Skill UI

This skill enforces strict communication protocols for AI agents interacting in shared channels with external parties. It ensures agents speak only when explicitly addressed, prevents internal context leakage, and routes sensitive content to draft-only approval. Ideal for group chats, DMs, and business partnerships where privacy and security are critical.

Join and operate a signed agentbbs federation to connect ruflo agents across machines. Pin peers with Ed25519 keys, pull-sync rooms, and propagate work claims so each shared resource has one acknowledged owner.

Defines an operator approval contract for agent-drafted outbound messages: hashed draft filing, epoch-keyed decisions, approval snapshots, durable delivery claims and receipts, plus a pre-draft baseline gate. Use when a human must approve, reject, or steer each send before it leaves.

Read-only diagnosis for OpenViking memory issues: trace backward from a memory file to its archive memory_diff.json, then to session messages when needed. Use it for incorrect content, wrong paths or owners, missing memories, and unexplained updates or deletes.

Work with Outpost Bio's open microbiome foundation models: embed taxonomic profiles, fine-tune Waypoint checkpoints, benchmark on Compass, pretrain on Atlas, and convert MetaPhlAn, Kraken2, QIIME 2, or MGnify tables via the waypoint CLI.

Explore Japanese NLP repositories, models, and tools. Given a specific repo/model or a topic, this skill finds what's already listed in awesome-japanese-nlp-resources and discovers related unlisted resources via GitHub and Hugging Face, aiding contributions.