Portable config for agent skills — for Skill creators and users alike.
<div align="center">
# skillctx
**Portable config for agent skills — for Skill creators and users alike.**
[](https://github.com/jackchuka/skillctx/actions/workflows/ci.yml)
[](https://www.python.org)
[](LICENSE)
[](https://github.com/jackchuka/skillctx)
<br>
<img alt="skillctx — one config, every skill, zero deps" src="assets/hero.svg" width="100%">
</div>
## The Problem
Agent skills are personal by default. A skill that posts your standup, manages your todos, or deploys your app is wired to **your** usernames, paths, Slack channel IDs, and API endpoints. It works perfectly — on your machine.
The moment you share it, it breaks. The next person has to dig through your SKILL.md, find every hardcoded value, and manually swap them out. Multiply that across ten skills and it's no longer "install and use" — it's "install and debug."
**For creators**, this means your skills aren't truly portable. You can publish them, but every user has to reverse-engineer your personal config.
**For users**, this means every new skill is a setup chore — hunting through files for values that need changing before anything works.
## The Solution
```diff
# SKILL.md (daily-standup)
- Post standup for alice in Slack (CABC123DEF) channel
- Save memo to ~/notes
+ Post standup for {username} in Slack ({channel_id}) channel
+ Save memo to {notebook_path}
```
Hardcoded values become `{placeholders}`, resolved at runtime from one shared config (`~/.config/skillctx/config.json`).
**For creators**: one command migrates your skill. No manual find-and-replace, no template syntax to learn.
**For users**: install a skill and run it. On first use you're prompted for missing values — fill theGoogle's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.