Update to Traspion

{
  "description": "Find, retrieve, translate, edit, save, rename, or export an existing Traspion speech-to-text transcript. Use when the user wants to work with audio-to-text or video-to-text content already stored in Traspion.",
  "included_files": [],
  "name": "traspion-work-with-content",
  "skill_md_contents": "---\nname: traspion-work-with-content\ndescription: Find, retrieve, translate, edit, save, rename, or export an existing Traspion speech-to-text transcript. Use when the user wants to work with audio-to-text or video-to-text content already stored in Traspion.\n---\n\n# Work with Traspion content\n\nResolve the intended file before using a file-specific tool.\n\n- Reuse a `fileId` already returned for the clearly identified file.\n- Otherwise call `list_files`, using its filename, date, or status filters when the user supplied those details. If several files could match, ask the user to choose; do not silently infer an ID. A request for the latest file may use the most recent matching list result.\n- When showing files returned by `list_files`, present them as a Markdown table with row number, filename, upload time, and status. Keep the returned order and use the row number to resolve a user's follow-up selection. Do not expose a pagination cursor unless it is needed for the next page.\n- Call `get_transcription` for every request to retrieve a transcript, including when the user switches to another file later in the conversation.\n\n## Retrieve and translate\n\n- Use the returned pagination flags and next offsets when more transcript content is required. Continue only until the user's task has enough content or the complete requested transcript has been retrieved.\n- Clearly identify partial results. Never describe a truncated transcript as complete.\n- When displaying a completed transcript or stored translation, retrieve all pages needed and use ChatGPT's native editable view when available. Otherwise show the text in the conversation. If client limits prevent showing it all, identify the result as partial and offer a complete export. The plugin does not supply its own editor.\n- Follow the returned `presentationMode`. When both speaker and channel identification are enabled, present each segment once in a combined form such as `[00:00–00:08] Channel 1 · Speaker A: text`. Preserve the returned labels and timestamps, omit a label only when it is absent, and do not duplicate the same content as a separate plain transcript unless the user explicitly asks for plain text.\n- Use `get_translation` first when the user asks for a translation, because a stored Traspion translation may have been requested during transcription. If it is still processing, report the status and stop after that check.\n- If `get_translation` reports `TRANSLATION_NOT_REQUESTED`, tell the user: \"You didn't opt for translation while transcribing, so I'll use ChatGPT to translate the transcription.\" Retrieve the complete transcription and translate it directly in ChatGPT into the user's requested language. If a requested stored translation is still processing, report that status instead of substituting ChatGPT translation.\n- Present that fallback as **Transcript translation**. Translate faithfully and preserve the transcript's meaning, paragraph structure, speaker labels, and timestamps when present. Do not summarize, paraphrase, polish, add commentary inside the translation, or claim that Traspion generated or stored it.\n- After translating the complete transcript in ChatGPT, present it in a native editable view if the client offers one. Otherwise present the complete translation in the conversation under **Transcript translation**.\n- Never save a ChatGPT-produced translation to Traspion, even after a save request. Tell the user to copy or download the ChatGPT result if they want to keep it.\n- For a stored translation, follow `nextTextOffset` until the complete text is available. For a transcript, follow the returned text and segment offsets as needed. Use `export_transcript` when a complete stored file is too large to display.\n\n## Edit and save\n\n- Retrieve the current stored Traspion content and its revision before editing it. Edits in ChatGPT's native view remain local until the user explicitly approves saving the complete revised content to Traspion.\n- Show the proposed content and call `save_content` from chat only after the user explicitly approves saving it to Traspion. Pass the revision returned by `get_transcription` or `get_translation` for those content types. If the document has changed since retrieval, ask the user to reopen and review it instead of retrying the overwrite.\n- Preserve the resolved `fileId` and choose the content type that matches the material being saved.\n- Never overwrite complete stored content with a partial or paginated fragment.\n- Call `save_content` once after approval. If saving fails, report the error instead of claiming the edit was stored. Never pass a ChatGPT-generated translation to this tool.\n\n## Rename and export\n\n- Use `rename_file` only when the target file and new name are clear.\n- For export, establish the format (`pdf`, `txt`, `docx`, or `json`) and whether the user wants the transcription, stored translation, speaker-labelled transcript, or channel-identified transcript. Ask when either choice is materially ambiguous.\n- Use `type: speaker-labelling` only when the file's transcription configuration indicates speaker partitioning was enabled. Use `type: channel-identification` only when channel identification was enabled. If the requested output was not enabled for that file, explain that it is unavailable instead of exporting a different content type.\n- Reproduce the exact Markdown download link returned by `export_transcript` and state that the link is temporary. Never rewrite, shorten, or omit it.\n"
}