self-reflection-knowledge-extraction

Extract reusable engineering knowledge from completed technical tasks.

1|Updated Apr 7, 2026
One-click install
npx skills add https://github.com/eatbreads/.agents --skill self-reflection-knowledge-extraction
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: self-reflection-knowledge-extraction
Source: https://github.com/eatbreads/.agents/tree/main/skills/self-reflection-knowledge-extraction
Command: npx skills add https://github.com/eatbreads/.agents --skill self-reflection-knowledge-extraction

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Turn a completed technical task into concise, reusable engineering knowledge instead of a narrative summary by extracting decision patterns, recognition signals, standardized troubleshooting flows, anti-patterns, and compact experience cards that speed future work.

Core Features & Use Cases

  • Extracts only high-signal, reusable artifacts: key decisions, recognition signals, narrowing strategies, standard debug flows, anti-patterns, and a standalone experience card.
  • Provides three output modes: direct in-chat reflection for immediate use, a registerable SKILL.md draft for saving as a reusable skill, or a knowledge-card formatted for storage at a specified path.
  • Ideal after successful coding, debugging, CI or pipeline runs, agent workflows, or confirmed root-cause analyses to convert success into operational knowledge for runbooks, onboarding, or automation.

Quick Start

Ask the skill to extract reusable knowledge from this successful task and output a concise experience card directly in chat.

Frequently Asked Questions about self-reflection-knowledge-extraction

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

FAQPage Schema
How do I extract reusable knowledge from a completed debugging task?

To extract reusable knowledge from debugging, you process the completed task to identify key decisions, recognition signals, and standard troubleshooting flows, generating a concise experience card for future reference.

What is the best way to create a runbook after a root-cause analysis?

Creating a runbook after a root-cause analysis involves extracting anti-patterns and narrowing strategies from the event, which can be formatted into a standalone knowledge card saved to a specified path.

Can I generate a SKILL.md draft from a successful CI pipeline run?

Yes, you can generate a registerable SKILL.md draft from a successful CI pipeline run by extracting high-signal operational knowledge and selecting the draft output mode to save it as a reusable skill.

Does knowledge extraction work for agent workflow retrospectives?

Knowledge extraction works effectively for agent workflow retrospectives by converting successful automated processes into compact decision patterns and experience cards for onboarding or future automation.

What formats are available for saving postmortem knowledge?

Available formats for saving postmortem knowledge include direct chat output for immediate use, a registerable SKILL.md draft, or a standalone knowledge card saved to a specified file path.

How do I mark uncertain inputs when extracting engineering knowledge?

When extracting engineering knowledge, the process explicitly marks uncertain inputs within the generated artifacts to ensure accuracy and signal reliability for future runbook or automation use.