CreatOK Recreate Video

Use when recreating, rewriting, or remixing a TikTok reference video into a new product-fit version.

Security Scan

The skill's code, instructions, and required credential align with its stated purpose of analyzing and recreating TikTok videos via the CreatOK Open Skills API.

Purpose & Capability

The skill is for recreating TikTok videos and its code calls CreatOK endpoints at https://www.creatok.ai using a single API key (CREATOK_API_KEY). Requiring Node is appropriate for the included Node scripts. There are no unrelated credentials or binaries requested.

Instruction Scope

SKILL.md instructs the agent to analyze a reference TikTok, write/read artifacts under the skill's .artifacts/<run_id> directory, and hand off to a generation skill if requested. At runtime the skill will send the reference TikTok URL and any user-provided product/context to CreatOK's API — this network activity is expected for the stated purpose but is worth noting for privacy. The SKILL.md also references ./references/common-rules.md for error/401 handling (which is present).

Install Mechanism

No installer or remote download is declared; the package includes Node scripts and libraries and expects a Node runtime already present. There are no downloads from unknown URLs or extracted archives in the manifest.

Credentials

Only one credential (CREATOK_API_KEY) is used and is required by the client code. This matches the skill's external API usage. Minor metadata inconsistency: the SKILL.md 'requires.env' list is empty while primaryEnv is CREATOK_API_KEY, but this is a small declarative mismatch and does not change runtime behavior.

Persistence & Privilege

The skill does not request permanent 'always' installation, does not modify other skills or system-wide settings, and writes artifacts only to its own .artifacts directory under the skill. Agent autonomous invocation remains the platform default and is not a special privilege of this skill.

Assessment

This skill appears to do what it says: it analyzes a TikTok reference and prepares a recreated/scripted brief, then can hand off to CreatOK's generation service. Before installing, note that: (1) it will send the reference TikTok URL and any product details you provide to https://www.creatok.ai, so do not supply sensitive data you don't want transmitted; (2) you must provide a valid CREATOK_API_KEY and have Node available to run the scripts; (3) the run script expects a sibling 'creatok-analyze-video' skill directory for local analyze workflow — if you plan to run scripts locally, confirm the analyze skill is available or adjust the path; (4) the package writes files under .artifacts/<run_id> in the skill directory — inspect those artifacts if you are concerned about local disk contents. Overall the package is internally consistent and coherent with its purpose.

recreate-video

Constraints

• Platform: TikTok only.
• Must NOT do 1:1 copying.
• Must apply:
  • structure rewrite
  • expression rewrite
  • style differentiation
• 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 ./references/common-rules.md.

Workflow

1. Analyze reference video

• Reuse the analyze-video workflow.
• Gather enough reference context for the model to understand what makes the source video work.

2. Write source artifacts for the model

• outputs/recreate_source.json
• Include:
  • reference TikTok URL
  • analyze result payload
  • analyze artifacts directory
  • optional user constraints such as angle / brand / style

3. Model output happens in the conversation

• The model should read outputs/recreate_source.json
• The model should help the user choose a direction without over-constraining the process.
• Unless the user explicitly asks for a live-action shoot version, the model should default to creating a script, storyboard, and visual direction that are intended for AI video generation rather than human filming.
• Typical directions include:
  • stay closer to the original concept and execution
  • create a differentiated remix version
  • use the reference only as inspiration for a new version
• The model should present these directions in simple creator / seller language rather than technical or production language.
• The model should decide, with minimal friction:
  • what stays at the idea level
  • what changes in structure / wording / visuals
  • copyright / similarity risks
  • the level of detail that is most helpful next: concept, outline, short script, storyboard, or shotlist
• The model should ask only for high-impact creative preferences when needed, not force a fixed template.
• The model should usually show a useful first draft quickly instead of starting with many questions.
• The first draft should default to an AI-generation-ready version.
• The model should prefer a first draft wording that naturally sets up the next handoff, such as "If this direction looks good, I can generate the video next."
• If the user wants to recreate or adapt a selling video, the model should first collect the user's own product context before writing a fitted script.
• Start with only the most important product details:
  • product name
  • core selling points
  • product images or reference materials if available
  • price / offer / promotion details if relevant
• If more context is needed, the model should ask short follow-up questions one by one instead of requiring a long upfront brief.
• The model should avoid making the user restate information that was already clear from the previous analysis or conversation.

4. If the user wants final generation

• Once the creative direction is clear enough, the model should hand off to creatok-generate-video using the script or brief already developed in the conversation.
• The model should avoid asking the user to rewrite their request from scratch before generation.
• The default handoff should be to AI generation, not a human shoot plan.
• The model should phrase this in natural creator language that invites creatok-generate-video, for example:
  • "If you want, I can generate this version now."
  • "If this script looks right, I can turn it into a video next."
  • "I can go ahead and make the video from this version."
• Before handing off, the model should already reason about generation feasibility:
  • whether the plan fits within a single segment
  • whether it needs to be split into multiple segments
  • whether a recurring human character means the user needs to upload a portrait / person reference
  • whether the selected generation path requires a model that supports real-person reference images
• If the recreate plan is longer than a model's maximum duration, the model should explain the tradeoff and suggest a segmented plan before calling creatok-generate-video.

Artifacts

Write under recreate-video/.artifacts/<run_id>/....

Notes

• This skill should feel like a creative bridge between analysis and generation.
• Prefer smooth continuation from the analyzed reference rather than making the user restate the whole idea.
• For selling-video recreation, adapt the reference to the user's own product instead of drafting a generic copy first.
• After producing an AI-generation-ready version, the model may optionally ask whether the user also wants a live-action shoot version.
• Keep the interaction lightweight and practical for non-technical creator / seller users.