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

if-design-dialogue

Skill0 starsChanged 7 months agoMITView on GitHub

Design free-order character conversations for an Ink interactive fiction project, including dialogue topics, availability, knowledge gates, relationship state, and revelations.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to design the conversation layer of an exploratory Ink game.

    line 10
  2. Very specific:

    Write project prose in story.language.

    line 57
  3. Distinctive:

    Ensure every critical clue has a reliable route and every optional clue has a purpose.

    line 63
  4. Distinctive:

    Add repeatable dialogue patterns that acknowledge prior visits without bloating state.

    line 64
  5. Very specific:

    Keep implementation-ready notes without drafting full Ink dialogue unless requested through if-draft-ink.

    line 66
  6. Distinctive:

    Do not write final Ink dialogue here.

    line 80
  7. Distinctive:

    Do not make critical knowledge missable without an alternate route.

    line 81
  8. Distinctive:

    Do not assume a fixed player conversation order.

    line 82

≈ “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 Dialogue

Overview

Use this skill to design the conversation layer of an exploratory Ink game. Conversations should work in player-chosen order, react to discovered knowledge, and avoid breaking continuity when topics are encountered early, late, or repeatedly.

Files To Read

Always read:

  • story.yaml
  • 03_characters/protagonist.md
  • 03_characters/supporting_cast.md
  • 04_design/story_beats.md
  • 04_design/state_model.md

Read when relevant:

  • 03_characters/relationships.md
  • 04_design/map.md
  • 04_design/locations.yaml
  • 04_design/dialogue_matrix.md
  • 04_design/progression.yaml
  • 07_continuity/*

Files To Write

Write or update:

  • 04_design/dialogue_matrix.md
  • 04_design/state_model.md when new conversation state is needed.

Optionally update:

  • 03_characters/relationships.md when interaction design clarifies relationships.

Dialogue Model

For each important character, define:

  • stable id;
  • where and when they can appear;
  • default conversational stance;
  • repeatable small talk or inspection loop;
  • one-time topic revelations;
  • topics gated by knowledge, inventory, skills, location, or prior dialogue;
  • relationship or trust changes;
  • what the character knows, conceals, misunderstands, or refuses to discuss.

Language Rules

Write project prose in story.language. Keep filenames, IDs, and YAML keys in English.

Procedure

  1. Identify which characters need interactive dialogue rather than static prose.
  2. Define topic groups and their dependencies.
  3. Ensure every critical clue has a reliable route and every optional clue has a purpose.
  4. Add repeatable dialogue patterns that acknowledge prior visits without bloating state.
  5. Mark topics that should become unavailable, altered, or newly available after state changes.
  6. Keep implementation-ready notes without drafting full Ink dialogue unless requested through if-draft-ink.

Output

Provide:

  • dialogue matrix summary;
  • key topic gates and revelations;
  • character availability rules;
  • state additions;
  • recommended next step, usually if-design-progression.

Restrictions

  • Do not write final Ink dialogue here.
  • Do not make critical knowledge missable without an alternate route.
  • Do not assume a fixed player conversation order.

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.