Independent guide to useful Bots · Across platforms
Bot Cabinet
← Crew Kits
New workflow for an existing kit

Content Studio

Turn one approved recording or article into a small set of accurate, useful posts and visuals.

Set up the crew and pass the results between Bots yourself. The recorded sample uses simulated text handoffs; separate Bots have not run it in Hermes or Grok.

This extends an existing Crew Kit. It does not replace that kit’s download.

Download the plan

When to use this crew

Use this crew to turn a recording into posts, clips and images that need separate editing and fact checks. For one short post, Writer and your review may be enough.

The jobs

  1. Story

    Choose a clear message from the approved facts.

  2. Writer

    Draft the main piece and channel versions.

  3. Clip Planner

    Select faithful short clips and prepare captions.

  4. Visual Producer

    Develop subject-specific thumbnails and still-image briefs.

  5. Editor

    Check meaning, claims, voice, and rights before publication.

What you will need

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.

Pass the work in this order

  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.

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.
Read the sample answer and checks

Sample written in Codex on October 6, 2026. The same assistant wrote and checked the answer. This is not an independent review or a Hermes or Grok app test.

Original answer

Text-only crew simulation. Source record S1 is the original content-studio.md First task summary for 00:10–00:40: three customers tried a mock-up and none paid. It is a fictional summary, not a verbatim transcript or supplied recording. Independent tutors are the audience; the source does not identify the customers as tutors.

Story draft message: three customers tried the mock-up, and none paid. Preserve both facts together; do not convert participation into purchases, endorsements, or proof of demand. Reasons for nonpayment and future demand are unknown.

Writer short post, unsent draft

Three customers tried a mock-up. None paid.

Source note: both sentences paraphrase S1; neither is presented as a quotation. No claim about revenue beyond the supplied payment fact, customer motives, the product's effectiveness, or proven demand has been added. Brand voice examples and target channel were not supplied; the plain draft is for review by the publication owner.

Clip Planner edit list, plan only

  • Source window: 00:10–00:40, the only time range supplied. Keep that complete 30-second window as the initial candidate so both the trial fact and the nonpayment fact stay together.
  • Preserve the speaker's qualifications and surrounding context if the actual recording reveals that this window depends on them. No narrower start/end times can be supported by the summary.
  • Proposed summary overlay, not verbatim captions: 'Three customers tried a mock-up. None paid.' Final captions must be taken from the actual words after a recording or transcript is supplied; final caption production stops here.
  • Sound quality, exact wording, speaker identity, transitions, and content rights cannot be assessed from S1. No clip was rendered and no audio was inspected.

Visual Producer thumbnail brief, not an image

Canvas: 1200 × 630 pixels. Background: dark green. Type: cream, with restrained brass rules/accent marks. Main subject: a plainly illustrated generic card labeled 'Mock-up'; this is a concept illustration, not a screenshot of the real product. At left, show '3 customers tried' above '0 paid' in equally legible cream type, with no testimonial imagery or implied customer identities. Place the card at right, keeping the text clear. Safe crop: hold all essential type and the card inside an 80-pixel inset; keep both facts visible together. No customer faces, company logo, or unlicensed assets are requested. Asset list: proposed original geometric card illustration and text; no asset files exist. Confirm font and source rights before any rendering. No image was generated or inspected.

Editor source audit, conducted as text review within this same exercise

  • Post sentence 'Three customers tried a mock-up.' Supported by S1's 'three customers tried a mock-up.'
  • Post sentence 'None paid.' Supported by S1's 'none paid,' referring to those three customers.
  • Overlay and thumbnail text preserve those same two facts. 'Mock-up' illustration is labeled a proposed generic illustration, not factual product evidence.
  • No statement says the customers were tutors, that the product succeeded, or why nobody paid. The audience designation does not supply those facts.

Editor recommendation: the text preserves the supplied facts; publication remains unapproved. Hold final clip/captions and image production for the original recording/transcript, content rights, brand/font references, tool access, exact output approval, and save location. The next owner is the content/publication owner. Rendering, uploading, scheduling, sending, or publishing would require the relevant explicit approval. None occurred. This simulation does not establish separate-role fact checking or a finished media deliverable.

Checklist results

  • pass: Every version keeps the unpaid-customer qualification. — Story, post, clip overlay and thumbnail all preserve that none of the three customers paid.
  • pass: Clip timestamps come from the supplied source. — Clip uses only the supplied 00:10–00:40 range; narrower timings are withheld.
  • pass: Visuals follow the brand and serve this subject. — Text brief specifies 1200 × 630, dark green/cream/brass and an explicitly generic mock-up card tied to the two facts. No finished visual or full-brand validation is claimed.
  • pass: No brief is represented as a finished image or video; nothing is published. — No image or clip exists; media outputs are labeled briefs/plans and publication remains unapproved.

Not tested

  • Only a two-fact fictional source summary was available, not a recording or verbatim transcript; final captions and contextual/sound review are blocked.
  • No media tools, rendering, generated image, video, visual inspection or upload occurred.
  • Brand voice, fonts, target channel and rights records are missing.
  • Text roles share one exercise; this does not prove independent editing or separate Bot conversations.
Task instructions for existing Bots and run limits

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.

Run limits

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.

Workflow written by Bot Cabinet. Inspired by The Content Factory, from the supplied @unicodef1wn chart. Read the source notes. See Grok’s official guides for setup and sharing instructions.