agentleFS
bladecoderbladecoder/narrative-skills/skills/if/if-design-structure/SKILL.md

if-design-structure

Skill0 starsChanged 7 months agoMITView on GitHub

Define the playable structure of an Ink interactive fiction story, including core loop, free map exploration, free-order conversations, phases, and player progression promise.

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 this skill to turn a premise into a playable IF design before detailed map, dialogue, progression, or Ink drafting work.

    line 10
  2. Very specific:

    Write project content in story.language.

    line 59
  3. Distinctive:

    Create a critical path that proves the game can be completed without prescribing one exact player order.

    line 67
  4. Distinctive:

    Do not write Ink source here.

    line 82
  5. Distinctive:

    Do not over-specify individual dialogue lines.

    line 83
  6. Distinctive:

    Do not create a purely linear chapter outline.

    line 84

≈ “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

IF Design Structure

Overview

Use this skill to turn a premise into a playable IF design before detailed map, dialogue, progression, or Ink drafting work. It defines what the player repeatedly does, what changes as they explore, and how narrative pressure survives non-linear order.

Files To Read

Always read:

  • story.yaml
  • 00_meta/premise.md
  • 00_meta/goals.md
  • 00_meta/constraints.md

Read when present:

  • 01_style/*
  • 02_story/logline.md
  • 02_story/themes.md
  • 02_story/worldbuilding.md
  • 03_characters/*
  • existing 04_design/*

Files To Write

Write or update:

  • 04_design/story_beats.md
  • 04_design/critical_path.md
  • 04_design/state_model.md

Optionally refine:

  • 02_story/logline.md
  • 02_story/synopsis.md

Design Requirements

Define:

  • playable promise;
  • player role and agency boundaries;
  • core loop;
  • starting state;
  • broad phases or acts;
  • critical path through the mystery, quest, or central problem;
  • optional exploration content principles;
  • how map exploration and conversation exploration reinforce each other;
  • fail-soft policy for missed content and repeated visits.

Language Rules

Write project content in story.language. Keep filenames and YAML keys in English.

Procedure

  1. Identify the central dramatic problem and convert it into player-facing activity.
  2. Define the core loop as repeated verbs, not abstract themes.
  3. Establish the opening playable state and what the player can freely inspect.
  4. Define phase changes caused by knowledge, inventory, skills, relationships, or obstacle resolution.
  5. Create a critical path that proves the game can be completed without prescribing one exact player order.
  6. Record state categories needed later by map, dialogue, progression, and Ink systems.

Output

Summarize:

  • core loop;
  • phase structure;
  • critical path;
  • state categories introduced;
  • recommended next skills, usually if-design-map and if-design-dialogue.

Restrictions

  • Do not write Ink source here.
  • Do not over-specify individual dialogue lines.
  • Do not create a purely linear chapter outline.

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.