Coordinate coding agents through AMQ. Use for agent messages, inboxes, receipts, sessions, wake delivery, cross-project routing, managed launches, or AMQ diagnostics. Use amq-spec for collaborative design; do not use this for general message queues or…
Pre-flight GitHub bounty security scanner and on-chain Proof-of-Escrow MCP verifier for AI coding agents. Classifies GitHub bounties into SAFE_WITH_ESCROW, SAFE_NO_ESCROW, or QUARANTINE.
Use this whenever you need to know what is actually in a database, warehouse, or DuckDB file before you trust it: inventory, column profiles, PII detection, grain and data-quality problems, verified joins, ER diagrams, ad-hoc SQL probes, segmentation, and the…
Use this to find out whether an existing dbt project or semantic layer (dbt, Ossie or SLayer) is correct against its warehouse, and if not, why. `maintain verify` checks the project as it stands; against a .dex/ snapshot, `maintain check` finds schema,…
Use this to author and change a dbt project or a semantic layer: bootstrap a project (`transform init`), write or refactor models from staging to marts, add tests and docs, and define semantic models, entities, dimensions, and metrics in MetricFlow, Apache…
Talk privately with another person's AI agent over SwarmMemo from Claude Code or Codex, in a DM or a group, optionally end-to-end encrypted (sealed), with every outgoing message scanned for secrets and every incoming one screened for prompt injection. Use…
Pro Motion: make a high-taste motion-graphics launch film, brand film, TVC or promo video and the unconventional campaign around it, audio first: pick a surprising campaign mechanism (media hijack, fake-broken ads, meme replies, UGC army, FOOH), plan the…
Write, upgrade or audit a Claude skill so it actually changes what gets generated, not a pile of notes. Use whenever the user wants to create a skill, turn a conversation, workflow or methodology into a skill, rename it, add research or lessons, asks why a…