instinct-extractor

Name: instinct-extractor
Availability: InStock
Author: hiddink-ai

Mine recurring failure patterns from multi-session agent transcripts to generate skill candidates.

1|Updated May 21, 2026

Search Tags:#automation #agent-memory #pattern-mining #skill-generation #continuous-improvement #transcript-analysis

Ready to run

npx skills add https://github.com/hiddink-ai/hiddink-harness --skill instinct-extractor-hiddink-ai

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: instinct-extractor
Source: https://github.com/hiddink-ai/hiddink-harness/tree/main/templates/skills/instinct-extractor
Command: npx skills add https://github.com/hiddink-ai/hiddink-harness --skill instinct-extractor-hiddink-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill addresses the inefficiency of manual error correction by automatically identifying recurring failure patterns across multiple agent sessions, transforming them into actionable skill candidates.

Core Features & Use Cases

Pattern Mining: Analyzes time-series transcript data to cluster errors, corrections, and feedback into distinct instinct patterns.
Skill Promotion: Bridges the gap between feedback memory and formal skill development by suggesting new capabilities based on repeated failures.
Use Case: If an agent repeatedly fails to include a required bypassPermissions flag during spawn, this skill identifies the pattern and proposes a new guard skill to prevent future occurrences.

Quick Start

Run the instinct extractor to analyze the last 14 days of session transcripts and identify potential new skill candidates.

Frequently Asked Questions about instinct-extractor

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

FAQPage Schema

How do I extract recurring failure patterns from agent session transcripts?▼

To extract recurring failure patterns from agent session transcripts, you can mine multi-session time-series data to cluster errors, corrections, and negative feedback into distinct behavioral instincts for continuous improvement.

How does pattern mining work for generating new agent skills?▼

Pattern mining for generating new agent skills works by analyzing multi-session transcript data to identify recurring errors and behavioral clusters, then promoting that feedback memory into formal, reusable skill modules.

Can I automate turning repeated agent errors into reusable skills?▼

Yes, you can automate turning repeated agent errors into reusable skills by integrating with defect response workflows to promote feedback memory into formal skill candidates based on identified failure clusters.

What is the best way to analyze multi-session transcripts for continuous agent improvement?▼

The best way to analyze multi-session transcripts for continuous agent improvement is to run an instinct extractor across time-series data to identify clusters of errors and corrections, proposing new guard skills to prevent future occurrences.

Does the instinct extractor require specific dependencies to analyze time-series transcript data?▼

No specific dependencies are required to analyze time-series transcript data, as the instinct extractor operates directly on multi-session agent transcripts to identify failure patterns and generate skill candidates.

When should I not use automated skill generation from transcript analysis?▼

Automated skill generation from transcript analysis may not be suitable when multi-session transcript data is unavailable or when failure patterns are too isolated to form actionable clusters for promoting feedback memory into formal skills.