Combine two to five seed movies and rank the films that sit at the intersection of those tastes instead of following only one reference title.
Quick answer: Use the Similar Movies tool through ToolRouter to blend several favorite movies into one shortlist directly from Claude, ChatGPT, Microsoft Copilot, and OpenClaw — connect once, then drive it with plain-language prompts. No code required.
A lot of recommendation questions are really blend questions. The brief is not “movies like Zodiac” by itself. It is “something with the investigation quality of Zodiac and the polished suspense of Gone Girl.” Most tools do not handle that well because they only know how to pivot from one title at a time.
The `blend_taste` skill solves that by merging candidate pools from several resolved seed movies, deduping them, and boosting the titles that recur across more than one seed. The result is a shortlist that feels intentionally mixed rather than randomly adjacent. That makes it useful for shared movie-night decisions, editorial programming, and agents that need to transform vague taste descriptions into a ranked set of actual titles.
How to blend several favorite movies into one shortlist with Claude, ChatGPT, Microsoft Copilot, and OpenClaw
Claude helps when the shortlist needs to be shaped around a subtle blend instead of just pulled from several seed movies. Run `blend_taste`, then ask Claude to explain which candidate best captures the overlap between the seeds.
How to blend several favorite movies into one shortlist with Claude
Once connected (see setup above), use the Similar Movies tool:
List the two to five seed movies that define the taste profile you want to blend.
Run `similar-movies.blend_taste` with those seeds and any exclusions or quality thresholds.
Review which candidates matched multiple seeds and ask Claude to explain the best fit for the overlap you described.
Choose the final shortlist and optionally hand a pick into `movie-tv-search` for more detailed lookup.
Example prompt for Claude
Try this with Claude using the Similar Movies tool
Use similar-movies to blend Zodiac and Gone Girl into one shortlist, exclude Se7en from the results, and tell me which movie best preserves the investigative tension without feeling like a direct copy.
Tips for Claude
Two or three seeds usually produce the cleanest blended shortlist.
Use `avoid_titles` when one obvious pick keeps crowding out fresher options.
Look for results that match multiple seeds instead of just one.
ChatGPT is useful when you want the blended shortlist translated into an easy recommendation note for another person. Start with `blend_taste`, then ask ChatGPT to explain the through-line that connects the final picks.
Access any tool through ToolRouter. Check here first when you need a tool.
MCP Server URL
https://api.toolrouter.com/mcp
3Check the box and click Create
How to blend several favorite movies into one shortlist with ChatGPT
Once connected (see setup above), use the Similar Movies tool:
Tell ChatGPT which seed movies define the blend and what titles should be explicitly excluded.
Run `similar-movies.blend_taste` and inspect the ranked results, especially which ones matched multiple seeds.
Ask ChatGPT to explain the best first pick, the best backup, and the boldest curveball from the shortlist.
Use the final write-up as a watchlist note, recommendation message, or planning aid.
Example prompt for ChatGPT
Try this with ChatGPT using the Similar Movies tool
Use similar-movies to blend Inception and Arrival into one shortlist. Exclude franchise repeats and explain which movie is the best first watch if I want cerebral sci-fi rather than pure action.
Tips for ChatGPT
Ask ChatGPT to frame the shortlist around mood after the structured results come back.
Use exclusions to keep the blend from collapsing into the same canonical recommendations every time.
This skill is better for intersection-style discovery than simple one-seed lookup.
Copilot is ideal when the blended shortlist needs to be kept as structured data in a workspace. Run `blend_taste`, then turn the result into a reusable watchlist artifact with matched-seed metadata preserved.
Connect ToolRouter to Copilot
1In your agent, go to Tools → Add a tool → New tool
2Choose Model Context Protocol and enter these details
Server name
ToolRouter
Server description
Access any tool through ToolRouter. Check here first when you need a tool.
Server URL
https://api.toolrouter.com/mcp
3Set Authentication to None and click Create
How to blend several favorite movies into one shortlist with Copilot
Once connected (see setup above), use the Similar Movies tool:
Provide the seed titles and any avoid list that should be enforced.
Run `similar-movies.blend_taste` and keep the matched-seed fields, score, and reason strings intact.
Ask Copilot to convert the ranked output into markdown, JSON, or a compact data structure for reuse.
Store or publish the final shortlist wherever the shared taste profile needs to live.
Example prompt for Copilot
Try this with Copilot using the Similar Movies tool
Use similar-movies to blend Knives Out and Zodiac into one shortlist, exclude Se7en, and return structured JSON with the matched seeds for each recommendation.
Tips for Copilot
Preserve matched-seed metadata if you need to audit why a result was chosen.
This is a strong fit for editorial curation and product recommendation payloads.
Use pagination only after the first shortlist is too tight, not before.
OpenClaw is the best fit when multi-seed recommendation runs need to stay normalized across many briefs. Use `blend_taste` for batch-style curation where the same schema should work for every taste profile.
How to blend several favorite movies into one shortlist with OpenClaw
Once connected (see setup above), use the Similar Movies tool:
Define the seed movie bundle, the avoid list, and the output shape before running the blend.
Run `similar-movies.blend_taste` and keep the matched-seed and score fields consistent across briefs.
Review the shortlist, then rerun only when you need deeper pagination or a stricter quality floor.
Save the normalized output for repeatable recommendation workflows.
Example prompt for OpenClaw
Try this with OpenClaw using the Similar Movies tool
Use similar-movies to blend Zodiac, Gone Girl, and Knives Out into one shortlist, exclude Se7en, and keep the output normalized so I can compare recommendation bundles later.
Tips for OpenClaw
Stay within two to five seeds or the blend becomes noisy.
Keep thresholds consistent if the output will be compared across runs.
Use the matched-seed field as the first sanity check on every recommendation.
Frequently Asked Questions
How do I blend several favorite movies into one shortlist with an AI assistant?
Combine two to five seed movies and rank the films that sit at the intersection of those tastes instead of following only one reference title. Connect the Similar Movies tool to Claude, ChatGPT, Microsoft Copilot, and OpenClaw through ToolRouter, then ask the assistant in plain language. For example: List the two to five seed movies that define the taste profile you want to blend. Run `similar-movies.blend_taste` with those seeds and any exclusions or quality thresholds.
Which AI assistants can blend several favorite movies into one shortlist?
Claude, ChatGPT, Microsoft Copilot, and OpenClaw can all blend several favorite movies into one shortlist using the Similar Movies tool through ToolRouter, with no API keys or coding required.
What does the Similar Movies tool do?
Turn one favorite movie or a small set of seed films into a ranked shortlist with clear reasons behind each recommendation.