pattern-capture

Identify repetitive user feedback across AI sessions and generate automation artifacts.

19|5|Updated Jan 4, 2026

Search Tags:#code quality #prompt engineering #pattern recognition #continuous learning #ai safety #feedback automation

Ready to run

npx skills add https://github.com/edwinhu/workflows --skill pattern-capture

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pattern-capture
Source: https://github.com/edwinhu/workflows/tree/main/skills/pattern-capture
Command: npx skills add https://github.com/edwinhu/workflows --skill pattern-capture

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the inefficiency of repeatedly giving the same feedback or corrections to an AI, transforming those recurring instructions into automated enforcement mechanisms.

Core Features & Use Cases

Pattern Identification: Detects repetitive user corrections across sessions.
Artifact Generation: Classifies patterns and generates appropriate artifacts like memory entries, validation hooks, or new skills.
Use Case: If a user repeatedly corrects the AI on how to format code comments, this skill can identify that pattern and automatically create a new rule in the AI's memory or a specific validation hook to prevent future errors.

Quick Start

Use the pattern-capture skill to find and automate repeated feedback.

Frequently Asked Questions about pattern-capture

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

FAQPage Schema

How do I automate repetitive ai feedback and corrections across multiple sessions?▼

To automate repetitive ai feedback, you analyze memory files and session transcripts to identify recurring user corrections, then classify those patterns into actionable artifacts like memory entries or validation hooks to prevent future errors.

What is the best way to turn recurring prompt corrections into validation hooks?▼

Turning recurring prompt corrections into validation hooks requires identifying repeated user instructions across session transcripts and classifying those feedback patterns into automated enforcement mechanisms to ensure continuous learning and ai safety.

How does pattern recognition work for classifying user feedback in session transcripts?▼

Pattern recognition for user feedback analyzes session transcripts and memory files to detect repetitive corrections, classifying those recurring patterns into actionable artifacts like memory entries, validation hooks, or new skills for prompt engineering.

Can I use session transcripts to generate memory entries for code quality automation?▼

Yes, you can analyze session transcripts to identify recurring code quality corrections, classify those repetitive feedback patterns, and automatically generate memory entries or validation hooks to enforce those rules in future sessions.

What are the limitations of automating user feedback correction from session reports?▼

Automating user feedback correction requires sufficient memory files and session transcripts to identify recurring patterns; without consistent repetitive corrections in the data, it cannot generate actionable artifacts like validation hooks or new skills.