agentleFS
Sign inStart free
badgidsbadgids/Story-Film-Skills/skills/decision-tree-interview/SKILL.md

decision-tree-interview

Skill4 starsChanged 3 months agoApache-2.0View on GitHub

Run a structured creative or production interview that exposes assumptions in dependency order for stories, books, images, audio, video, films, trailers, campaigns, and production workflows.

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:

    Use when the user wants their idea challenged, clarified, pressure-tested, or fully specified through questions.

    line 12
  2. Distinctive:

    Ask the whole frontier in one numbered round when practical.

    line 17
  3. Distinctive:

    Wait for the user's decisions before asking questions that depend on those answers.

    line 18
  4. Distinctive:

    Never answer the user's side of a creative decision merely to keep the process moving.

    line 20
  5. Distinctive:

    Stop when the frontier is empty or every remaining item is explicitly deferred or out of scope.

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Decision Tree Interview

Read ../../references/CREATIVE_DECISION_PROTOCOL.md.

Use when the user wants their idea challenged, clarified, pressure-tested, or fully specified through questions.

  1. Build a decision tree from what is already known.
  2. Resolve factual unknowns from available sources instead of asking the user to research them.
  3. Identify the current frontier: decisions whose prerequisites are settled.
  4. Ask the whole frontier in one numbered round when practical. For each question include a concise recommended answer and why it fits the current project.
  5. Wait for the user's decisions before asking questions that depend on those answers.
  6. Recompute the frontier after every round.
  7. Never answer the user's side of a creative decision merely to keep the process moving.
  8. Stop when the frontier is empty or every remaining item is explicitly deferred or out of scope.

For durable work, append normalized DEC-### records to 00_project/creative_decisions.jsonl.

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.

Check your setup, free