@remixmate/cli 0.1.2 → 0.9.5

package/skills/gen-script/scripts/gen_script.py

@@ -56,13 +56,6 @@ try:
 except ImportError:
     _HAS_REGISTRY_LOADER = False
 
-try:
-    # Centralized monorepo-path resolver living in template-registry/scripts/;
-    # the import works because the same sys.path.insert above pointed at it.
-    from template_paths import monorepo_template_src_dir as _monorepo_template_src_dir
-except ImportError:
-    _monorepo_template_src_dir = None
-
 VALID_PLATFORMS = ["douyin", "xiaohongshu", "bilibili", "wechat", "youtube", "generic"]
 VALID_RATIOS = ["16:9", "9:16", "1:1", "4:3", "3:4", "21:9"]
 VALID_PURPOSES = ["opening", "point", "example", "explanation", "highlight", "cta", "ending"]
@@ -322,9 +315,9 @@ def generate_image_prompt(
 def _load_template_config(template_id: str) -> dict | None:
     """Load template definition for the given template ID.
 
-    解析顺序（与 match_template / template_binder 保持一致）：
-      1. 通过 registry_loader 从 monorepo template-library/packages/metadata/registry.json
-         （或 VIDEO_TEMPLATE_REGISTRY[_URL] 环境变量）加载，并按 templateId 匹配。
+    解析顺序：
+      1. 通过 registry_loader 从 ab-api（单一数据源，URL 取
+         VIDEO_TEMPLATE_REGISTRY_URL 或按 MM_API_BASE_URL 推导）加载，按 templateId 匹配。
       2. 兜底：旧路径 template-registry/video_dsl/templates/<id>/template.json
          （仅在仓库还残留旧目录时使用）。
     返回完整 template dict（含 supportedAspectRatios / assetRequirements / slotMapping 等），
@@ -384,6 +377,29 @@ def _template_primary_visual_type(template_config: dict | None) -> str:
     return "none"
 
 
+def _template_needs_narration(template_config: dict | None) -> bool:
+    """模板是否需要旁白（TTS）。
+
+    默认 True —— 保持历史行为：每个场景挂一个 gen-voice 素材 + 写入
+    ``audio.narration`` 骨架，由 agent 后续填真实文案。
+
+    模板可通过 ``capabilities.needsNarration=false`` 声明"纯视觉 / 无旁白"
+    （如单图 Ken Burns、BGM-only 展示）。此时 gen_script：
+      - 不生成 gen-voice 素材；
+      - 场景不写 ``audio.narration``。
+    于是骨架的 narrationSceneCount=0，ab-agent 的 prepare_video_assets 预校验
+    会直接放行，不再强制用户为每个场景填旁白（与 spotlight-card 等无配音模板
+    走的是同一条 pass-through 路径）。
+
+    兼容历史脏数据：部分模板的 ``capabilities`` 是空列表 ``[]``（而非 dict），
+    统一按"未声明"处理 → 返回 True。仅当显式为 JSON ``false`` 时才关闭旁白。
+    """
+    caps = (template_config or {}).get("capabilities")
+    if not isinstance(caps, dict):
+        return True
+    return caps.get("needsNarration", True) is not False
+
+
 def _template_needs_image(template_config: dict | None) -> bool:
     """Check if a template requires image assets.
 
@@ -396,23 +412,98 @@ def _template_needs_image(template_config: dict | None) -> bool:
 
 
 # ═══════════════════════════════════════════════════════════════════════════════
-# Template-as-Contract: input-schema driven DSL assembly
+# Template-as-Contract: capabilities-driven DSL assembly
 # ═══════════════════════════════════════════════════════════════════════════════
 #
-# 当模板目录下存在 input-schema.json 时，gen_script 用该 schema 动态组装 DSL，
-# 无需为每个模板写 if-else 分支。模板作者只需维护 input-schema.json + dsl-example.json。
+# 模板的所有差异都通过 template.json 的 ``capabilities`` 声明（registry 是单一数据源，
+# 内置模板与个人 OSS 模板同源可达）。gen_script 把 capabilities 归一化成一份 contract，
+# 再用同一条流水线组装 DSL —— 不再有 input-schema.json，也不再有 if template_id==X 分支。
+#
+# 归一化 contract 字段（全部可缺省，缺省值保证"未声明能力"的模板走通用图文旁白）：
+#   - needs_narration   bool         capabilities.needsNarration，默认 True
+#   - scene_strategy    str          capabilities.sceneStrategy ∈ {arc, single, fixed}，默认 arc
+#   - fixed_scenes      list[dict]   capabilities.fixedScenes（single/fixed 用；缺省单 opening）
+#   - payload_style     str          capabilities.payloadStyle ∈ {visual-overlay, slide, carousel-caption}
+#   - duration_strategy str          capabilities.durationStrategy ∈ {explicit, fit-caption}
+#   - payload_defaults  dict         capabilities.payloadDefaults（carousel-caption 的轮播/字幕默认值）
+#   - primary_visual_type / default_layout 由 assetRequirements / capabilities 推导
+
+
+def _resolve_contract(template_config: dict | None) -> dict:
+    """把 template.json 的 capabilities 归一化成一份装配 contract。
+
+    宽容读取：capabilities 缺失 / 非 dict（历史脏数据可能是 ``[]``）一律按"未声明"
+    处理，回退到通用图文旁白（arc + visual-overlay + 旁白开），保证没有声明能力的
+    模板与无模板场景行为一致。
+    """
+    caps = (template_config or {}).get("capabilities")
+    caps = caps if isinstance(caps, dict) else {}
+
+    needs_narration = caps.get("needsNarration", True) is not False
 
+    scene_strategy = caps.get("sceneStrategy")
+    if scene_strategy not in ("arc", "single", "fixed"):
+        scene_strategy = "arc"
 
-def _locate_template_dir(template_id: str) -> str | None:
-    """定位模板源码目录（template-library/packages/templates/src/<id>/）。
+    primary_visual_type = _template_primary_visual_type(template_config)
+
+    payload_style = caps.get("payloadStyle")
+    if payload_style not in ("visual-overlay", "slide", "carousel-caption"):
+        payload_style = "slide" if primary_visual_type == "none" else "visual-overlay"
+
+    duration_strategy = caps.get("durationStrategy")
+    if duration_strategy not in ("explicit", "fit-caption"):
+        duration_strategy = "explicit"
+
+    fixed_scenes = caps.get("fixedScenes")
+    if not isinstance(fixed_scenes, list) or not fixed_scenes:
+        # single / fixed 未显式给 fixedScenes 时退化为单 opening 场景
+        fixed_scenes = [{"purpose": "opening"}] if scene_strategy in ("single", "fixed") else []
+
+    payload_defaults = caps.get("payloadDefaults")
+    payload_defaults = payload_defaults if isinstance(payload_defaults, dict) else {}
+
+    return {
+        "needs_narration": needs_narration,
+        "scene_strategy": scene_strategy,
+        "fixed_scenes": fixed_scenes,
+        "payload_style": payload_style,
+        "duration_strategy": duration_strategy,
+        "payload_defaults": payload_defaults,
+        "primary_visual_type": primary_visual_type,
+        "default_layout": caps.get("defaultLayout"),
+    }
 
-    路径解析已集中到 ``template_paths.monorepo_template_src_dir``；
-    当 helper 不可用（template-registry/scripts/ 不在 sys.path）时回退到 None,
-    与原始函数"找不到就返回 None"的语义一致。
+
+def _plan_contract_scenes(
+    contract: dict, topic: str, duration: int, scene_count: int | None, language: str
+) -> list:
+    """按 contract.scene_strategy 规划场景列表。
+
+      - arc    : 沿用 plan_scenes 叙事弧（opening → point* → cta，最少 3 段）。
+      - single : 单场景（默认 opening），整段时长归一个场景。
+      - fixed  : 按 capabilities.fixedScenes 顺序展开，时长均分。
+
+    single / fixed 完全绕开 arc 的"最少 3 段"下限 —— 单图 Ken Burns / 打字机卡片
+    这类模板由此能产出真正的单场景，而不再被强行补到 3 段。``--scenes`` 只对 arc 生效。
     """
-    if _monorepo_template_src_dir is None:
-        return None
-    return _monorepo_template_src_dir(template_id)
+    if contract["scene_strategy"] == "arc":
+        return plan_scenes(topic, duration, scene_count, False, language=language)
+
+    fixed = contract["fixed_scenes"] or [{"purpose": "opening"}]
+    n = len(fixed)
+    per = max(1, round(duration / n))
+    plans = []
+    for i, fs in enumerate(fixed):
+        purpose = fs.get("purpose", "opening") if isinstance(fs, dict) else "opening"
+        if purpose == "opening":
+            label = _localize_label(language, "label_opening")
+        elif purpose == "cta":
+            label = _localize_label(language, "label_cta")
+        else:
+            label = _localize_label(language, "label_point", n=i)
+        plans.append({"purpose": purpose, "duration": per, "label": label})
+    return plans
 
 
 def _plain_len(text: str) -> int:
@@ -480,27 +571,9 @@ def _estimate_fit_caption_duration(custom_payload: dict) -> float:
     return recommended
 
 
-def _load_input_schema(template_id: str) -> dict | None:
-    """Load input-schema.json for a template. Returns None if not found."""
-    tpl_dir = _locate_template_dir(template_id)
-    if not tpl_dir:
-        return None
-    schema_file = os.path.join(tpl_dir, "input-schema.json")
-    if not os.path.isfile(schema_file):
-        return None
-    try:
-        with open(schema_file, "r", encoding="utf-8") as f:
-            return json.load(f)
-    except (OSError, json.JSONDecodeError) as exc:
-        print(f"⚠️  failed to load input-schema.json for {template_id}: {exc}", file=sys.stderr)
-        return None
-
-
-def _build_dsl_from_input_schema(
+def _build_carousel_caption_dsl(
     *,
     template_id: str,
-    template_config: dict,
-    input_schema: dict,
     topic: str,
     headline: str,
     subheadline: str,
@@ -511,22 +584,19 @@ def _build_dsl_from_input_schema(
     style: str,
     ratio: str,
     resolution: str,
-    voice_id: str,
     output_language: str,
     resolved_voice_id: str,
+    narration_enabled: bool,
+    payload_defaults: dict,
+    duration_strategy: str | None,
 ) -> dict:
-    """Schema-driven DSL assembly.
+    """carousel-caption 装配（spotlight-card 类：单场景、图/视频轮播 + 打字机）。
 
-    Uses the template's input-schema.json + defaults to build a complete DSL
-    with the correct customPayload structure. No template-specific if-else.
+    所有差异来自归一化 contract（capabilities.payloadDefaults / durationStrategy /
+    needsNarration），不再读 input-schema.json，也没有 if template_id==X 分支。
+    轮播素材由调用方在 carousel_items 里直接给 URL（existing 资产），不触发 AI 生图。
     """
-    defaults = input_schema.get("defaults", {})
-
-    # 旁白开关：部分模板（如 spotlight-card）是打字机 / 画面驱动，刻意无配音。
-    # 由 input-schema.json 的 narration.enabled 声明，缺省 True 保持其它 schema
-    # 模板的向后兼容。关闭时不产出 gen-voice 音频资产，scene 也不带 audio.narration，
-    # 这样 prepare_video_assets 不会触发 TTS、render_video 也不会按 TTS 拉长场景时长。
-    narration_enabled = bool(input_schema.get("narration", {}).get("enabled", True))
+    defaults = payload_defaults or {}
 
     # ── Build assets from carousel_items ──────────────────────────────────
     assets = []
@@ -597,15 +667,9 @@ def _build_dsl_from_input_schema(
                                      label="", topic=topic, duration=duration)
 
     # ── Effective scene duration ──────────────────────────────────────────
-    # fit-caption 策略（input-schema.sceneStrategy.fixedScenes[].durationStrategy）：
-    # 时长由打字机自然节奏决定，而不是盲取调用方传入的 targetDuration。
+    # fit-caption 策略：时长由打字机自然节奏决定，而不是盲取调用方传入的 targetDuration。
     # 这是 spotlight-card 这类打字机/画面驱动模板的核心——没有旁白来"撑"时长，
     # 必须由 caption 自己定，否则文字打完后画面会静止到 targetDuration。
-    scene_strategy = input_schema.get("sceneStrategy", {})
-    fixed_scenes = scene_strategy.get("fixedScenes", [])
-    duration_strategy = (
-        fixed_scenes[0].get("durationStrategy") if fixed_scenes else None
-    )
     effective_duration = duration
     if duration_strategy == "fit-caption":
         est = _estimate_fit_caption_duration(custom_payload)
@@ -731,9 +795,9 @@ def build_dsl(
     When template_id is provided, loads the template config and adapts the DSL
     structure to match the template's assetRequirements and scene patterns.
 
-    If the template has an input-schema.json AND the caller provides structured
-    inputs (carousel_items / caption_lines), the schema-driven assembly path is
-    used — producing a template-native DSL without any template-specific if-else.
+    模板差异全部来自归一化 contract（capabilities）：payloadStyle=carousel-caption
+    走单场景轮播+打字机装配；其余按 sceneStrategy（arc/single/fixed）+ visual-overlay/
+    slide 走统一场景循环。无 input-schema.json、无 if template_id==X 分支。
 
     headline / subheadline 让作者显式提供画面上的"短主标题 + 副标题"。
     DSL 元字段命名约定：
@@ -744,48 +808,17 @@ def build_dsl(
     注意：subtitle（CC 字幕）由 global.subtitle 与 render-plan.subtitleSegments
     单独承载，与 subheadline 完全是两个东西，命名上刻意分开避免歧义。
     """
-    # Load template config to determine asset requirements
+    # Load template config（registry 单一数据源）→ 归一化 contract
     template_config = _load_template_config(template_id) if template_id else None
+    contract = _resolve_contract(template_config)
 
-    # ── Schema-driven path: if input-schema.json exists AND structured inputs provided ──
-    if template_id and (carousel_items or caption_lines):
-        input_schema = _load_input_schema(template_id)
-        if input_schema and template_config:
-            # Resolve language + voice (same logic as generic path)
-            output_language, template_default_voice_id = _resolve_template_language_meta(template_config)
-            resolved_voice_id = _resolve_voice_id(voice_id, template_default_voice_id, output_language)
-            if resolved_voice_id != voice_id:
-                print(
-                    f"ℹ️  voice resolution: cli={voice_id!r} → resolved={resolved_voice_id!r} "
-                    f"(templateDefault={template_default_voice_id!r}, language={output_language})",
-                    file=sys.stderr,
-                )
-            effective_headline = (headline or "").strip() or topic
-            effective_subheadline = (subheadline or "").strip()
-            print(
-                f"ℹ️  using input-schema driven assembly for template {template_id}",
-                file=sys.stderr,
-            )
-            return _build_dsl_from_input_schema(
-                template_id=template_id,
-                template_config=template_config,
-                input_schema=input_schema,
-                topic=topic,
-                headline=effective_headline,
-                subheadline=effective_subheadline,
-                carousel_items=carousel_items or [],
-                caption_lines=caption_lines or [],
-                duration=duration,
-                platform=platform,
-                style=style,
-                ratio=ratio,
-                resolution=resolution,
-                voice_id=voice_id,
-                output_language=output_language,
-                resolved_voice_id=resolved_voice_id,
-            )
-    primary_visual_type = _template_primary_visual_type(template_config)
-    has_visual = primary_visual_type in ("image", "video")
+    primary_visual_type = contract["primary_visual_type"]
+    payload_style = contract["payload_style"]
+    # visual-overlay 模板才生成视觉素材并用 visuals.background；slide / carousel-caption 不走。
+    has_visual = payload_style == "visual-overlay"
+    # 旁白是模板能力（capabilities.needsNarration）。声明为 false 的模板（纯视觉 /
+    # BGM-only，如单图 Ken Burns）不分配 gen-voice 素材、场景不写 audio.narration。
+    needs_narration = contract["needs_narration"]
 
     # ── Resolve template-driven output language + voice ────────────────────
     # outputLanguage is owned by the template (template.json). Missing/invalid
@@ -799,11 +832,37 @@ def build_dsl(
             file=sys.stderr,
         )
 
-    # 缺省值：headline 退回 topic（向后兼容），subheadline 默认空字符串
+    # 缺省值：headline 退回 topic，subheadline 默认空字符串
     effective_headline = (headline or "").strip() or topic
     effective_subheadline = (subheadline or "").strip()
 
-    scene_plans = plan_scenes(topic, duration, scene_count, allow_digital_human, language=output_language)
+    # ── carousel-caption 模板（单场景、图/视频轮播 + 打字机）单独装配并直接返回 ──
+    if payload_style == "carousel-caption":
+        print(
+            f"ℹ️  contract: payloadStyle=carousel-caption for template {template_id}",
+            file=sys.stderr,
+        )
+        return _build_carousel_caption_dsl(
+            template_id=template_id,
+            topic=topic,
+            headline=effective_headline,
+            subheadline=effective_subheadline,
+            carousel_items=carousel_items or [],
+            caption_lines=caption_lines or [],
+            duration=duration,
+            platform=platform,
+            style=style,
+            ratio=ratio,
+            resolution=resolution,
+            output_language=output_language,
+            resolved_voice_id=resolved_voice_id,
+            narration_enabled=needs_narration,
+            payload_defaults=contract["payload_defaults"],
+            duration_strategy=contract["duration_strategy"],
+        )
+
+    # ── 其余模板：统一场景规划（arc 叙事弧 / single / fixed）+ 统一装配循环 ──────
+    scene_plans = _plan_contract_scenes(contract, topic, duration, scene_count, output_language)
 
     assets = []
     scenes = []
@@ -815,11 +874,14 @@ def build_dsl(
             visual_asset_id = f"video-{scene_id}"
         else:
             visual_asset_id = f"img-{scene_id}"
-        narration_asset_id = f"narration-{scene_id}"
-        narration_text = estimate_narration_text(plan["label"], plan["purpose"], plan["duration"], topic, language=output_language)
+        narration_asset_id = f"narration-{scene_id}" if needs_narration else None
+        narration_text = (
+            estimate_narration_text(plan["label"], plan["purpose"], plan["duration"], topic, language=output_language)
+            if needs_narration else ""
+        )
 
-        # 根据模板 assetRequirements 生成对应类型的视觉素材
-        if primary_visual_type == "image":
+        # 仅 visual-overlay 模板生成视觉素材（slide 无视觉素材，carousel-caption 已提前返回）
+        if has_visual and primary_visual_type == "image":
             if stub_image_url:
                 assets.append({
                     "assetId": visual_asset_id,
@@ -848,7 +910,7 @@ def build_dsl(
                     "status": "planned",
                     "payload": img_payload,
                 })
-        elif primary_visual_type == "video":
+        elif has_visual and primary_visual_type == "video":
             if stub_video_url:
                 assets.append({
                     "assetId": visual_asset_id,
@@ -881,15 +943,17 @@ def build_dsl(
         # narration text 不再在 audio asset 的 payload 里冗余存放——
         # 唯一来源是下游 scenes[].audio.narration.text，render_video 在
         # 调用 TTS skill 前会按 assetRef 回查 scene 文本注入。
-        assets.append({
-            "assetId": narration_asset_id,
-            "type": "audio",
-            "source": "gen-voice",
-            "status": "planned",
-            "payload": {
-                "voiceId": resolved_voice_id,
-            },
-        })
+        # 模板声明 needsNarration=false 时，完全不生成 gen-voice 素材。
+        if needs_narration:
+            assets.append({
+                "assetId": narration_asset_id,
+                "type": "audio",
+                "source": "gen-voice",
+                "status": "planned",
+                "payload": {
+                    "voiceId": resolved_voice_id,
+                },
+            })
 
         if has_visual:
             layout = "text-overlay" if plan["purpose"] in ("opening", "cta") else "full-visual"
@@ -916,33 +980,35 @@ def build_dsl(
                 if effective_subheadline:
                     text_layers.append({"role": "subheadline", "content": effective_subheadline, "animation": "fade-in"})
 
-            scenes.append({
+            scene = {
                 "id": scene_id,
                 "purpose": plan["purpose"],
                 "duration": plan["duration"],
                 "layout": layout,
                 "visuals": {"background": {"assetRef": visual_asset_id}},
-                "audio": {
+                "textLayers": text_layers,
+                "animationHints": {
+                    "entrance": "fade",
+                    "motion": "kenburns-in" if idx % 2 == 0 else "kenburns-out",
+                },
+            }
+            if needs_narration:
+                scene["audio"] = {
                     "narration": {
                         "text": narration_text,
                         "assetRef": narration_asset_id,
                         # 骨架标记：scenes[].audio.narration.text 同样需要被真实旁白替换
                         "needsFill": True,
                     },
-                },
-                "textLayers": text_layers,
-                "animationHints": {
-                    "entrance": "fade",
-                    "motion": "kenburns-in" if idx % 2 == 0 else "kenburns-out",
-                },
-            })
+                }
+            scenes.append(scene)
         else:
             # The "no-visual" branch labels each scene with a layout hint.
             # Historical fallback was hardcoded "html-slide" — when no template
             # was specified, every audio-only scene defaulted to html-slide
             # styling. We replace the hardcoded fallback chain with:
             #   1. template.capabilities.defaultLayout   ⇐ the template tells
-            #      ab-skill what layout name it wants on its no-visual scenes
+            #      remixmate what layout name it wants on its no-visual scenes
             #   2. template_id                            ⇐ legacy: pass id as
             #      layout name (existing behavior when no capability declared)
             #   3. "html-slide"                           ⇐ absolute fallback
@@ -966,22 +1032,24 @@ def build_dsl(
 
             custom_payload = _build_custom_payload(plan["purpose"], topic, plan["label"], idx, len(scene_plans), language=output_language)
 
-            scenes.append({
+            scene = {
                 "id": scene_id,
                 "purpose": plan["purpose"],
                 "duration": plan["duration"],
                 "layout": layout,
-                "audio": {
+                "textLayers": text_layers,
+                "customPayload": custom_payload,
+            }
+            if needs_narration:
+                scene["audio"] = {
                     "narration": {
                         "text": narration_text,
                         "assetRef": narration_asset_id,
                         # 骨架标记：scenes[].audio.narration.text 同样需要被真实旁白替换
                         "needsFill": True,
                     },
-                },
-                "textLayers": text_layers,
-                "customPayload": custom_payload,
-            })
+                }
+            scenes.append(scene)
 
     dsl = {
         "version": "v1alpha1",
@@ -1001,8 +1069,10 @@ def build_dsl(
             "aspectRatio": ratio,
             "resolution": resolution,
             "fps": 30,
-            "subtitle": {"enabled": True, "style": "bottom"},
-            "narration": {"voiceId": resolved_voice_id, "speed": 1.0},
+            # 无配音模板：关闭 CC 字幕（字幕段是 narration→TTS 的派生物），并省略
+            # global.narration，避免下游误判存在旁白。
+            "subtitle": {"enabled": needs_narration, "style": "bottom"},
+            **({"narration": {"voiceId": resolved_voice_id, "speed": 1.0}} if needs_narration else {}),
             "bgm": {"enabled": True, "volume": 0.12},
         },
         "assets": assets,
@@ -1075,9 +1145,9 @@ Examples:
         default=None,
         help="Media URL for the template's carousel/gallery. Can be repeated: "
              "--carousel-items url1 --carousel-items url2. "
-             "For templates with input-schema.json (e.g. spotlight-card), these URLs "
-             "are placed directly into customPayload.carousel.items as existing assets, "
-             "bypassing AI image generation entirely.",
+             "For carousel-caption templates (capabilities.payloadStyle=carousel-caption, "
+             "e.g. spotlight-card), these URLs are placed directly into "
+             "customPayload.carousel.items as existing assets, bypassing AI image generation entirely.",
     )
     parser.add_argument(
         "--caption-lines",
@@ -1085,8 +1155,9 @@ Examples:
         default=None,
         help="Bottom typewriter text line. Can be repeated: "
              "--caption-lines 'line1' --caption-lines 'line2'. "
-             "For templates with input-schema.json (e.g. spotlight-card), these are placed "
-             "into customPayload.caption.lines. Supports **emphasis** syntax.",
+             "For carousel-caption templates (capabilities.payloadStyle=carousel-caption, "
+             "e.g. spotlight-card), these are placed into customPayload.caption.lines. "
+             "Supports **emphasis** syntax.",
     )
 
     args = parser.parse_args()

package/skills/gen-script/skill.json

@@ -27,7 +27,7 @@
       "carousel_items": {
         "type": "array",
         "items": { "type": "string" },
-        "description": "Media URLs for the template's image/video carousel (e.g. spotlight-card's middle carousel). When provided together with a template_id that has an input-schema.json, these URLs are placed directly into customPayload.carousel.items as existing assets — NO AI image generation is triggered. **Must** pass when the user explicitly provides image/video URLs for carousel-style templates (spotlight-card, etc.). Each element is a full URL string."
+        "description": "Media URLs for the template's image/video carousel (e.g. spotlight-card's middle carousel). When provided together with a template_id whose capabilities.payloadStyle=carousel-caption, these URLs are placed directly into customPayload.carousel.items as existing assets — NO AI image generation is triggered. **Must** pass when the user explicitly provides image/video URLs for carousel-style templates (spotlight-card, etc.). Each element is a full URL string."
       },
       "caption_lines": {
         "type": "array",

package/skills/gen-script/version.json

@@ -2,6 +2,6 @@
   "skillName": "gen-script",
   "repoName": "agent-skill-media-maker",
   "skillId": "474",
-  "version": "V8",
+  "version": "V11",
   "skillDescription": "视频脚本生成技能，将用户主题转化为结构化 Video DSL（JSON），描述视频的完整结构、素材需求与叙事逻辑。\n\n当用户提到以下任何需求时，立即使用本 skill：\n- 帮我写视频脚本、生成视频脚本、视频策划、写分镜脚本\n- 做一个短视频、帮我规划视频内容、生成视频 DSL\n- 把主题转成视频结构、视频内容规划\n\n即使用户没有明确说「生成 DSL」，只要他们想要把一个主题变成视频内容结构，也要使用本 skill。"
 }

package/skills/gen-video/SKILL.md

@@ -19,7 +19,7 @@ triggers:
 
 Wraps ab-api's `POST /model/genVideo` (the same endpoint the web "Lingchuang AI Video" tool uses), authenticated with the **Tianyan privateToken**, routed through LiteLLM to **Seedance** or **Veo**. Generation is async — the handler submits the task and polls `/model/getVideoStatus` until completion.
 
-> This skill was migrated from a Python script to an ab-skill CLI HTTP handler (`entry.type: http`). The agent invocation is unchanged (same tool name `gen_video`, same params as in `skill.json`); local repro goes through `ab-skill gen-video ...`.
+> This skill was migrated from a Python script to an remixmate CLI HTTP handler (`entry.type: http`). The agent invocation is unchanged (same tool name `gen_video`, same params as in `skill.json`); local repro goes through `remixmate gen-video ...`.
 
 ## Models
 
@@ -72,7 +72,7 @@ No skill-local env file — the executing process inherits the system environmen
 ### Seedance text-to-video (default model)
 
 ```bash
-ab-skill gen-video \
+remixmate gen-video \
   --prompt "<video description>" \
   --duration 5 \
   --ratio "16:9"
@@ -83,7 +83,7 @@ ab-skill gen-video \
 Frame images accept local file paths, HTTPS URLs, or data URIs (local files are base64-encoded into a data URI).
 
 ```bash
-ab-skill gen-video \
+remixmate gen-video \
   --prompt "<transition description>" \
   --first-frame ./start.png \
   --last-frame ./end.png \
@@ -94,7 +94,7 @@ ab-skill gen-video \
 ### Veo 3.1 high-resolution
 
 ```bash
-ab-skill gen-video \
+remixmate gen-video \
   --model veo \
   --prompt "<video description>" \
   --duration 8 \
@@ -105,7 +105,7 @@ ab-skill gen-video \
 ### Veo 3.1 Fast for rapid iteration
 
 ```bash
-ab-skill gen-video \
+remixmate gen-video \
   --model veo-fast \
   --prompt "<video description>" \
   --duration 6
@@ -116,7 +116,7 @@ ab-skill gen-video \
 Pass `--reference` multiple times (Veo only, up to 3).
 
 ```bash
-ab-skill gen-video \
+remixmate gen-video \
   --model veo \
   --prompt "<video description>" \
   --reference ./ref1.png \

package/skills/gen-video/version.json

@@ -2,6 +2,6 @@
   "skillName": "gen-video",
   "repoName": "agent-skill-media-maker",
   "skillId": "339",
-  "version": "V7",
+  "version": "V8",
   "skillDescription": "AI 生视频技能，根据文字描述生成素材视频（调用 ab-api /model/genVideo，支持 Seedance 与 Veo）。\n\n当用户提到以下任何需求时，立即使用本 skill：\n- AI 生视频、文生视频、文字生成视频、生成一段视频、AI 制作视频\n- 使用 doubao / 豆包 / seedance、Veo、Google 等生成视频\n- 用户提供视频提示词并希望生成视频\n- 图生视频、首帧生成视频、参考图生成视频\n\n即使用户没有明确说「使用 AI」，只要他们想要根据描述生成视频，也要使用本 skill。"
 }

package/skills/gen-voice/SKILL.md

@@ -34,7 +34,7 @@ There is no skill-local env file — the executing process inherits the system e
 
 ## Operations
 
-> This skill was migrated from a Python script to an ab-skill CLI HTTP handler (`entry.type: http`). The agent invocation is unchanged (same tool name `gen_voice`, same params as in `skill.json`); local repro goes through `ab-skill gen-voice ...`. The legacy `--download` flag has been removed — audio URLs are persisted in the cloud and play directly.
+> This skill was migrated from a Python script to an remixmate CLI HTTP handler (`entry.type: http`). The agent invocation is unchanged (same tool name `gen_voice`, same params as in `skill.json`); local repro goes through `remixmate gen-voice ...`. The legacy `--download` flag has been removed — audio URLs are persisted in the cloud and play directly.
 
 1. **Text**: confirm what to synthesize. Punctuation drives pauses (commas short, periods long).
 2. **Voice**: if the user prefers a specific voice, run `--list-voices` first and pick a matching id.
@@ -43,13 +43,13 @@ There is no skill-local env file — the executing process inherits the system e
 ### List available voices
 
 ```bash
-ab-skill gen-voice --list-voices
+remixmate gen-voice --list-voices
 ```
 
 To inspect the local language-tagged fallback catalog used by the voice resolver (no remote API call), add `--local`:
 
 ```bash
-ab-skill gen-voice --list-voices --local
+remixmate gen-voice --list-voices --local
 ```
 
 The local catalog prints one voice per line as `<voice-id>\t<lang>\t<display-name>`.
@@ -57,13 +57,13 @@ The local catalog prints one voice per line as `<voice-id>\t<lang>\t<display-nam
 ### Default synthesis (URL output)
 
 ```bash
-ab-skill gen-voice --text "<text-to-synthesize>"
+remixmate gen-voice --text "<text-to-synthesize>"
 ```
 
 ### With voice + speed
 
 ```bash
-ab-skill gen-voice \
+remixmate gen-voice \
   --text "<text-to-synthesize>" \
   --voice-id "female-shaonv" \
   --speed 1.2
@@ -72,7 +72,7 @@ ab-skill gen-voice \
 ### JSON output (with subtitle timestamps)
 
 ```bash
-ab-skill gen-voice --text "<text-to-synthesize>" --json-output
+remixmate gen-voice --text "<text-to-synthesize>" --json-output
 ```
 
 ## Common CLI flags