Produces a named ADA disposition preset (YAML) and a layered behavioral analysis (structural decomposition + evidence-cited classifications) from a system prompt. Use when: "analyze this system prompt", "extract disposition from prompt", "reverse-engineer agent behavior", "what patterns does this prompt use", "build a preset from this prompt".
System prompts are the DNA of agent behavior. Reading them carefully reveals what the designers optimized for -- and what they sacrificed. Every constraint implies a past failure; every encouragement implies a desired behavior that doesn't happen naturally.
Archaeology is the right metaphor: you are uncovering layers of intent deposited over time. The earliest layers are identity and safety. Later layers add tool definitions, behavioral nudges, output formatting. The strata tell a story about what went wrong in production and how the team responded.
This skill does not judge prompts as good or bad. It classifies them structurally so their patterns can be reused, adapted, or deliberately avoided.
Do NOT use when:
Source the raw text. Preferred sources in order of reliability:
Piebald-AI/claude-code-system-prompts GitHub repo (versioned, dated)Record: tool name, version, date acquired, acquisition method, and confidence level.
Parse the prompt into these canonical layers (not all will be present):
| Layer | What to Look For |
|---|---|
| Identity | Name, role definition, persona framing ("You are...") |
| Safety/Constraints | Refusal patterns, content policy, boundary rules |
| Tool Definitions | Available tools, parameter schemas, usage instructions |
| Behavioral Rules | Pacing, initiative, verbosity, formatting preferences |
| Output Formatting | Response structure, markdown usage, citation style |
| Context Injection | System reminders, memory sections, dynamic context |
| Meta-Instructions | Instructions about how to handle instructions |
Tag each section with its layer. Note sections that span multiple layers.
For each behavioral rule, classify along these dimensions:
Document evidence for each classification -- quote the specific prompt text.
Translate behavioral signals into ADA-compatible disposition format:
preset_name: "[Tool]-[Version]-[Archetype]"
source_tool: "[Tool name and version]"
extracted_date: "[ISO date]"
behavioral_cluster: "[Deep Investigator|Rapid Builder|Balanced Assistant|Minimal Responder]"