wicked-garden:classify

Classify user prompts into v11 work-shape archetypes and persist signals to SessionState.

8|2|Updated Feb 9, 2026

Search Tags:#LLM #catalog #archetypes #classify #session-state #prompt-routing

Ready to run

npx skills add https://github.com/mikeparcewski/wicked-garden --skill wicked-garden-classify

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: wicked-garden:classify
Source: https://github.com/mikeparcewski/wicked-garden/tree/main/skills/classify
Command: npx skills add https://github.com/mikeparcewski/wicked-garden --skill wicked-garden-classify

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

v11 LLM-based work-shape classifier. Replaces the regex archetype detector with the model's own reasoning. Reads the user's prompt, picks the right archetype(s) from the catalog, identifies signals (blast_radius, novelty, reversibility, etc.), and persists to SessionState so downstream turns are steered correctly.

Core Features & Use Cases

Classifies prompts into v11 archetypes using model-driven reasoning instead of regex.
Identifies signals such as blast_radius, novelty, reversibility, ambiguity, and scope to guide downstream playbooks.
Persists results to SessionState for consistent routing across turns and re-classification events.
Use at session start, when a <wg classify-due /> directive is emitted, or during mid-session re-classification after scope changes.

Quick Start

Invoke the classify function at session start or whenever you want to reclassify the current prompt to steer routing.

Frequently Asked Questions about wicked-garden:classify

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

FAQPage Schema

How does LLM prompt classification route sessions to different work archetypes?▼

LLM prompt classification analyzes the user prompt using model-driven reasoning to select matching work-shape archetypes from a catalog. It identifies routing signals like blast_radius, novelty, and reversibility, then persists these classifications to SessionState to steer downstream task execution.

When should I re-classify a prompt during an active session?▼

You should re-classify a prompt during an active session whenever the scope changes significantly or when a specific classify-due directive is emitted. Mid-session re-classification updates the SessionState so downstream routing adapts to the new task requirements and signals.

How do I replace regex pattern matching with model-driven reasoning for prompt routing?▼

To replace regex pattern matching with model-driven reasoning for prompt routing, invoke an LLM-based classifier that reads the prompt and selects the correct work-shape archetypes from a predefined catalog. This approach uses the model's own reasoning to identify signals and persist results to SessionState.

Can I use prompt classification with SessionState for consistent routing across turns?▼

Yes, prompt classification persists its archetype selections and identified signals directly to SessionState. This ensures consistent task routing across multiple turns and prevents drift during mid-session re-classification events.

What signals are extracted during prompt classification to guide downstream playbooks?▼

During prompt classification, the model extracts signals including blast_radius, novelty, reversibility, ambiguity, and scope. These signals are identified through model-driven reasoning and stored in SessionState to guide the selection and execution of downstream playbooks.