DJ Claude – 6 Claude Codes in a jam band
Fun multi-agent jam concept but unclear execution—MCP spec is new, demo is Loom video, production viability unproven.
Claude Code skill for async collaborative brainstorming between human+Claude pairs
No merge conflicts by design since every save creates a unique file.
Developers using Claude Code for pair programming or research
Obsidian · Git
So I built a Claude skill that enables asynchronous collaboration between multiple human / agent pairs.
Its write once markdown files in a shared location, git, dropbox, network, that all users can view realtime. User driven summaries can be created to save context and summarise status for new joiners to the workspace. If wanted these can be posted to git discussions for wider collaboration or sharing.
On git there are no branches, merges or PRs so nothing to slow you down. Files are uniquely named so no clashes. It's all markdown files with links between summaries and summary commands that extract themes into a patterns.md file. No database, no embeddings or vector DBs. If you want to put Obsidian over the top you can, it's just not built in.
I'd love feedback on the concept and implementation. Raw data kept forever for review, with the compressed summaries available for faster review by humans and to save tokens for agents.
Fun multi-agent jam concept but unclear execution—MCP spec is new, demo is Loom video, production viability unproven.
TLA+ code generation for agents, but audience is tiny—only useful if your agent needs formal verification.
Self-modifying skills let agents persist new behaviors without restarts or config edits.
Naur's 1985 theory applied to AI agents, but it's just a prompt template.
AI-assisted TLAPS proof writing, but audience is tiny and proof quality unverified.
Charming async grid concept but no technical innovation to speak of.