agentleFS
badgidsbadgids/Story-Film-Skills/skills/story-research/SKILL.md

story-research

Skill4 starsChanged 3 months agoApache-2.0View on GitHub

Research factual, historical, technical, cultural, location, or craft details needed by a story or screenplay, recording source type, confidence, conflicts, contradictions, gaps, and production-relevant implications.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when a creative decision depends on real-world facts or when the project needs grounded detail it does not yet have.

    line 11
  2. Very specific:

    Read ../../references/CORE_CONTRACT.md, ../../references/RESEARCH_RULES.md, the brief, and the story assumptions relevant to the question.

    line 15
  3. Distinctive:

    Write the exact research questions before searching.

    line 16
  4. Distinctive:

    Prefer primary, official, scholarly, or practitioner sources according to the question.

    line 17
  5. Distinctive:

    Update canon only for facts or creative decisions the project has explicitly adopted.

    line 21
  6. Distinctive:

    Every adopted factual constraint names its source or evidence class, uncertainty is visible, and the writer can use the note without …

    line 25

≈ “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

Story Research

Use when a creative decision depends on real-world facts or when the project needs grounded detail it does not yet have.

Workflow

  1. Read ../../references/CORE_CONTRACT.md, ../../references/RESEARCH_RULES.md, the brief, and the story assumptions relevant to the question.
  2. Write the exact research questions before searching.
  3. Prefer primary, official, scholarly, or practitioner sources according to the question. Use current sources when the fact can change.
  4. Separate verified fact, supported interpretation, contested claim, anecdotal detail, creative inspiration, and project decision.
  5. Record credible disagreements instead of flattening them into one answer.
  6. Save 01_story/research/<topic>.md with: question, usable findings, source notes, confidence, conflicts, contradictions with current story assumptions, gaps, and story implications.
  7. Update canon only for facts or creative decisions the project has explicitly adopted.

Done

Every adopted factual constraint names its source or evidence class, uncertainty is visible, and the writer can use the note without repeating the research.

Evidence ledger handoff

When research will support documentary narration, historical claims, press materials, social copy, a pitch, a treatment presented as factual, or any other public factual statement, route adopted claims through evidence-research and 01_story/research/claims.jsonl. Research notes may remain richer than the ledger. The ledger exists to make public-use evidence and uncertainty machine-checkable.

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.