agentleFS
neskuchnyneskuchny/content_factory/.claude/skills/idea-dice/SKILL.md

idea-dice

Skill1 starsChanged 2 days agoMITView on GitHub

Idea dice: a way to get away from the first obvious concept. The video's topic is crossed with a random real thing (an object, a profession, a natural phenomenon, an invention, a genre, an everyday situation) and an unexpected angle emerges from the intersection. Use for the producer during the sighting round (3–5 different variants per topic), when concepts come out similar, and when the human asks for \"something interesting\".

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Look for a real intersection: a format, mechanic, visual language or conflict that the spark gives the topic ("forecast for seedlings: …

    line 17
  2. Distinctive:

    Test: if the concept could be handed to any other company unchanged, roll again.

    line 20
  3. Distinctive:

    Do not mock people, professions, regions or nationalities.

    line 24
  4. Distinctive:

    Do not use other people's brands, characters, songs or recognizable formats of specific shows.

    line 25
  5. Distinctive:

    Do not touch politics, religion or tragedies.

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Idea dice

Based on dice.py / sparks.json from sarpstar/cinecode (MIT); the list of "sparks" is our own, written for everyday topics and the client's audience.

How to roll

python3 scripts/qa/dice.py [N] [--seed S] outputs N sparks (3 by default) from config/sparks.yaml, one from each of different categories. The seed is written into the brief so the roll can be repeated.

How to use

  1. The video's topic (for example, "choosing a spot for the product") + a spark (for example, "weather forecast").
  2. Look for a real intersection: a format, mechanic, visual language or conflict that the spark gives the topic ("forecast for seedlings: shade expected on this plot until noon").
  3. From three sparks, make three fully different concepts for the sighting round (hook, mechanic, ending).
  4. Test: if the concept could be handed to any other company unchanged, roll again.
  5. A spark adds no facts about the product: the fact-check rules stay in force.

Prohibitions

  • Do not mock people, professions, regions or nationalities.
  • Do not use other people's brands, characters, songs or recognizable formats of specific shows.
  • Do not touch politics, religion or tragedies.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.