Analyzes past learnings and failure logs to discover recurring issues and optimize future behavior.

Install

mkdir -p .claude/skills/trace-analysis && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13159" && unzip -o skill.zip -d .claude/skills/trace-analysis && rm skill.zip

Installs to .claude/skills/trace-analysis

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Use during retrospective or when trying to understand recurring failure patterns across sessions, based on historical learnings data in .agent-harness/learnings.jsonl.
167 chars✓ has a “when” trigger
Beginner

Key capabilities

  • Classify failure patterns from historical learnings data
  • Identify recurring failure modes across sessions
  • Prioritize skill improvements based on analyzer output
  • Match analyzer recommendations to skill invocations
  • Interpret output to understand systemic issues

How it works

This skill uses a trace analyzer script to classify failure patterns like 'loop' or 'drift' from historical session data. It then sorts these patterns by count to prioritize improvements.

Inputs & outputs

You give it
Historical learnings data in `.agent-harness/learnings.jsonl`
You get back
Classification of failure patterns and recommendations for skill improvement

When to use trace-analysis

  • Conduct retrospective
  • Analyze failure trends
  • Improve agent reliability
  • Debug agent behavior

About trace-analysis

Classifies failures (e.g., loops, drift) from log files. Helps developers prioritize skill improvements based on actual session data.

Use during retrospective or when trying to understand recurring failure patterns across sessions, based on historical learnings data in .agent-harness/learnings.jsonl.

When not to use it

  • When treating one learning as a pattern (requires 3+ occurrences)
  • When skipping analysis because learnings are sparse
  • When acting on every pattern at once

Limitations

  • Requires historical learnings data in `.agent-harness/learnings.jsonl`
  • Needs 3+ occurrences to confirm a real pattern
  • Recommendations are matched to specific skill invocations

How it compares

This skill provides a data-driven approach to identify and prioritize agent failure patterns from historical session data, offering concrete recommendations for skill improvements, unlike relying on intuition.

Compared to similar skills

trace-analysis side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
trace-analysis (this skill)01moReviewBeginner
model-usage52moReviewBeginner
analytics-tracking76moNo flagsIntermediate
splunk-analysis55moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

model-usage

openclaw

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

548

analytics-tracking

davila7

When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," or "tracking plan." For A/B test measurement, see ab-test-setup.

736

splunk-analysis

incidentfox

Splunk log analysis using SPL (Search Processing Language). Use when investigating issues via Splunk logs, saved searches, or alerts.

536

tracking-crypto-derivatives

jeremylongshore

Track cryptocurrency futures, options, and perpetual swaps with funding rates, open interest, liquidations, and comprehensive derivatives market analysis. Use when monitoring derivatives markets, analyzing funding rates, tracking open interest, finding liquidation levels, or researching options flow. Trigger with phrases like "funding rate", "open interest", "perpetual swap", "futures basis", "liquidation levels", "options flow", "put call ratio", "derivatives analysis", or "BTC perps".

437

weights-and-biases

davila7

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

325

perf-analyzer

ComposioHQ

Use when synthesizing perf findings into evidence-backed recommendations and decisions.

324

Search skills

Search the agent skills registry