explanation-traces

Explain routing, agent selection, and gate verdicts from session-trace.json entries.

415|44|Updated Mar 18, 2026
One-click install
npx skills add https://github.com/notque/vexjoy-agent --skill explanation-traces
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: explanation-traces
Source: https://github.com/notque/vexjoy-agent/tree/main/skills/meta/explanation-traces
Command: npx skills add https://github.com/notque/vexjoy-agent --skill explanation-traces

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Explanation traces prevent confident-sounding but unverifiable rationalizations by showing users a factual timeline of routing, agent selection, skill phases, and gate outcomes from the recorded session trace.

Core Features & Use Cases

  • Reads recorded decision evidence: Presents a human-readable timeline sourced only from session-trace.json, never from memory or post-hoc inference.
  • Query-focused trace filtering: Narrows results to the specific decision the user asks about (e.g., routing, a chosen agent, gate verdicts).
  • Honest gap reporting: Flags missing or incomplete evidence fields so answers do not overclaim when the trace is partial.
  • Troubleshoots missing tracing: If the trace file is absent, guides enabling hooks and points to the expected trace schema.

Quick Start

Ask your agent to explain routing decisions and show the decision log for your current session by querying the trace, for example: "show trace for why you chose that agent".

Frequently Asked Questions about explanation-traces

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

FAQPage Schema
How do I trace why an agent was chosen during a workflow?

To trace agent selection, query the session-trace.json file to view a factual timeline of routing decisions. This filters recorded JSON evidence to show exactly why a specific agent was picked, preventing post-hoc rationalizations.

How does decision tracing handle missing or incomplete trace evidence?

Decision tracing handles incomplete evidence by flagging missing fields and reporting gaps honestly. It applies integrity checks against the session-trace.json schema to ensure answers do not overclaim when the recorded data is partial.

What is the best way to troubleshoot why a workflow gate failed?

The best way to troubleshoot a failed gate is to filter the session-trace.json for gate verdicts. This read-only approach presents the exact recorded decision evidence, showing the specific reason a gate failed without reconstructing events.

Can I visualize routing decisions if the trace file is absent?

You cannot visualize routing decisions without the trace file, but the system guides you on enabling hooks to generate it. It points to the expected trace schema so you can start recording session data for future analysis.

Does decision tracing reconstruct routing events from memory?

Decision tracing does not reconstruct events from memory. It parses session-trace.json using read-only discovery to present a human-readable timeline of routing and skill phase transitions, preserving the original evidence exactly as recorded.