Detects anomalies in swing-scan and morning-brief workflows to prevent classifier drift.

Install

mkdir -p .claude/skills/bug-scan && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14322" && unzip -o skill.zip -d .claude/skills/bug-scan && rm skill.zip

Installs to .claude/skills/bug-scan

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.

Classifier-anomaly detector for the swing-scan, morning-brief, and external-scanner crons. Detects Pattern B shapes (absent-with-subs, silent, ghost), sub-signal weight drift, L3 calibration skew, and cross-TF classification contradictions. Audit 2026-06-23 #2.
261 charsno explicit “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Intermediate

Key capabilities

  • →Detect Pattern B shapes (absent-with-subs, silent, ghost)
  • →Detect sub-signal weight drift
  • →Detect L3 calibration skew
  • →Detect cross-timeframe classification contradictions
  • →Run offline against a pre-computed state file
  • →Perform fresh scans on ad-hoc tickers

How it works

The skill acts as a classifier-anomaly detector, applying specific rules to L2/L3 analysis outputs or state files to identify patterns like weight drift, calibration skew, and cross-timeframe contradictions.

Inputs & outputs

You give it
L2/L3 analysis envelopes, swing-scan state tracker, or ad-hoc tickers
You get back
A JSON report of detected classifier anomalies and their severity

When to use bug-scan

  • →Detect classifier anomalies
  • →Identify classification drift
  • →Surface cross-timeframe conflicts

About bug-scan

Classifies and detects anomalies in classification data, surfacing issues like signal weight drift and conflicting strategy directions across timeframes.

Classifier-anomaly detector for the swing-scan, morning-brief, and external-scanner crons. Detects Pattern B shapes (absent-with-subs, silent, ghost), sub-signal weight drift, L3 calibration skew, and cross-TF classification contradictions. Audit 2026-06-23 #2.

When not to use it

  • →For full L2/L3 analysis
  • →For live trade signals

Prerequisites

Python 3.12+uv

Limitations

  • →It is a detector, not a replacement for full L2/L3 analysis
  • →Output is purely diagnostic and should not be used for execution
  • →Requires specific input formats like L2/L3 envelopes or state files

How it compares

This skill provides a diagnostic layer on top of existing analysis tools, specifically identifying anomalies that might be missed by direct L2/L3 analysis, rather than performing the analysis itself.

Compared to similar skills

bug-scan side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
bug-scan (this skill)04moReviewIntermediate
langsmith-observability410moReviewIntermediate
optimizing-performance15moReviewIntermediate
fireflies-debug-bundle14moCautionBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

langsmith-observability

davila7

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.

430

optimizing-performance

CloudAI-X

Analyzes and optimizes application performance across frontend, backend, and database layers. Use when diagnosing slowness, improving load times, optimizing queries, reducing bundle size, or when asked about performance issues.

113

fireflies-debug-bundle

jeremylongshore

Collect Fireflies.ai debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Fireflies.ai problems. Trigger with phrases like "fireflies debug", "fireflies support bundle", "collect fireflies logs", "fireflies diagnostic".

13

sentry-debug-bundle

jeremylongshore

Execute collect debug information for Sentry support tickets. Use when preparing support requests, debugging complex issues, or gathering diagnostic information. Trigger with phrases like "sentry debug info", "sentry support ticket", "gather sentry diagnostics", "sentry debug bundle".

13

openrouter-debug-bundle

jeremylongshore

Execute set up comprehensive logging and debugging for OpenRouter. Use when investigating issues or monitoring requests. Trigger with phrases like 'openrouter debug', 'openrouter logging', 'openrouter trace', 'monitor openrouter'.

11

python-observability

wshobson

Python observability patterns including structured logging, metrics, and distributed tracing. Use when adding logging, implementing metrics collection, setting up tracing, or debugging production systems.

11

Search skills

Search the agent skills registry