session-runner

Automate D&D playtest sessions across PREP, PLAY, and LOG stages.

Updated Apr 19, 2026
One-click install
npx skills add https://github.com/giodl73-repo/QUEST --skill session-runner
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: session-runner
Source: https://github.com/giodl73-repo/QUEST/tree/main/.claude/skills/session-runner
Command: npx skills add https://github.com/giodl73-repo/QUEST --skill session-runner

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Running a full D&D playtest with fidelity, repeatability, and voice-consistency is labor-intensive. This skill automates the end-to-end session lifecycle by acting as a deterministic DM and all PCs, orchestrating PREP → PLAY → LOG and producing canonical session artifacts for auditing and iteration.

Core Features & Use Cases

  • Orchestrates a 7-stage session pipeline (PREP, PLAY, LOG and downstream stages) to streamline playtest design, execution, and logging.
  • Supports both Option A (solo-DM) and Option C (per-PC agent-spawn at meaningful decision points) to preserve character voice and dramatic tension.
  • Ensures deterministic dice resolution via a built-in dice engine and logs every mechanical outcome for reproducibility.
  • Generates canonical artifacts such as sessions/S{N}-prep.md and sessions/S{N}-log.md, and updates the party shared log for ongoing memory.
  • Logs detailed state changes, warnings, and manifest events (state_updates/events) for cross-session playtesting analysis.

Quick Start

Create an adventure module (module.md) and a party directory (personas/parties/...), then run the session-runner to generate the first session log at sessions/S1-log.md.

Frequently Asked Questions about session-runner

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate a D&D playtest session from start to finish?

You can automate a D&D playtest by orchestrating the PREP, PLAY, and LOG stages using a compiled module.md and file-based party sheets. The session-runner acts as a deterministic DM and all PCs, generating canonical session logs for reproducibility.

What do I need to set up before running an automated D&D playtest?

To run an automated D&D playtest, you need a compiled adventure module at module.md, party sheets stored in a personas/parties directory, a sessions directory for outputs, and an executable dice engine for deterministic mechanical resolution.

How does per-PC agent-spawn work during AI dungeon master play?

Per-PC agent-spawn activates at meaningful decision points during AI dungeon master play, preserving character voice and dramatic tension. This Option C mode contrasts with Option A solo-DM mode, where the system deterministically controls all player characters.

Can I generate reproducible logs for cross-session D&D playtesting analysis?

Yes, the system generates canonical artifacts like sessions/S{N}-prep.md and sessions/S{N}-log.md, logging detailed state changes, warnings, and manifest events to ensure reproducible logs for cross-session playtesting analysis.

What is the best way to maintain party memory across multiple D&D playtest sessions?

The best way to maintain party memory across multiple D&D playtest sessions is by updating the party shared log during the LOG stage. This ensures ongoing memory and state continuity for subsequent playtest iterations.

Are there limitations to using a deterministic dice engine for AI D&D playtesting?

A deterministic dice engine ensures reproducible mechanical outcomes for audit and gate analysis, but it removes the randomness of physical dice. You should not use this approach if your playtest requires true random number generation for statistical variance.