chat-scout-method-zh

Name: chat-scout-method-zh
Availability: InStock
Author: funnycups

Identify key narrative elements from recent chat logs with signal filtering.

387|31|Updated Feb 8, 2026

Search Tags:#storytelling #chat analysis #signal filtering #narrative planning #emotional thread detection

Ready to run

npx skills add https://github.com/funnycups/Luker --skill chat-scout-method-zh

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: chat-scout-method-zh
Source: https://github.com/funnycups/Luker/tree/main/default/skills/global/chat-scout-method-zh
Command: npx skills add https://github.com/funnycups/Luker --skill chat-scout-method-zh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps identify key elements in recent chat logs, such as unresolved emotional threads and setups awaiting payoff, to inform the direction of a narrative scene.

Core Features & Use Cases

Unresolved Emotional Threads: Detects questions raised but unanswered and tensions that remain unreleased.
In-Flight Setups: Identifies character promises, decisions, and foreshadowed objects waiting for payoff.
Character States: Recognizes recent character decisions and commitments.
Tonal Trajectory: Monitors the emotional tone over time.
Signal Filtering: De-emphasizes lines that did not resonate with the audience.
Output Format: Provides a list of up to 6 relevant items with one-line summaries, source citations, and signal levels.

Quick Start

Run the chat-scout-method-zh skill on the last 10 turns of chat to identify key narrative elements.

Frequently Asked Questions about chat-scout-method-zh

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

FAQPage Schema

How do I detect unresolved narrative threads in recent chat logs?▼

Identify in-flight setups in storytelling chats by scanning recent chat logs for character promises, decisions, and foreshadowed objects waiting for payoff. The skill outputs up to 6 relevant items with one-line summaries, source citations, and signal levels to guide narrative planning.

How does signal filtering work for chat analysis in narrative planning?▼

Signal filtering for chat analysis works by de-emphasizing lines that did not resonate with the audience, ensuring only meaningful character states and tonal trajectories inform your narrative planning. This highlights emotional threads with active audience engagement for scene direction.

Can I use chat analysis to monitor tonal trajectory and character states?▼

You can use chat analysis to monitor tonal trajectory by tracking the emotional tone over time across recent chat logs. The skill also recognizes recent character decisions and commitments, providing source citations and signal levels to map emotional contexts for storytelling workflows.

What is the best way to extract emotional threads from chat logs for content creation?▼

The best way to extract emotional threads from chat logs for content creation is to scan the last 10 turns of chat for unresolved tensions and unanswered questions. This yields up to 6 cited items with signal levels, directly informing scene direction and character emotional contexts.

Does chat analysis for storytelling require specific dependencies or components?▼

Chat analysis for storytelling requires no specific dependencies or components to function. The skill operates independently on recent chat logs, applying signal filtering to extract narrative elements and output structured summaries with source citations and signal levels.