claudeception

Extract non-obvious insights from work sessions into reusable Claude Code skills.

Updated Jan 24, 2026
One-click install
npx skills add https://github.com/strataga/claude-setup --skill claudeception-strataga
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: claudeception
Source: https://github.com/strataga/claude-setup/tree/main/skills/claudeception
Command: npx skills add https://github.com/strataga/claude-setup --skill claudeception-strataga

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Claude Code can autonomously extract reusable knowledge from work sessions and codify it into new skills, reducing repeated discovery work in future tasks.

Core Features & Use Cases

  • Continuous extraction: evaluates sessions to identify non-obvious insights worth preserving.
  • Auto-skill creation: generates human-readable YAML frontmatter Skill definitions and templates for future retrieval.
  • Semantic surface: stores skills in a library and surfaces them via context-aware matching during tasks.
  • Workflow integration: supports activation via /claudeception and "save this as a skill" prompts to build a knowledge base across projects.

Quick Start

Trigger an extraction by saying "save this as a skill" or running /claudeception, and Claudeception will generate a new Claude Code skill.

Frequently Asked Questions about claudeception

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

FAQPage Schema
How do I save reusable knowledge from a Claude Code debugging session?

Claude Code knowledge extraction works by evaluating active work sessions to identify non-obvious insights, then codifying them into human-readable YAML frontmatter skill definitions. These skills are stored in a library and surfaced via context-aware semantic matching during future tasks.

How do I create a reusable Claude Code skill from project exploration discoveries?

To create a reusable Claude Code skill from project exploration discoveries, prompt "save this as a skill" or run /claudeception. The system converts discoveries into a SKILL.md file featuring YAML frontmatter, a body, and optional scripts or references for future use.

Do I need YAML to build Claude Code skills with autonomous knowledge extraction?

Yes, YAML is required for autonomous knowledge extraction. The process generates a SKILL.md file containing YAML frontmatter with a name and description, alongside a body and optional scripts or assets for the skill library.

How are stored Claude Code skills retrieved during future tasks?

Stored Claude Code skills are retrieved using context-aware semantic matching. The memory model surfaces relevant skills from the library by evaluating the current task context against previously extracted knowledge definitions.

What is the best way to automate knowledge management across multiple Claude Code projects?

The best way to automate knowledge management across multiple Claude Code projects is through continuous extraction workflows. Triggering /claudeception across debugging and tool integration sessions builds a centralized, semantically searchable skill library.