Agent skill · software engineering · jeremylongshore
assemblyai-reference-architecture
Analyze and design an AssemblyAI architecture spanning pre-recorded jobs, Streaming v3, LLM Gateway, callbacks, queues, retention, and audit evidence. Use when performing system design or review. Trigger with "AssemblyAI architecture" or "design AssemblyAI pipeline".
Why this skill is useful
Provides a structured project layout and specific implementation patterns for AssemblyAI transcription services that the AI wouldn't reliably generate on its own.
What it needs
Requires assemblyai installed locally. About 2k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
AssemblyAI Governed Reference Architecture Overview Design explicit trust and lifecycle boundaries for ingestion, jobs, live turns, analysis, and deletion. Keep data, credentials, region, spend, and destructive state visible. Prerequisites The target repository or integration path and the requested operator outcome. The AssemblyAI project, environment, region, data classification, and accountable owner. Current first-party documentation plus credentials only for a narrowly approved live check. Current Contract Pre-recorded jobs are asynchronous resources addressed by transcript ID. Streaming v3 is a stateful billed session requiring termination. LLM Gateway is a separate analysis plane replacing LeMUR. Callback payloads differ by family. Region, principal, credential, retention, and deletion remain visible on every edge. Authentication For live work, inject ASSEMBLYAIAPIKEY from an approved secret manager and send the raw value only in the AssemblyAI Authorization header to the configured first-party host. Never print, commit, place in a URL, or expose it to an untrusted client. Callback secrets and temporary streaming tokens are separate credentials. Instructions 1. Capture use cases, SLOs, languages, data classes, consent, region, retention, and cost. 2. Separate audio ingress, submitter, v3 gateway, token issuer, callback ingress, queues, workers, and stores. 3. Assign each edge a principal, credential, host, timeout, retry budget, and schema. 4. Model job and session states including duplicates, reconnect, failure, and termination. 5. Place LLM Gateway behind prompt allowlists and output schemas. 6. Map deletion through vendor, storage, databases, caches, search, and analytics. Tool Discipline Use Read, Glob, and Grep to inspect repository code, configuration, fixtures, and evidence. Use Write and Edit only for approved implementation or documentation changes. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/assemblyai-reference-architecture