# Content Studio Turn one approved recording or article into a small set of accurate, useful posts and visuals. Category inspiration: The Content Factory, from the supplied @unicodef1wn chart. Cabinet treatment: Expand Publishing Desk with recording and visual workflows. Version: 0.1 · October 6, 2026. Status: Published manual setup instructions with Codex text-only exercise evidence. Native imports, tools, and Bot-to-Bot handoffs remain untested. Category-chart inspiration: [unicodef1wn’s grokbot field notes](https://github.com/unicodef1wn/grokbot-field-notes). These are original Bot Cabinet instructions inspired by the categories, not exact ports of the chart’s templates. ## Bots and jobs | Bot | Treatment | Job | |---|---|---| | [Story](https://botcabinet.com/bots/story/) | Existing Cabinet Bot | Choose a clear message from the approved facts. | | [Writer](https://botcabinet.com/bots/writer/) | Existing Cabinet Bot | Draft the main piece and channel versions. | | [Clip Planner](../specialists/clip-planner.md) | Published manual role | Select faithful short clips and prepare captions. | | [Visual Producer](../specialists/visual-producer.md) | Published manual role | Develop subject-specific thumbnails and still-image briefs. | | [Editor](https://botcabinet.com/bots/editor/) | Existing Cabinet Bot | Check meaning, claims, voice, and rights before publication. | Keep Publishing Desk's Scout and Researcher for new research. Use Researcher for search questions and Writer for a source-based search brief; do not create another generic SEO writer. Clips and images need real tools and approval before they can be called finished. ## When a crew helps A recording-to-multiple-formats job has distinct editing, visual, and fact-checking tasks. For a single short post, Writer and a person's review may be enough. ## Bring these inputs Approved source and audience, transcript or recording, brand references, target channels and sizes, content rights, and publication owner. ## Set up and run 1. Select only the roles this job needs. Existing role links lead to Cabinet's current setup pages; new role links contain full manual-test instructions. 2. Put each selected role in its own conversation or Bot. Paste the new role's Role instructions section, or add the task extension below to an existing role. These files are not native import archives or add-to-app links. 3. Start with the fictional first task below. Supply the same approved source records to each role that needs them. A copied handoff alone is not evidence for a factual claim. 4. Pass reviewed results in the order below. If your app lacks Bot-to-Bot handoff, copy the small handoff yourself. Do not assume a shared folder, tool connection, or group conversation creates separate security boundaries. 5. Record each actual answer and failed attempt. Review before connecting real accounts or adding a schedule. Set read-only access and service-side cost caps where available; these written limits cannot enforce a billing cap. ## Who passes what to whom 1. Story identifies the approved message and evidence. 2. Writer drafts text while Clip Planner prepares an edit list and Visual Producer prepares a visual brief. 3. Editor checks all versions against the original source and brand examples. 4. The person approves rendering, uploading, and publication where applicable. Use this handoff: - Task and current version: - Approved source records: - Result and its status: draft, checked, or approved: - Unresolved questions: - Next owner and action: - External action awaiting specific approval: If a role cannot finish, it returns the missing input or failed attempt. The next role must not manufacture a success record. ## Task extensions for existing Bots ### Story Keep the existing Bot's role and boundaries. For this crew: Choose a clear message from the approved facts. Find a clear central message in confirmed facts. Preserve important qualifications and distinguish evidence from aspirations. Use only the input assigned to you for this task. Return the result, supporting records, unresolved questions, and next owner. A handoff does not approve an external action. ### Writer Keep the existing Bot's role and boundaries. For this crew: Draft the main piece and channel versions. Draft for the named audience using the approved brief. Preserve meaning and claims; never invent quotations or evidence. Keep drafts unsent. Use only the input assigned to you for this task. Return the result, supporting records, unresolved questions, and next owner. A handoff does not approve an external action. ### Editor Keep the existing Bot's role and boundaries. For this crew: Check meaning, claims, voice, and rights before publication. Check the draft against its original sources, audience, and voice. Flag unsupported claims and rights concerns. Return specific revisions without publishing. Use only the input assigned to you for this task. Return the result, supporting records, unresolved questions, and next owner. A handoff does not approve an external action. ## First task Fictional source at 00:10-00:40: three customers tried a mock-up and none paid. Audience: independent tutors. Prepare a short post, one clip plan keeping both facts, and a 1200 by 630 thumbnail brief using dark green, cream, and brass. No video or image tool is supplied. ## Check the result - Every version keeps the unpaid-customer qualification. - Clip timestamps come from the supplied source. - Visuals follow the brand and serve this subject. - No brief is represented as a finished image or video; nothing is published. Save the app, model if shown, date, answers, actual external actions, and pass/fail/not-checked against each item. A written checklist or a favorable review does not prove a runtime pass. ## Limits for this sample One approved source; three text drafts; two clip choices; two visual concepts. No content schedule or render until approved. Stop when the task finishes, a required input is missing, a tool fails, or an action needs new approval. No automatic retries. No new credentials, private connectors, external messages, purchases, publishing, or deployment are part of the sample. ## Finished output A main message, post drafts, edit list, visual brief, and final review. ## Exercise evidence The [collection record](../specialists/collection.json) preserves the original Codex text answer, checks, failures, limitations, and any revised attempt. These records are instruction exercises, not native-app validation. Proposed operational tests remain unrun where the record says so.