ankitai-s

Superdialog Playbook Skill — Development skill for Claude Code

Development community

Claude Code / Codex skill for authoring and reviewing SuperDialog voice-agent playbook YAMLs — schema reference, 15-point failure-pattern checklist, interrupt-guard code pattern.

How to install Superdialog Playbook Skill

This entry records only its repository, not the path inside it, so there is no exact command to give. Open ankitai-s/superdialog-playbook-skill and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Superdialog Playbook Skill does

Claude Code / Codex skill for authoring and reviewing SuperDialog voice-agent playbook YAMLs — schema reference, 15-point failure-pattern checklist, interrupt-guard code pattern.

Alternatives in Development

Skill Authoring Standard — The DNA of every skill in this repository 5.3k ★
Stop Review Gate — You are reviewing uncommitted changes before the author finishes their turn 664 ★
Pi Reserved Keybindings — Extensions cannot override these shortcuts — they are silently skipped by registerShortcut() 526 ★

README

superdialog-playbook-skill

[![Claude Code](https://img.shields.io/badge/Claude%20Code-compatible-D97757?logo=anthropic&logoColor=white)](https://github.com/ankitai-s/superdialog-playbook-skill) [![Codex](https://img.shields.io/badge/Codex-compatible-412991?logo=openai&logoColor=white)](https://github.com/ankitai-s/superdialog-playbook-skill) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE) [![Patterns](https://img.shields.io/badge/failure%20patterns-15-blue)](playbook/references/checklist.md)

A skill for building, reviewing, and fixing **SuperDialog voice-agent playbook YAMLs** — the `persona` / `llm` / `journeys` / `checkpoints` / `interrupts` / `policies` / `knowledge_base` schema that drives a Director+Talker voice agent.

Works identically in **Claude Code** and **Codex** — both load the same `SKILL.md` + `references/` format natively, no conversion needed.

How a playbook actually runs

Every turn, the **Director** (a fast/cheap LLM) reads the transcript and decides whether to advance the checkpoint, fire an interrupt, or stay — then the **Talker** (usually a stronger LLM) speaks from whatever checkpoint the Director landed on. Almost every hard bug in a playbook traces back to something left to Director/Talker *judgment* that should have been made *structural* instead.

sequenceDiagram
    autonumber
    actor Caller
    participant Runtime
    participant Director as Director LLM
(judge: llm | expr)
    participant Talker as Talker LLM

    Caller->>Runtime: speaks this turn
    Runtime->>Director: evaluate(transcript, current checkpoint)
    alt slot filled / expr condition met
        Director-->>Runtime: advance -> next checkpoint
    else caller said something matching an interrupt
        Director-->>Runtime: interrupt -> target checkpoint
    else nothing resolved yet
        Director-->>Runtime: stay
    end
    Runtime->>Talker: current checkpoint's guidance + slots
    Talker-->>Caller: spoken