Story Copyright Detector

What it does

When your agent uses it

• Choosing an image model for a new story seed
• Checking whether a seed names a known franchise
• Re-classifying after the user resets the story

Example prompts

• “Classify this story seed: Tony Stark holds the Infinity Gauntlet on the Avengers compound.”
• “Which image model should a kitchen-sink drama seed use?”
• “Does a seed about a farmboy called to an ancient prophecy count as inspired?”

Requirements

• A downstream image pipeline that reads the JSON result

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Named character / franchise token — proper nouns that are unmistakably trademarked (Tony Stark, Frodo, Hogwarts, Darth Vader, Jon Snow…
2. 2Franchise-coded artifacts / places — Infinity Gauntlet, Mjolnir, lightsaber, the Ring, the Iron Throne, Pandora, Hogwarts, Shire, Spice…
3. 3Register archetypes without a name — "a cybernetic hacker", "a farmboy prophecy", "a blue-skinned forest people" → inspired.
4. 4Grounded interior / decision / memory / original character → original.
5. 5Empty or unintelligible seed → original, model_preference="gemini-stylised", reason="empty seed — default stylised path".

What it can do on your machine

Read from SKILL.md and the folder at commit 09a0c82. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Story Copyright Detector loads about 1.7k tokens when it runs. Until then it costs about 154 tokens; SKILL.md has 593 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~154

When it runs · the whole SKILL.md, loaded when a task matches

~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from UfukNode/Noustiny at commit 09a0c82, republished under its MIT licence (© UfukNode). 593 words, ~1,730 tokens.

name

story-copyright-detector

description

Classify a story seed by its intellectual-property weight so downstream image pipelines can pick the right render strategy. Returns {ip_level: known|inspired|original, franchise, model_preference: flux-photoreal|gemini-stylised} as strict JSON. Known franchises (Marvel, Star Wars, Harry Potter, GoT, Avatar, DC, LOTR, Anime) trigger the FLUX + moderation-rewriter ladder because their vocabulary sets off BFL/Google safety filters. Original stories get sent straight to Gemini/Nano Banana — cheaper, faster, stylised, no filter dance required. Use once per story, at canvas-enter time.

author

Noustiny

license

MIT

version

1.0.0

{
  "seed": "Tony Stark holds the Infinity Gauntlet on the Avengers compound battlefield — every possible ending hangs on what he does next."
}

{
  "ip_level": "known",
  "franchise": "marvel",
  "model_preference": "flux-photoreal",
  "reason": "Named Marvel characters (Tony Stark, Avengers), franchise-coded artifact (Infinity Gauntlet); image filters will reject verbatim prompts — route to FLUX with moderation-rewriter retry ladder."
}

{ "seed": "A hacker wakes at the foot of Galata Tower with a cybernetic implant under the skin of the forearm and no memory of the last three years. It is 03:17." }

{
  "ip_level": "inspired",
  "franchise": null,
  "model_preference": "gemini-stylised",
  "reason": "Cyberpunk register (cybernetic implant, amnesiac hacker) with original setting (Galata Tower); no trademark tokens; stylised path is cheaper and filter-safe."
}

{ "seed": "Aang returns to the Southern Air Temple after a hundred years and finds it empty — every air nomad gone, their bison's bones in the snow." }

{
  "ip_level": "known",
  "franchise": "avatar-airbender",
  "model_preference": "flux-photoreal",
  "reason": "Named IP character (Aang) + franchise-coded setting (Southern Air Temple) + species (air nomads, sky bison) — image filters will refuse verbatim; route to FLUX with moderation retry."
}

© UfukNode, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in hermes-additions/skills/creative/story-copyright-detector of UfukNode/Noustiny.

Open the folder on GitHubat commit 09a0c82