skill-extractor

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

Analyze task execution trajectories and feedback memory to propose reusable skill modules.

1|Updated May 21, 2026

Search Tags:#automation #knowledge-management #pattern-recognition #workflow-optimization #agent-learning

Ready to run

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

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the problem of knowledge loss by identifying successful task execution patterns and converting them into reusable, standardized skill modules.

Core Features & Use Cases

Pattern Analysis: Automatically parses session outcomes to detect high-success workflows.
Proposal Generation: Drafts new SKILL.md files based on proven agent behavior and success rates.
Failure Analysis: Analyzes feedback memory to promote recurring failure resolutions into permanent structural improvements.

Quick Start

Run the skill extractor to analyze the current session and propose new skills based on successful task outcomes.

Frequently Asked Questions about skill-extractor

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

FAQPage Schema

How do I turn successful task execution patterns into reusable skills?▼

To turn successful task execution patterns into reusable skills, you analyze task trajectories and feedback memory to identify high-success workflows, then draft standardized skill modules based on that proven agent behavior.

What is the best way to automate knowledge management from agent task outcomes?▼

Automating knowledge management from agent task outcomes involves parsing session results to detect successful workflows, then generating standardized skill proposals to permanently expand the knowledge base and prevent knowledge loss.

How does pattern recognition work for converting ad-hoc task success into permanent knowledge?▼

Pattern recognition for permanent knowledge conversion works by automatically parsing session outcomes and feedback memory to detect high-success workflows, then promoting recurring failure resolutions into permanent structural improvements.

Do I need a task-outcome-recorder to generate reusable workflow proposals?▼

Yes, a task-outcome-recorder is required to capture session outcomes and feedback memory, providing the necessary task execution trajectories for the skill extractor to detect patterns and generate reusable workflow proposals.

Can I analyze failure resolutions to create permanent structural improvements in my workflows?▼

You can analyze failure resolutions to create permanent structural improvements by parsing feedback memory to identify recurring failure patterns, then promoting those resolutions into standardized skill modules within your knowledge base.