AssemblyAI

Blurt's hard "don't do this" rules — architecture decisions that were made deliberately and reverted before. Load this before adding or changing engine/app/build/test code so you don't reintroduce something that was intentionally removed.

Cut and publish a Blurt release (build, sign, notarize, staple, DMG, GitHub). Use when the user asks to ship/release a new version. User-invoked only — it has real side effects (notarization, git tags, GitHub release).

Verify the repo is green by running scripts/check.sh — the same full health check CI runs (swift test + coverage gate, sanitizers, xcodegen drift, app build, swift-format/swiftlint/periphery/prettier/markdownlint/shellcheck). Use before claiming a change builds, passes, or is ready to commit/PR. Bakes in the macOS-only guard so a Linux/web sandbox flags "verify on a Mac" instead of fabricating a green result; there, scripts/check.sh --portable runs the platform-independent subset (docs/site/scripts/workflows).

Print a daily Blurt launch KPI snapshot — Blurt.dmg download count, GitHub stars, and repo traffic/referrers — and compare against the campaign's baseline/good/great bands. Use during launch week, or wrap with /loop for a recurring check.

Use the AssemblyAI CLI (`assembly`) from the command line — transcribe audio/video files, URLs, and YouTube/podcast links; stream live real-time transcription from a mic/file/system audio; run full-duplex voice agents; query the LLM Gateway over transcripts; browse transcript and streaming-session history; sign in and manage account balance, usage, rate limits, API keys, and audit logs; scaffold a starter app (init); diagnose setup (doctor); and set up your coding agent's AssemblyAI docs MCP + skills (setup). Use whenever an agent is invoking the `assembly` command.

Prepare an assembly CLI release — confirm main is green, then tag (locally or via the manual workflow) to trigger the bottle pipeline. Use when cutting a new release.

Run the full local verification gate for the assembly CLI (the same checks CI runs). Use before pushing or opening a PR.

Plan a new assembly CLI feature the way this repo does — drive the superpowers planning skill, then persist the spec + plan into docs/superpowers/ under this repo's naming and verification conventions. Use before building anything non-trivial.

Use when implementing speech-to-text, audio transcription, real-time streaming STT, audio intelligence features, or voice AI using AssemblyAI APIs or SDKs. Use when user mentions AssemblyAI, voice agents, transcription, speaker diarization, PII redaction of audio, LLM Gateway for audio understanding, or applying LLMs to transcripts. Also use when building voice agents with LiveKit or Pipecat that need speech-to-text, or when the user is working with any audio/video processing pipeline that could benefit from transcription, even if they don't mention AssemblyAI by name.