Skip to content
Skills Library
AI & agents · Analysis

trace-debug

/trace-debug

Debug AI system behavior using traces — prompt reconstruction, output comparison, failure attribution. Use when asked "why did the model output this", "debug this LLM failure", or "reconstruct the prompt".

Repository
tonone ↗
Licence
MIT
Last repository change
14.10.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 14.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Debug AI system behavior using traces — prompt reconstruction, output comparison, failure attribution. Use when asked "why did the model output this", "debug this LLM failure", or "reconstruct the prompt".

Triggers from the description

why did the model output thisdebug this LLM failurereconstruct the prompt
Original author description

Debug AI system behavior using traces — prompt reconstruction, output comparison, failure attribution. Use when asked "why did the model output this", "debug this LLM failure", or "reconstruct the prompt".

How it works

  1. Steps
  2. Key Rules
  3. Output Format
  4. Delivery
Original SKILL.md headings · 34 lines, 245 words
SKILL.md preview
---
name: trace-debug
description: Debug AI system behavior using traces — prompt reconstruction, output comparison, failure attribution. Use when asked "why did the model output this", "debug this LLM failure", or "reconstruct the prompt".
allowed-tools: Read, Bash, Glob, Grep, Write, WebFetch, WebSearch, AskUserQuestion
version: 1.0.0
author: tonone-ai <hello@tonone.ai>
license: MIT
compatibility: Designed for Claude Code
tags: [ai-ops, observability, debug]
---

# Trace Debug

You are Trace — the LLM Observability Engineer on the AI Operations Team.

## Steps

### Step 0: Reproduce from the Trace

Pull the full trace for the failing request — reconstruct the exact prompt sent, including any retrieved context or tool outputs.

### Step 1: Compare Against Expected Behavior

Run the reconstructed prompt against the model again (or a known-good version) and compare outputs to isolate whether the model, the prompt, or the input data caused the failure.

### Step 2: Attribute the Failure

Pin the root cause to a specific stage — retrieval, prompt construction, model behavior, or post-processing — with the trace evidence that supports it.

## Key Rules

- Follow the output format defined in docs/output-kit.md
- Always reconstruct the exact prompt from the trace — don't debug against what the prompt template 'should' produce
- Distinguish a model failure from a data/retrieval failure before proposing a fix — they need different owners
- Cite the specific trace span or field as evidence for the root cause, not just a description of the symptom

## Output Format

A root-cause finding tied to a specific pipeline stage, with the trace evidence and a reproduction of the failure.

## Delivery

If output exceeds the 40-line CLI budget, invoke `/atlas-report` with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.

Versions

RepositoryScoreLicence
This page · tonone-ai/tonone90MIT
whitebeardit/claude-plugins100MIT

Identical content appears in 1 other GitHub folders. We show one copy with the highest score.

Database snapshot: 13.11.2026 · package version af84ce1e6126 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 90debug-agent-from-traces
    Use this to diagnose WHY an LLM agent or chain produced a wrong, empty, slow, or expensive result, by reading its observability trace. Trigger on "my agent gave the wrong answer", "the chain returned nothing", "why is this so slow/expensive", "debug this trace/run", or when a…
  • 95exploring-llm-traces
    ABSOLUTE MUST to debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace URL (e.g. /llm-observability/traces/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were…
  • 100arize-traces
    Retrieve and debug trace data from the Arize ML observability platform. Use when users want to list recent traces, look up a specific trace by trace ID, get all spans within a trace, analyze trace performance (latency, tokens, cost), or export trace data. Triggers on "list…
  • 100exploring-llm-traces
    Debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace or session URL (e.g. /ai-observability/traces/<id> or /ai-observability/sessions/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly,…
  • 90debug-agent
    Root-causes AI agent failures from MLflow traces without requiring a code change, regression suite, scorer, or evaluation run. Use when the user asks to debug, investigate, explain, or determine why an agent produced an output. Prefer an existing matching trace; reproduce only…
  • 100langsmith
    Monitor, trace, debug, and evaluate LLM applications with LangSmith. Use when a user asks to trace LLM calls, debug chain executions, evaluate AI output quality, set up LLM observability, monitor agent performance, run prompt experiments, compare model outputs, create evaluation…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.