Dialogue Parser

SkillDev tools

Parses dialogue script text into intermediate section structures using regex, then builds a validated JSON graph schema with typed nodes and edges. Handles section headers, speaker lines, numbered choices with optional tags, and edge targets.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Dialogue Parser skill

What this skill tells your AI

The instructions your AI receives, as published by openlair/openskill in tasks-evolved/dialogue-parser/environment/skills/evo-dialogue-parser/SKILL.md and read by ahel’s review.

This skill parses raw dialogue script text files into a structured JSON graph.

Parsing Rules

  • Section headers: [NodeName] on their own line
  • Speaker lines: Speaker: text -> Target (target optional)
  • Choice lines: N. [OptionalTag] Choice text -> Target
  • Node type is "choice" if section has numbered choices, else "line"

Output Schema

{"nodes": [{"id": str, "text": str, "speaker": str, "type": str}], "edges": [{"from": str, "to": str, "text": str}]}

Key Functions

  • parse_dialogue_text(script_text) - Parse raw text into intermediate sections
  • build_json_graph(sections) - Convert sections to graph schema
  • validate_graph(graph) - Validate reachability and edge targets
  • parse_script(script_text) - End-to-end: parse, build, validate

Signals

GitHub stars
89
Forks
4
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
evo-dialogue-parser
Source
github.com/openlair/openskill