pattern-recognition

Detect recurring structural problems and codify them into automated pattern checks.

1|Updated May 6, 2026
One-click install
npx skills add https://github.com/jacob-balslev/skill-graph --skill pattern-recognition-jacob-balslev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pattern-recognition
Source: https://github.com/jacob-balslev/skill-graph/tree/main/marketplace/skills/pattern-recognition
Command: npx skills add https://github.com/jacob-balslev/skill-graph --skill pattern-recognition-jacob-balslev

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you stop repeatedly fixing the same underlying issues by identifying recurring patterns in errors, code, board states, design systems, and domain data, then codifying detection so the violations can’t keep reappearing.

Core Features & Use Cases

  • Observe → Cluster → Name → Codify → Detect → Prevent workflow to elevate recurring findings into durable automated checks.
  • Grep-based audit discipline (define, scan, count, sample, classify, triage) plus a three-pass strategy (discovery, refinement, verification) to minimize false positives.
  • Deterministic error clustering via normalize-then-hash to group repeated failure modes (tool failures, type errors, runtime crashes, stalls, permissions, context exhaustion, and more).
  • Board-health pattern detection (stale tasks, WIP overflow, priority drift, duplicates, orphans) with process-oriented prevention guidance.
  • Design-pattern and domain-pattern recognition (token drift, heading hierarchy contract violations, null-vs-zero, minor/major conversions, safe math boundaries) with eval-as-pattern-test guidance.

Quick Start

Use this Skill to audit a repository for recurring convention drift and generate actionable pattern-based detection and prevention steps.

Frequently Asked Questions about pattern-recognition

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

FAQPage Schema
How do I detect and prevent recurring convention drift in a codebase?

To detect convention drift, you define deterministic grep audits, scan and count matches, sample results, classify violations, and triage findings. This define-to-triage workflow minimizes false positives and turns recurring structural problems into durable automated checks that prevent repeat regressions.

Can I automate design-token and heading hierarchy invariant enforcement using grep audits?

Yes, you can enforce design-token and heading hierarchy invariants using grep-based audits combined with an eval-as-pattern-test step. This approach detects structural drift in design systems deterministically, ensuring violations are caught by automated checks before reaching production.

What is the best way to cluster recurring error failures from session logs?

The best way to cluster recurring failures is normalize-then-hash error clustering, which groups tool failures, type errors, and runtime crashes by their normalized signatures. This deterministic method prevents false positives and reveals the true root cause behind repeated regressions.

How do I audit a repository for board-health issues like stale tasks and WIP overflow?

Board-health pattern detection identifies stale tasks, WIP overflow, priority drift, duplicates, and orphans by applying deterministic scanning to board states. This process-oriented prevention guidance codifies detection so workflow violations are automatically flagged and prevented.

What are the limitations of using grep audits for pattern detection?

Grep audits require a three-pass strategy of discovery, refinement, and verification to minimize false positives. Without deterministic detection methods and an eval-as-pattern-test step before relying on automation, grep-based pattern detection risks surfacing inaccurate structural violations.