Automatically extract reusable skills from Codex session transcripts using LLM analysis and wire them into a Stop hook
Scanned 9/9/2026
Install to Claude Code
Skills Directorynpx -y skills add vamseeachanta/workspace-hub --skill extract-skills-from-claude-code-sessions --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Extract Skills From Claude Code Sessions?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/vamseeachanta-extract-skills-from-claude-code-sessions)More formats (shields.io, HTML) on the badges page.
---
name: extract-skills-from-Codex-sessions
description: Automatically extract reusable skills from Codex session transcripts using LLM analysis and wire them into a Stop hook
version: 1.0.0
source: auto-extracted
extracted: 2026-04-10
metadata:
tags: ["Codex", "skills", "automation", "self-improvement", "hooks"]
---
# Extract Skills from Codex Sessions
Wire a Stop hook that fires when Codex ends a session. The hook runs `skill-extractor.py`, which reads the transcript, calls an LLM (via OpenRouter) to identify skill-worthy patterns, and writes a SKILL.md file if extraction succeeds. Use `openai` library for API calls, strip JSON fence artifacts with `.strip()`, and request concise content (<1500 tokens) to avoid truncation. Test end-to-end with synthetic skill-worthy conversations before deploying.Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
