X2 Extract

by teklabsdigital

X2 Extract is an AI Engineering skill for Claude Code, published by teklabsdigital in x2-method.

14 stars1 forkson teklabsdigital/x2-methodAdded 2026/08/12+8% in starsRepository updated 2026/08/06

View source on GitHub Download repo ZIP

agentic-codingagileai-agentsai-assisted-developmentclaudeclaude-codeclaude-skillsdotnetllm

Install in seconds

Install X2 Extract

Copy X2 Extract into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/teklabsdigital/x2-method/tree/master/skills/extract ~/.claude/skills/extract

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/teklabsdigital/x2-method.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/extract/SKILL.md in teklabsdigital/x2-method
Installs to: ~/.claude/skills/extract
Collection: One of 13 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What X2 Extract does

X2 Extract runs after an X2 project reaches a milestone to compute metrics, churn, and sanitized method-level findings from the turn ledger and decision records. It prepares candidates, confirmations, and negative-space nominations for a human rulings pass without exposing raw project material.

X2 Extract is cataloged under AI Engineering on DirSkills. X2 Extract comes from a repository tagged agentic-coding, agile, ai-agents, ai-assisted-development and claude.

Documentation

README

Excerpt

X2 Extract

The turn ledger is not just a cost record. It is a map of negative space: every human turn marks a place the method or the edition was not yet good enough. Defect turns are the loud half of that map. The quiet half is churn: a wrong-but-green decision leaves no defect behind it, it gets reworked across many small, individually-green turns that cluster on the same decision. This skill mines both halves and feeds the method, so each project makes the next one cheaper. It exists so the loop runs the same way every time, without anyone having to think about how.

Run in its own context (the intake seat), never the builder's. The builder is the measured subject and does not grade its own record.

1. Intake

This is the opening of the README. Read the full README on GitHub.

Frequently asked about X2 Extract

What else does teklabsdigital publish alongside X2 Extract?
X2 Extract is one of 13 skills that DirSkills catalogs from teklabsdigital/x2-method, the repository it ships in. Its siblings there include Decompose, Derive Tests and Lock. Each one is a separate skill with its own page in this directory, installs the same way X2 Extract does, and is maintained by teklabsdigital in that same repository. The rest of the collection is listed on the teklabsdigital/x2-method page.
How does X2 Extract compare to other AI Engineering skills?
X2 Extract ranks #2407 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of X2 Extract against them. Open each page to compare what they document and how they install.