+                    response = page.goto(cfg["url"], wait_until="commit")
                 except Exception as e:
-                    # 一条模型能据以行动的错误，胜过 30 行 Playwright traceback。
-                    # 导航失败是这个 skill 最常见的失败形态（打不开 / 超时 / DNS），
-                    # 让它读起来像"这个网址打不开"，而不是像程序崩了。
-                    raise SystemExit(
-                        f"打开页面失败：{cfg['url']}\n"
-                        f"{type(e).__name__}: {str(e).splitlines()[0]}\n"
-                        "可能是网络不可达、站点屏蔽了无头浏览器，或加载超过了超时时间。"
-                        "可尝试加大 --timeout、换 --user-agent，或确认该 URL 在本机能打开。"
-                    )
+                    raise _navigation_error(cfg["url"], e)
+                dom_ready = True
+                try:
+                    page.wait_for_load_state("domcontentloaded", timeout=_DOM_READY_TIMEOUT_MS)
+                except Exception:
+                    dom_ready = False
+                if gate.stalled or not dom_ready:
+                    note = gate.summary() if gate.stalled else "部分子资源未返回"
+                    if not dom_ready:
+                        note += f"；页面 {_DOM_READY_TIMEOUT_MS // 1000}s 内未完成解析，按当前已加载的 DOM 抽取"
+                    print(f"[web_read] {note}", file=sys.stderr)
                 status = response.status if response else None
                 if status is not None and status >= 400:
                     # Keep going: many sites serve real content under a 403/404

package/skills/web-screenshot/version.json

@@ -2,6 +2,6 @@
   "skillName": "web-screenshot",
   "repoName": "agent-skill-media-maker",
   "skillId": "555",
-  "version": "V7",
+  "version": "V8",
   "skillDescription": "Web-page screenshot skill (still images only, png/jpg), built on Playwright Python — captures any URL to a local image file.\nSupports: full-page / viewport / element / region capture, device emulation, waiting for dynamic content, hiding or masking distracting elements, and static annotations (highlight box / arrow / caption / numbered sequence / redact / code-line highlight).\n\nImages only (`.png` / `.jpg`). For video (`.webm` / screen recording / storyboard clips) use web-record / `web_record`.\n\nUse this skill immediately whenever the user asks for any of:\n- Web page screenshot, screen capture, full-page screenshot, long screenshot\n- Capture a specific element / region, partial screenshot, focus on an area\n- Hide or mask elements before capturing (cookie banner, sensitive information)\n- Annotate a still screenshot (highlight box / arrow / label / caption bar / numbering)\n- Highlight lines L5-L20 of a file and screenshot it\n- Wait for an element to appear, then capture\n- Mobile / device-emulated screenshot (iPhone / Pixel, etc.)\n- Capture with cookies / a logged-in session / storageState\n\nEven when the user does not say \"playwright\", any request to screenshot a URL and get a local image file should route here."
 }