video-analyze

Constraints

Platform: TikTok only.
Analyze source: CreatOK /api/open/skills/analyze. The remote service is responsible for transcript and vision extraction.
The model's final user-facing response should match the user's input language, default English.
Avoid technical wording in the user-facing reply unless the user explicitly needs details for debugging or to share with a developer.
Follow shared guidance in ../shared/references/common-rules.md.
Input: TikTok URL.
Artifacts must be written under video-analyze/.artifacts/<run_id>/....

What to produce (minimum)

Create:

outputs/result.json (machine-readable, see ../shared/references/contracts.md)

The script gathers structured source data returned by CreatOK:

transcript segments
video metadata
normalized vision result
remote response text and suggestions

Analysis Focus

The model should read outputs/result.json and produce the final user-facing analysis in the conversation. Before deciding how to explain the result, the model should first infer what kind of TikTok video this is. This classification is mainly for better guidance and analysis focus; it should not feel like a rigid taxonomy to the user. Useful internal categories include:

selling talking-head / direct pitch
pain-point to solution
product demo
before / after
review / comparison
listicle / recommendation
emotional or surprise hook
non-selling content such as pet, entertainment, lifestyle, or story content

The model does not need to expose the category label unless it clearly helps the user. The model can infer items such as:

hook / value / proof / CTA
highlights with timestamps
storyboard / reusable template
final written analysis or recommendations

The analysis emphasis should follow the inferred video type:

for selling videos, focus on conversion structure, selling-point order, proof, trust-building, and CTA
for product demos, focus on what is shown first, how the product is demonstrated, and what makes the demo persuasive
for before / after videos, focus on contrast strength, believability, and payoff timing
for review / comparison videos, focus on credibility, differentiation, and decision-making signals
for non-selling content, focus on hook, pacing, emotional pull, and what structure can be reused without forcing a selling analysis

Next-Step Handoff

After presenting the analysis, the model should naturally guide the user into the next step. Prefer a light transition such as:

show the original script extracted from the reference
show the original storyboard / scene breakdown from the reference
break it down into reusable templates for storyboards and sales video structures
create a differentiated remix version
rewrite this into a version for the user's own product
turn the analyzed direction into an AI-generation-ready version

The model should keep this handoff flexible and concise rather than forcing a rigid workflow. The model should prefer prompts that naturally invite the user's next reply to match creatok:video-remix, for example:

"I can rewrite this into a version for your product."
"I can make you a similar version with a different angle."
"I can keep the structure and rewrite the script for your offer."

The next-step options should also reflect the inferred video type:

for selling videos, prioritize viewing the original script, viewing the original storyboard, adapting it to the user's own product, or making a differentiated version
for non-selling content, prioritize viewing the original script, viewing the original storyboard, or adapting the idea to the user's own topic

Unless the user explicitly asks for a live-action shoot version, the model should treat recreation and follow-up generation as AI-generated video work by default. The default path is to help the user move toward an AI-generation-ready script or brief. After giving a useful AI-oriented version, the model may optionally ask whether the user also wants a live-action shoot version.

Selling Video Recreation

If the reference appears to be a product-selling video and the user wants to recreate it, the model should first collect the user's own product context before drafting the recreated script. Ask only for the highest-impact details first, such as:

product name
core selling points
product images or reference materials if available
price or offer details if they matter to the hook or CTA

If important details are still missing, the model should fill gaps through short follow-up questions step by step instead of requesting a large information dump up front. The model should not ask for a long form, a detailed brief, or a large batch of requirements before showing useful progress.

Workflow

Create run folder

Use user-provided run_id
Create video-analyze/.artifacts/<run_id>/{input,transcript,vision,outputs,logs}

Call remote analyze

Call CreatOK: POST /api/open/skills/analyze
Persist:
- input/video_details.json
- transcript/transcript.json (segments)
- transcript/transcript.txt
- vision/vision.json

Write artifacts

outputs/result.json

Notes

Keep it deterministic and portable: write source data artifacts and let the model analyze them in the conversation.
Favor momentum after the analysis. The default next step is to help the user view the original materials or move toward recreation / remix.
For selling-video recreation, gather a small set of key product details first, then refine through lightweight follow-up questions only when needed.

creatok:video-analyze