[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CB09J3KEKPB3PC8RYERKHC":3,"skill-same:01M7CB09J3KEKPB3PC8RYERKHC":205},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7CB09J3KEKPB3PC8RYERKHC","hyperframes-media",null,"Audio and media assets for HyperFrames compositions, produced by one shared audio engine (`scripts\u002Faudio.mjs`) — multi-provider TTS (HeyGen \u002F ElevenLabs \u002F Kokoro local), background music + sound effects (HeyGen audio-library retrieval by default, with local Lyria \u002F MusicGen BGM generation and a bundled SFX library as the no-credential fallback), Whisper transcription, background removal, and caption authoring. Use for voiceover \u002F TTS, BGM, SFX \u002F sound effects, transcription, captions \u002F subtitles \u002F lyrics \u002F karaoke \u002F per-word styling, voice + provider selection, and music-mood prompting.","VideoVerses\u002FCuti-Harness","VideoVerses","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F175584708?v=4","01M7CAV1DS56HR4KMB99EX9KAH","01M7CAV1EC999NFVVG4K7N1VJS",74,"MIT","https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: hyperframes-media\ndescription: Audio and media assets for HyperFrames compositions, produced by one shared audio engine (`scripts\u002Faudio.mjs`) — multi-provider TTS (HeyGen \u002F ElevenLabs \u002F Kokoro local), background music + sound effects (HeyGen audio-library retrieval by default, with local Lyria \u002F MusicGen BGM generation and a bundled SFX library as the no-credential fallback), Whisper transcription, background removal, and caption authoring. Use for voiceover \u002F TTS, BGM, SFX \u002F sound effects, transcription, captions \u002F subtitles \u002F lyrics \u002F karaoke \u002F per-word styling, voice + provider selection, and music-mood prompting.\n---\n\n# HyperFrames Media\n\nCreate the audio and media assets a composition needs — voiceover (TTS), background music + sound effects, transcription, captions, background removal — then consume and animate that data in HTML. For placing assets into compositions, see `hyperframes-core`.\n\n## The audio engine — one source for TTS · BGM · SFX\n\nWorkflows do NOT hand-roll audio or vendor a copy. There is one engine — **`scripts\u002Faudio.mjs`** — that takes a neutral `audio_request.json` and writes `audio_meta.json` (plus assets under `assets\u002Fvoice|bgm|sfx`):\n\n```bash\n# \u003CMEDIA_DIR> = this skill's directory\nnode \u003CMEDIA_DIR>\u002Fscripts\u002Faudio.mjs --request .\u002Faudio_request.json --hyperframes . --out .\u002Faudio_meta.json\n```\n\nAll three capabilities degrade on **ONE switch** — whether a HeyGen credential is present (resolved from `$HEYGEN_API_KEY` \u002F `$HYPERFRAMES_API_KEY` \u002F `~\u002F.heygen`, **not** the CLI):\n\n| Capability | HeyGen credential present                          | absent                                               |\n| ---------- | -------------------------------------------------- | ---------------------------------------------------- |\n| TTS        | HeyGen Starfish REST (native word timestamps)      | → ElevenLabs → Kokoro (chain `transcribe` for words) |\n| BGM        | HeyGen music **retrieval**                         | Lyria → MusicGen local **generation** (detached)     |\n| SFX        | HeyGen sound-effects **retrieval** (min_score 0.4) | bundled 21-file library (`assets\u002Fsfx\u002F`)              |\n\n- **Request** (`audio_request.json`): `{ provider?, lang?, speed?, lines: [{ id, text, sfx?: [names] }], bgm: { mode?, query?, prompt? } }`. `id` joins each line back to the caller's model (a frame number, a scene id, …). `bgm.mode` = `retrieve | generate | none`; omit for auto (retrieve when credentialed, else generate). An **explicit** `retrieve` is strict — it skips rather than starting a detached generate (for callers with no `wait-bgm` step).\n- **Output** (`audio_meta.json`, id-keyed): `{ tts_provider, voice_id, bgm, bgm_pending, …, voices: [{ id, path, duration_s, words }], sfx: [{ id, name, file, source, offset_s, duration_s, volume }], total_duration_s }`.\n- `--only tts,bgm,sfx` runs a subset and **merges** into an existing `--out` (e.g. TTS+BGM early, SFX once cues exist).\n- BGM generate is spawned **detached** (`bgm_pending: true`) — run `scripts\u002Fwait-bgm.mjs` before assembling.\n- `scripts\u002Fheygen-tts.mjs` is a single-shot CLI over the same code (one text → wav + words) for when you just need HeyGen TTS without a request file.\n\nFull flag list + the `audio_meta.json` schema live in the header of `scripts\u002Faudio.mjs`. The references below cover the provider details and edge cases behind each capability.\n\n## Preflight — show sign-in status before any audio\n\n**Always run this before generating voice or BGM — inside a full workflow _or_ a one-off \"generate me a BGM\u002Fvoiceover\" request.** No HeyGen credential is **not** a reason to silently fall back to local engines: first recommend signing in and let the user decide. Run the shared preflight and **relay its output verbatim** — don't improvise your own \"missing key\" prompt, and don't offer to write keys into a per-repo `.env`:\n\n```bash\nnpx hyperframes auth status\n```\n\n- **Signed in** → it prints the account; proceed.\n- **Not signed in** (`exit 1` is expected here — \"not signed in\" is a normal state, not a failure) → it prints registration-first guidance. Recommend signing in: `npx hyperframes auth login` is browser OAuth — it **signs in and creates an account** (always available through this repo's CLI). To use an existing HeyGen API key (from app.heygen.com\u002Fsettings\u002Fapi), run `npx hyperframes auth login --api-key` — it saves to the shared `~\u002F.heygen` (no per-repo `.env`). The output also lists the local engines voice\u002FBGM will fall back to and a `pip` hint when deps are missing. **Relay this output as-is — don't paraphrase it into your own wording.** Then **STOP and wait** for the user to choose — sign in, or say \"go\" \u002F \"local\" to continue offline — **before generating anything.** This is a real decision point, not a passing note: don't fold it into another question, and don't proceed past it on your own. (Exception: in autonomous \u002F non-interactive mode, note the status and continue offline.)\n- `npx hyperframes auth status --json` returns `{ configured, recommended_action, offline_engines }` for deterministic branching.\n- **If the CLI can't run** (not on PATH and `npx` can't fetch it) → still **recommend signing in** (`npx hyperframes auth login`) and **STOP for the user's choice** — don't treat \"no credential\" as a silent green light for local generation.\n\nCredential resolution, full key priority, and the local-dependency list are in `references\u002Frequirements.md`.\n\n## Provider chains (the detail behind the engine)\n\n**TTS** — first available provider wins (the engine, or `npx hyperframes tts \"...\"`):\n\n| Order | Provider                      | Detected when                                | Word timestamps                                                  |\n| ----- | ----------------------------- | -------------------------------------------- | ---------------------------------------------------------------- |\n| 1     | HeyGen (Starfish)             | `$HEYGEN_API_KEY` \u002F `hyperframes auth login` | **Yes, native** — pass `--words narration.words.json` to capture |\n| 2     | ElevenLabs                    | `$ELEVENLABS_API_KEY` set                    | No — chain `transcribe` after                                    |\n| 3     | Kokoro-82M (local, 54 voices) | always (no key required)                     | No — chain `transcribe` after                                    |\n\n> The published `hyperframes tts` CLI is often the local-only build (its `--help` says \"Kokoro-82M\", no `--provider`\u002F`--words`) and silently falls back to Kokoro even with `$HEYGEN_API_KEY` set. That is why the engine's HeyGen path is the self-contained `scripts\u002Fheygen-tts.mjs` (REST), NOT the CLI; the CLI is used only for the Kokoro path. See `references\u002Ftts.md`.\n\n**BGM & SFX** — by default **retrieved** from the HeyGen audio library (`\u002Fv3\u002Faudio\u002Fsounds`), same credential as HeyGen TTS, with the no-credential fallback from the switch above:\n\n| Asset | HeyGen `type`                   | Lands in                                                   | Fallback (no credential)                                   |\n| ----- | ------------------------------- | ---------------------------------------------------------- | ---------------------------------------------------------- |\n| BGM   | `music`                         | `assets\u002Fbgm\u002Ftrack.mp3` (retrieve) · `track.wav` (generate) | Lyria \u002F MusicGen generation                                |\n| SFX   | `sound_effects` (min_score 0.4) | `assets\u002Fsfx\u002F\u003Cslug>.mp3`                                    | bundled 21-file library (`assets\u002Fsfx\u002F*` + `manifest.json`) |\n\nSee `references\u002Fbgm.md` and `references\u002Fsfx.md`.\n\n## Routing\n\n| Task                                                                | Read                                         |\n| ------------------------------------------------------------------- | -------------------------------------------- |\n| The audio engine — request\u002Fmeta schema, `--only`, the switch        | `scripts\u002Faudio.mjs` (header comment)         |\n| `npx hyperframes tts` \u002F `heygen-tts.mjs` — providers, voices, words | `references\u002Ftts.md`                          |\n| BGM — HeyGen retrieval + local Lyria \u002F MusicGen generation          | `references\u002Fbgm.md`                          |\n| SFX — HeyGen retrieval (min_score 0.4) + bundled local library      | `references\u002Fsfx.md`                          |\n| `npx hyperframes transcribe` — Whisper, model rules, output shape   | `references\u002Ftranscribe.md`                   |\n| `npx hyperframes remove-background` — transparent cutouts           | `references\u002Fremove-background.md`            |\n| TTS → transcription → captions (no recorded voiceover)              | `references\u002Ftts-to-captions.md`              |\n| Caption authoring — style detection, layout, word grouping, exit    | `references\u002Fcaptions\u002Fauthoring.md`           |\n| Transcript handling — input formats, quality gates, cleanup, APIs   | `references\u002Fcaptions\u002Ftranscript-handling.md` |\n| Caption motion — karaoke, marker effects, audio-reactive            | `references\u002Fcaptions\u002Fmotion.md`              |\n| Model caches, system dependencies, troubleshooting                  | `references\u002Frequirements.md`                 |\n\n## Non-negotiable rules\n\n- **One engine, no vendored copies.** Produce audio via `scripts\u002Faudio.mjs` (or `heygen-tts.mjs` for one-shot HeyGen TTS). Don't re-implement TTS\u002FBGM\u002FSFX inside a workflow — write an `audio_request.json` adapter and call the engine.\n- **\"HeyGen available\" = a resolvable credential, not the CLI.** The whole switch keys off `heygenCredential()`; the published `hyperframes tts` may be Kokoro-only, and there is no `hyperframes bgm` \u002F `hyperframes sfx` command at all.\n- **Voice IDs are provider-specific.** `am_michael` is Kokoro-only; HeyGen UUIDs don't work on Kokoro. If you pass `--voice`, also pin `--provider` to avoid silent provider drift when the user's env changes.\n- **Always pass `--model` to `transcribe`.** The CLI default `small.en` silently translates non-English audio. See `references\u002Ftranscribe.md` → \"Language Rule\".\n- **HeyGen returns word timestamps; ElevenLabs \u002F Kokoro do not.** The engine chains `transcribe` automatically for the latter two; standalone, pass `--words` to HeyGen or run `transcribe` against the audio file.\n- **Captions consume the flat word-array format** with `{ id, text, start, end }`. See `references\u002Ftranscribe.md` → \"Output Shape\".\n- **`remove-background --background-output` is hole-cut, not inpainted.** For \"scene without the person\", a different tool is needed. See `references\u002Fremove-background.md` → \"When NOT the right tool\".\n- **BGM\u002FSFX default to HeyGen retrieval; the no-credential fallback is generation (BGM) or the bundled library (SFX).** `\u002Faudio\u002Fsounds` ranks by a text query — name effects concretely (`glass shatter`, not `dramatic sound`); a no-match **skips**, never blocks the render. SFX sit at volume ~0.35 under voice + BGM. See `references\u002Fsfx.md` \u002F `references\u002Fbgm.md`.\n- **Treat workflow caption HTML as generated output.** For preset-backed videos, the reusable skin source lives at `.hyperframes\u002Fcaption-skin.html` and the workflow script writes `compositions\u002Fcaptions.html`; do not edit generated `compositions\u002Fcaptions.html` to fix the skin. Rebuild via the workflow's `captions.mjs`, or use that workflow's explicit overrides mechanism when present.\n","# HyperFrames Media\n\nCreate the audio and media assets a composition needs — voiceover (TTS), background music + sound effects, transcription, captions, background removal — then consume and animate that data in HTML. For placing assets into compositions, see `hyperframes-core`.\n\n## The audio engine — one source for TTS · BGM · SFX\n\nWorkflows do NOT hand-roll audio or vendor a copy. There is one engine — **`scripts\u002Faudio.mjs`** — that takes a neutral `audio_request.json` and writes `audio_meta.json` (plus assets under `assets\u002Fvoice|bgm|sfx`):\n\n```bash\n# \u003CMEDIA_DIR> = this skill's directory\nnode \u003CMEDIA_DIR>\u002Fscripts\u002Faudio.mjs --request .\u002Faudio_request.json --hyperframes . --out .\u002Faudio_meta.json\n```\n\nAll three capabilities degrade on **ONE switch** — whether a HeyGen credential is present (resolved from `$HEYGEN_API_KEY` \u002F `$HYPERFRAMES_API_KEY` \u002F `~\u002F.heygen`, **not** the CLI):\n\n| Capability | HeyGen credential present                          | absent                                               |\n| ---------- | -------------------------------------------------- | ---------------------------------------------------- |\n| TTS        | HeyGen Starfish REST (native word timestamps)      | → ElevenLabs → Kokoro (chain `transcribe` for words) |\n| BGM        | HeyGen music **retrieval**                         | Lyria → MusicGen local **generation** (detached)     |\n| SFX        | HeyGen sound-effects **retrieval** (min_score 0.4) | bundled 21-file library (`assets\u002Fsfx\u002F`)              |\n\n- **Request** (`audio_request.json`): `{ provider?, lang?, speed?, lines: [{ id, text, sfx?: [names] }], bgm: { mode?, query?, prompt? } }`. `id` joins each line back to the caller's model (a frame number, a scene id, …). `bgm.mode` = `retrieve | generate | none`; omit for auto (retrieve when credentialed, else generate). An **explicit** `retrieve` is strict — it skips rather than starting a detached generate (for callers with no `wait-bgm` step).\n- **Output** (`audio_meta.json`, id-keyed): `{ tts_provider, voice_id, bgm, bgm_pending, …, voices: [{ id, path, duration_s, words }], sfx: [{ id, name, file, source, offset_s, duration_s, volume }], total_duration_s }`.\n- `--only tts,bgm,sfx` runs a subset and **merges** into an existing `--out` (e.g. TTS+BGM early, SFX once cues exist).\n- BGM generate is spawned **detached** (`bgm_pending: true`) — run `scripts\u002Fwait-bgm.mjs` before assembling.\n- `scripts\u002Fheygen-tts.mjs` is a single-shot CLI over the same code (one text → wav + words) for when you just need HeyGen TTS without a request file.\n\nFull flag list + the `audio_meta.json` schema live in the header of `scripts\u002Faudio.mjs`. The references below cover the provider details and edge cases behind each capability.\n\n## Preflight — show sign-in status before any audio\n\n**Always run this before generating voice or BGM — inside a full workflow _or_ a one-off \"generate me a BGM\u002Fvoiceover\" request.** No HeyGen credential is **not** a reason to silently fall back to local engines: first recommend signing in and let the user decide. Run the shared preflight and **relay its output verbatim** — don't improvise your own \"missing key\" prompt, and don't offer to write keys into a per-repo `.env`:\n\n```bash\nnpx hyperframes auth status\n```\n\n- **Signed in** → it prints the account; proceed.\n- **Not signed in** (`exit 1` is expected here — \"not signed in\" is a normal state, not a failure) → it prints registration-first guidance. Recommend signing in: `npx hyperframes auth login` is browser OAuth — it **signs in and creates an account** (always available through this repo's CLI). To use an existing HeyGen API key (from app.heygen.com\u002Fsettings\u002Fapi), run `npx hyperframes auth login --api-key` — it saves to the shared `~\u002F.heygen` (no per-repo `.env`). The output also lists the local engines voice\u002FBGM will fall back to and a `pip` hint when deps are missing. **Relay this output as-is — don't paraphrase it into your own wording.** Then **STOP and wait** for the user to choose — sign in, or say \"go\" \u002F \"local\" to continue offline — **before generating anything.** This is a real decision point, not a passing note: don't fold it into another question, and don't proceed past it on your own. (Exception: in autonomous \u002F non-interactive mode, note the status and continue offline.)\n- `npx hyperframes auth status --json` returns `{ configured, recommended_action, offline_engines }` for deterministic branching.\n- **If the CLI can't run** (not on PATH and `npx` can't fetch it) → still **recommend signing in** (`npx hyperframes auth login`) and **STOP for the user's choice** — don't treat \"no credential\" as a silent green light for local generation.\n\nCredential resolution, full key priority, and the local-dependency list are in `references\u002Frequirements.md`.\n\n## Provider chains (the detail behind the engine)\n\n**TTS** — first available provider wins (the engine, or `npx hyperframes tts \"...\"`):\n\n| Order | Provider                      | Detected when                                | Word timestamps                                                  |\n| ----- | ----------------------------- | -------------------------------------------- | ---------------------------------------------------------------- |\n| 1     | HeyGen (Starfish)             | `$HEYGEN_API_KEY` \u002F `hyperframes auth login` | **Yes, native** — pass `--words narration.words.json` to capture |\n| 2     | ElevenLabs                    | `$ELEVENLABS_API_KEY` set                    | No — chain `transcribe` after                                    |\n| 3     | Kokoro-82M (local, 54 voices) | always (no key required)                     | No — chain `transcribe` after                                    |\n\n> The published `hyperframes tts` CLI is often the local-only build (its `--help` says \"Kokoro-82M\", no `--provider`\u002F`--words`) and silently falls back to Kokoro even with `$HEYGEN_API_KEY` set. That is why the engine's HeyGen path is the self-contained `scripts\u002Fheygen-tts.mjs` (REST), NOT the CLI; the CLI is used only for the Kokoro path. See `references\u002Ftts.md`.\n\n**BGM & SFX** — by default **retrieved** from the HeyGen audio library (`\u002Fv3\u002Faudio\u002Fsounds`), same credential as HeyGen TTS, with the no-credential fallback from the switch above:\n\n| Asset | HeyGen `type`                   | Lands in                                                   | Fallback (no credential)                                   |\n| ----- | ------------------------------- | ---------------------------------------------------------- | ---------------------------------------------------------- |\n| BGM   | `music`                         | `assets\u002Fbgm\u002Ftrack.mp3` (retrieve) · `track.wav` (generate) | Lyria \u002F MusicGen generation                                |\n| SFX   | `sound_effects` (min_score 0.4) | `assets\u002Fsfx\u002F\u003Cslug>.mp3`                                    | bundled 21-file library (`assets\u002Fsfx\u002F*` + `manifest.json`) |\n\nSee `references\u002Fbgm.md` and `references\u002Fsfx.md`.\n\n## Routing\n\n| Task                                                                | Read                                         |\n| ------------------------------------------------------------------- | -------------------------------------------- |\n| The audio engine — request\u002Fmeta schema, `--only`, the switch        | `scripts\u002Faudio.mjs` (header comment)         |\n| `npx hyperframes tts` \u002F `heygen-tts.mjs` — providers, voices, words | `references\u002Ftts.md`                          |\n| BGM — HeyGen retrieval + local Lyria \u002F MusicGen generation          | `references\u002Fbgm.md`                          |\n| SFX — HeyGen retrieval (min_score 0.4) + bundled local library      | `references\u002Fsfx.md`                          |\n| `npx hyperframes transcribe` — Whisper, model rules, output shape   | `references\u002Ftranscribe.md`                   |\n| `npx hyperframes remove-background` — transparent cutouts           | `references\u002Fremove-background.md`            |\n| TTS → transcription → captions (no recorded voiceover)              | `references\u002Ftts-to-captions.md`              |\n| Caption authoring — style detection, layout, word grouping, exit    | `references\u002Fcaptions\u002Fauthoring.md`           |\n| Transcript handling — input formats, quality gates, cleanup, APIs   | `references\u002Fcaptions\u002Ftranscript-handling.md` |\n| Caption motion — karaoke, marker effects, audio-reactive            | `references\u002Fcaptions\u002Fmotion.md`              |\n| Model caches, system dependencies, troubleshooting                  | `references\u002Frequirements.md`                 |\n\n## Non-negotiable rules\n\n- **One engine, no vendored copies.** Produce audio via `scripts\u002Faudio.mjs` (or `heygen-tts.mjs` for one-shot HeyGen TTS). Don't re-implement TTS\u002FBGM\u002FSFX inside a workflow — write an `audio_request.json` adapter and call the engine.\n- **\"HeyGen available\" = a resolvable credential, not the CLI.** The whole switch keys off `heygenCredential()`; the published `hyperframes tts` may be Kokoro-only, and there is no `hyperframes bgm` \u002F `hyperframes sfx` command at all.\n- **Voice IDs are provider-specific.** `am_michael` is Kokoro-only; HeyGen UUIDs don't work on Kokoro. If you pass `--voice`, also pin `--provider` to avoid silent provider drift when the user's env changes.\n- **Always pass `--model` to `transcribe`.** The CLI default `small.en` silently translates non-English audio. See `references\u002Ftranscribe.md` → \"Language Rule\".\n- **HeyGen returns word timestamps; ElevenLabs \u002F Kokoro do not.** The engine chains `transcribe` automatically for the latter two; standalone, pass `--words` to HeyGen or run `transcribe` against the audio file.\n- **Captions consume the flat word-array format** with `{ id, text, start, end }`. See `references\u002Ftranscribe.md` → \"Output Shape\".\n- **`remove-background --background-output` is hole-cut, not inpainted.** For \"scene without the person\", a different tool is needed. See `references\u002Fremove-background.md` → \"When NOT the right tool\".\n- **BGM\u002FSFX default to HeyGen retrieval; the no-credential fallback is generation (BGM) or the bundled library (SFX).** `\u002Faudio\u002Fsounds` ranks by a text query — name effects concretely (`glass shatter`, not `dramatic sound`); a no-match **skips**, never blocks the render. SFX sit at volume ~0.35 under voice + BGM. See `references\u002Fsfx.md` \u002F `references\u002Fbgm.md`.\n- **Treat workflow caption HTML as generated output.** For preset-backed videos, the reusable skin source lives at `.hyperframes\u002Fcaption-skin.html` and the workflow script writes `compositions\u002Fcaptions.html`; do not edit generated `compositions\u002Fcaptions.html` to fix the skin. Rebuild via the workflow's `captions.mjs`, or use that workflow's explicit overrides mechanism when present.\n",{"name":5,"description":7},"main","60364690293feed5d9b458e19a441d4d7561e65e","services\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media",1,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness","https:\u002F\u002Fnewai.land\u002Fcuti-harness","https:\u002F\u002Fgithub.com\u002FVideoVerses","2026-10-11 19:27:56",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add VideoVerses\u002FCuti-Harness --skill hyperframes-media",{"tool":37,"command":38},"bunx","bunx skills add VideoVerses\u002FCuti-Harness --skill hyperframes-media",{"tool":40,"command":41},"pnpm","pnpm dlx skills add VideoVerses\u002FCuti-Harness --skill hyperframes-media","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002FSKILL.md",true,[45,51,55,58,62,66,70,74,78,82,86,90,94,98,102,106,110,114,118,122,126,129,135,139,143,147,151,155,159,163,167,171,177,181,185,189,193,197,201],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"assets\u002Fsfx\u002Fchime.mp3","ASSET","资产文件",27309,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fassets\u002Fsfx\u002Fchime.mp3",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"assets\u002Fsfx\u002Fclick-soft.mp3",11702,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fassets\u002Fsfx\u002Fclick-soft.mp3",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":57},"assets\u002Fsfx\u002Fclick.mp3","https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fassets\u002Fsfx\u002Fclick.mp3",{"path":59,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":60,"sourceHtmlUrl":61},"assets\u002Fsfx\u002FCREDITS.md",1183,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fassets\u002Fsfx\u002FCREDITS.md",{"path":63,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":64,"sourceHtmlUrl":65},"assets\u002Fsfx\u002Ferror.mp3",51827,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fassets\u002Fsfx\u002Ferror.mp3",{"path":67,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":68,"sourceHtmlUrl":69},"assets\u002Fsfx\u002Fglitch-1.mp3",84427,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fassets\u002Fsfx\u002Fglitch-1.mp3",{"path":71,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":72,"sourceHtmlUrl":73},"assets\u002Fsfx\u002Fglitch-2.mp3",112128,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fassets\u002Fsfx\u002Fglitch-2.mp3",{"path":75,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":76,"sourceHtmlUrl":77},"assets\u002Fsfx\u002Fglitch-3.mp3",99072,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fassets\u002Fsfx\u002Fglitch-3.mp3",{"path":79,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":80,"sourceHtmlUrl":81},"assets\u002Fsfx\u002Fimpact-bass-1.mp3",67709,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fassets\u002Fsfx\u002Fimpact-bass-1.mp3",{"path":83,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":84,"sourceHtmlUrl":85},"assets\u002Fsfx\u002Fimpact-bass-2.mp3",82944,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fassets\u002Fsfx\u002Fimpact-bass-2.mp3",{"path":87,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":88,"sourceHtmlUrl":89},"assets\u002Fsfx\u002Fkey-press.mp3",3909,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fassets\u002Fsfx\u002Fkey-press.mp3",{"path":91,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":92,"sourceHtmlUrl":93},"assets\u002Fsfx\u002Fmanifest.json",3721,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fassets\u002Fsfx\u002Fmanifest.json",{"path":95,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":96,"sourceHtmlUrl":97},"assets\u002Fsfx\u002Fnotification.mp3",78576,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fassets\u002Fsfx\u002Fnotification.mp3",{"path":99,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":100,"sourceHtmlUrl":101},"assets\u002Fsfx\u002Fping.mp3",26400,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fassets\u002Fsfx\u002Fping.mp3",{"path":103,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":104,"sourceHtmlUrl":105},"assets\u002Fsfx\u002Fpop.mp3",23040,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fassets\u002Fsfx\u002Fpop.mp3",{"path":107,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":108,"sourceHtmlUrl":109},"assets\u002Fsfx\u002Friser.mp3",321024,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fassets\u002Fsfx\u002Friser.mp3",{"path":111,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":112,"sourceHtmlUrl":113},"assets\u002Fsfx\u002Fsparkle.mp3",57678,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fassets\u002Fsfx\u002Fsparkle.mp3",{"path":115,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":116,"sourceHtmlUrl":117},"assets\u002Fsfx\u002Ftyping.mp3",26852,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fassets\u002Fsfx\u002Ftyping.mp3",{"path":119,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":120,"sourceHtmlUrl":121},"assets\u002Fsfx\u002Fwhoosh-cinematic.mp3",177408,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fassets\u002Fsfx\u002Fwhoosh-cinematic.mp3",{"path":123,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":124,"sourceHtmlUrl":125},"assets\u002Fsfx\u002Fwhoosh-short.mp3",18390,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fassets\u002Fsfx\u002Fwhoosh-short.mp3",{"path":127,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":124,"sourceHtmlUrl":128},"assets\u002Fsfx\u002Fwhoosh.mp3","https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fassets\u002Fsfx\u002Fwhoosh.mp3",{"path":130,"resourceType":131,"resourceTypeDesc":132,"sizeBytes":133,"sourceHtmlUrl":134},"references\u002Fbgm.md","REFERENCE","参考文档",7223,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Freferences\u002Fbgm.md",{"path":136,"resourceType":131,"resourceTypeDesc":132,"sizeBytes":137,"sourceHtmlUrl":138},"references\u002Fcaptions\u002Fauthoring.md",9050,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Freferences\u002Fcaptions\u002Fauthoring.md",{"path":140,"resourceType":131,"resourceTypeDesc":132,"sizeBytes":141,"sourceHtmlUrl":142},"references\u002Fcaptions\u002Fmotion.md",5656,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Freferences\u002Fcaptions\u002Fmotion.md",{"path":144,"resourceType":131,"resourceTypeDesc":132,"sizeBytes":145,"sourceHtmlUrl":146},"references\u002Fcaptions\u002Ftranscript-handling.md",5439,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Freferences\u002Fcaptions\u002Ftranscript-handling.md",{"path":148,"resourceType":131,"resourceTypeDesc":132,"sizeBytes":149,"sourceHtmlUrl":150},"references\u002Fremove-background.md",8465,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Freferences\u002Fremove-background.md",{"path":152,"resourceType":131,"resourceTypeDesc":132,"sizeBytes":153,"sourceHtmlUrl":154},"references\u002Frequirements.md",3875,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Freferences\u002Frequirements.md",{"path":156,"resourceType":131,"resourceTypeDesc":132,"sizeBytes":157,"sourceHtmlUrl":158},"references\u002Fsfx.md",3503,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Freferences\u002Fsfx.md",{"path":160,"resourceType":131,"resourceTypeDesc":132,"sizeBytes":161,"sourceHtmlUrl":162},"references\u002Ftranscribe.md",2783,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Freferences\u002Ftranscribe.md",{"path":164,"resourceType":131,"resourceTypeDesc":132,"sizeBytes":165,"sourceHtmlUrl":166},"references\u002Ftts-to-captions.md",1187,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Freferences\u002Ftts-to-captions.md",{"path":168,"resourceType":131,"resourceTypeDesc":132,"sizeBytes":169,"sourceHtmlUrl":170},"references\u002Ftts.md",8572,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Freferences\u002Ftts.md",{"path":172,"resourceType":173,"resourceTypeDesc":174,"sizeBytes":175,"sourceHtmlUrl":176},"scripts\u002Faudio.mjs","SCRIPT","脚本",12072,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fscripts\u002Faudio.mjs",{"path":178,"resourceType":173,"resourceTypeDesc":174,"sizeBytes":179,"sourceHtmlUrl":180},"scripts\u002Fheygen-tts.mjs",4262,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fscripts\u002Fheygen-tts.mjs",{"path":182,"resourceType":173,"resourceTypeDesc":174,"sizeBytes":183,"sourceHtmlUrl":184},"scripts\u002Flib\u002Fbgm.mjs",10389,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fscripts\u002Flib\u002Fbgm.mjs",{"path":186,"resourceType":173,"resourceTypeDesc":174,"sizeBytes":187,"sourceHtmlUrl":188},"scripts\u002Flib\u002Fheygen.mjs",5675,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fscripts\u002Flib\u002Fheygen.mjs",{"path":190,"resourceType":173,"resourceTypeDesc":174,"sizeBytes":191,"sourceHtmlUrl":192},"scripts\u002Flib\u002Fsfx.mjs",4695,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fscripts\u002Flib\u002Fsfx.mjs",{"path":194,"resourceType":173,"resourceTypeDesc":174,"sizeBytes":195,"sourceHtmlUrl":196},"scripts\u002Flib\u002Ftts.mjs",9917,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fscripts\u002Flib\u002Ftts.mjs",{"path":198,"resourceType":173,"resourceTypeDesc":174,"sizeBytes":199,"sourceHtmlUrl":200},"scripts\u002Flyria-recipe.py",4547,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fscripts\u002Flyria-recipe.py",{"path":202,"resourceType":173,"resourceTypeDesc":174,"sizeBytes":203,"sourceHtmlUrl":204},"scripts\u002Fwait-bgm.mjs",5486,"https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fbuiltin\u002Fhyperframes-media\u002Fscripts\u002Fwait-bgm.mjs",[206,213,220,227,234,242],{"skillNo":207,"name":208,"nameZh":6,"description":209,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":210,"categories":211,"keywords":212,"publishedAt":18},"01M7CB3T5C44KCS1RRXMXXNCHF","external-shot-continuity","External continuity review method for long-form video projects.","https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Ftests\u002Ffixtures\u002Fexternal-skills\u002Fexternal-shot-continuity\u002FSKILL.md",[],[],{"skillNo":214,"name":215,"nameZh":6,"description":216,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":217,"categories":218,"keywords":219,"publishedAt":18},"01M7CB3PKKR1JRB3XAG5S9T7NS","independent-story-workflow","Create a three-part story document without paid media generation.","https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Ftests\u002Ffixtures\u002Fdynamic-workflow\u002FSKILL.md",[],[],{"skillNo":221,"name":222,"nameZh":6,"description":223,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":224,"categories":225,"keywords":226,"publishedAt":18},"01M7CB3K7RMRQ4WDYAYNC1S1S0","suno-song","Instruction helper: write a singable original Suno song from Bitwize (verbatim copy), then call suno.generate. Trigger: 原创歌曲, 写歌, Suno lyrics, $suno-song. Not a workflow.","https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fexternal\u002Fsuno-song\u002FSKILL.md",[],[],{"skillNo":228,"name":229,"nameZh":6,"description":230,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":231,"categories":232,"keywords":233,"publishedAt":18},"01M7CB3CYCSAQENCW9SB58BYHC","short-drama-workflow","Workflow for producing plot-dense short dramas with character and location reference sheets, complete 15-second Seedance segments, native dialogue, parallel multi-reference T2V generation, duration validation, and final assembly. Use for 爽文短剧、都市反转短剧、对白短剧、连续多段短剧，或用户明确调用 $short-drama-workflow. Do not use for product-centered scenario advertisements.","https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fexternal\u002Fshort-drama-workflow\u002FSKILL.md",[],[],{"skillNo":235,"name":236,"nameZh":6,"description":237,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":238,"sourceHtmlUrl":239,"categories":240,"keywords":241,"publishedAt":18},"01M7CB36GV8A2YX4P41457FRZ6","seedance2","Workflow: 即梦 Seedance 视频创意工作台。图+文案→看图分析→文案扩写→运镜→API生成。 触发词：即梦、Seedance、seedance、视频提示词、AI视频、运镜、短剧广告、$seedance2.","https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fexternal\u002Fseedance2\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fexternal\u002Fseedance2\u002FSKILL.md",[],[],{"skillNo":243,"name":244,"nameZh":6,"description":245,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":246,"categories":247,"keywords":248,"publishedAt":18},"01M7CB2ZDR784PMJ60NZ616GWQ","product-voiceover-narration","Design concise native voiceover for commercial product-video segments and bind each spoken line to verified selling points, visible actions, and exact timeline ranges. Use when a product advertisement should introduce the product through narration, when Seedance 2.0 should generate picture and voice together, or when product shots need coordinated narration, music, and sound direction. Do not synthesize a separate voice track and never invent product claims.","https:\u002F\u002Fgithub.com\u002FVideoVerses\u002FCuti-Harness\u002Fblob\u002Fmain\u002Fservices\u002Fvideo-runtime\u002Fskills\u002Fexternal\u002Fproduct-voiceover-narration\u002FSKILL.md",[],[]]