Skip to content
SkillModel-led2,535 tokens in use

Dialogue Systems

Builds engine-neutral branching dialogue with Ink, Yarn Spinner or a small JSON graph runner: lines, choices, conditions, variables and localization IDs.

9,682 stars on the repository Apache License 2.0gamedev-skills/awesome-gamedev-agent-skills · skills/disciplines/dialogue-systems
npx skills add gamedev-skills/awesome-gamedev-agent-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Dialogue Systems costs

96tokens idle
2,535tokens in use
6,203tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter8/15
  • Structure25/25
  • Examples12/15
  • Output15/15
  • Size15/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity92
  • Maintenance96
  • Community60
  • Maturity24
  • Momentum40

This skill models a conversation as a graph: nodes hold lines, choices branch, conditions gate options, and one variable store remembers what the player did. Its first decision is build or adopt, Ink or Yarn Spinner when writers need real flow control and a small data-driven runner when lines, choices and flags are enough.

It covers the runner contract, line IDs for localization, where to apply costs, and validation with the Ink and Yarn command-line compilers or a graph validator.

What You Get

  • A decision guide for Ink, Yarn Spinner or a custom runner, with the case each one suits
  • A JSON dialogue graph example with line IDs, gated choices and variable changes on the transition
  • Ink and Yarn Spinner examples for the same guard-and-bribe conversation
  • A validation routine covering compile errors, dead ends, missing targets, undeclared variables and unreachable nodes

Common Use Cases

  • Adding an NPC conversation with choices that depend on gold or earlier answers
  • Fixing a dialogue that stalls because a node has no next step or end
  • Preparing dialogue for translation by using line IDs from the start
  • Choosing a dialogue tool for a Unity or Godot project

What Makes It Unique

It is built around the mistakes that waste a writer’s time: costs placed on a node that can be revisited, Ink once-only choices that empty a hub menu, undeclared Yarn variables that only warn, Yarn 3 syntax in a Yarn 2 project, and expression evaluation that would run arbitrary code from data files. It states a rule never to invent a new scripting language.

Under The Hood

The skill is instructions and two reference files, one on Ink and Yarn syntax and one holding a custom runner with a validator. It has no scripts of its own. It tells the agent to look at the project for existing dialogue files and integrations, and to run the Ink compiler inklecate or the Yarn console ysc on the files to check them, which reads the story files and can write compiled output. It does not fetch web pages or call APIs. It warns against running eval on dialogue expressions.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers