Plan AssemblyAI throughput and handle request limit errors by reviewing account capacity, separating operation queues, and bounding retries. Use callbacks, delayed retries, and transcript ID checks to control polling load and repeated submissions.
Build recurring database archival pipelines that move historical records into archive tables or cloud storage. Define retention criteria, verify batches before deleting source records, track archived files, and prepare retrieval procedures for later access.
Set up ways to detect Apple Notes changes using periodic polling, file system notifications, or Shortcuts automations. Produce deduplicated added, modified, and deleted events while keeping note content out of event records by default.
Run a small AssemblyAI transcription check on a pre-recorded fixture to validate a new integration. It selects a region and ordered model options, waits for a terminal job status, checks safe assertions, and returns a content-free pass or fail record.
Use this skill to plan and validate migrations from AssemblyAI Streaming v2 and LeMUR to Streaming v3 and LLM Gateway. It guides endpoint and message changes, output comparisons, synthetic test cases, canary rollout, rollback checks, and legacy cleanup.
Prepare for SOC 2 Type I or Type II audits by organizing evidence and reviewing controls against Trust Service Criteria. The skill identifies missing or weak controls and produces a readiness report, remediation backlog, and auditor interview guide.
Audit CORS, the browser rules for requests between different sites, by probing API responses with varied Origin headers. Check origin validation, credential settings, preflight requests, and caching headers, then produce findings in JSON, JSONL, or Markdown.
Review an AssemblyAI speech workflow’s credentials, processing region, consent, retention, deletion, and model training settings. It helps document data handling decisions, validate the requested scope, and report risks without exposing audio, transcripts, or secrets.
Design a typed adapter around the official AssemblyAI SDK so application code stays insulated from vendor changes. Define stable request and result types, regional routing, retries, polling, and streaming lifecycles while keeping credentials and sensitive audio or transcript content out of evidence.
Build Attio workflows for sales pipelines and operational queues. Keep parent records separate from list-specific information, reuse existing list entries, and verify updates while treating notes and tasks as separate linked resources.
Triage failures across AssemblyAI REST requests, transcripts, Streaming v3, webhooks, and LLM Gateway. Separate transport, authentication, quota, processing, and callback issues, then report a retry, input fix, capacity action, or escalation using content-free evidence.
Review an AssemblyAI integration before launch or a major change. Check evidence for authentication, data retention, reliability, cost, monitoring, and rollback, then produce a concise pass or fail receipt with risks and ownership.
Review an Attio integration’s access, tenant boundaries, logs, and webhook handling. The skill identifies security gaps around credential scope, secret rotation, signature checks, and duplicate event processing, then returns findings and remediation owners.
Design or review an AssemblyAI system for recorded audio jobs, live Streaming v3 sessions, and LLM Gateway analysis. Map services, credentials, queues, callbacks, retention, and deletion paths so the architecture makes data handling, costs, and operational boundaries visible.
Diagnose Attio REST API failures using response status, structured error details, and endpoint documentation. Identify authentication, permission, validation, and rate-limit problems, then apply a minimal correction and verify it while keeping tokens and customer data out of diagnostic records.
Set up REST authentication for an Attio integration by choosing a workspace API key or OAuth for multiple workspaces. Map required scopes to endpoints, protect and rotate tokens, and verify access with a read-only request.
Design a production Attio integration from existing repository code. Plan workspace-specific credentials, queued writes, verified event notifications, duplicate handling, and data reconciliation, then document component ownership, rollout steps, and rollback procedures.
Diagnose slow Attio requests and growing sync queues by measuring query complexity, pagination, concurrency, retries, and cache behavior. Compare a targeted change against a representative baseline while checking data correctness, freshness, and rollback thresholds.
Measure an Attio integration’s requests, retries, query patterns, sync churn, and retained data to find avoidable workload. Get ranked, reversible improvement proposals with estimated impact and tradeoffs for data freshness, reliability, and complexity.
Configure AssemblyAI authentication and regional endpoints for an integration. Keep project keys on trusted servers, design temporary streaming tokens for browser or mobile clients, and document configuration checks without exposing credentials or audio content.
Deploy AssemblyAI processing workers, temporary streaming token services, and authenticated callback receivers. Configure durable queues, duplicate handling, shutdown behavior, and rollback controls, then check the deployment with synthetic audio before broader use.
Create and organize tests for REST and GraphQL endpoints from API specifications. Check valid and invalid requests, authentication, response schemas, CRUD behavior, and edge cases, then produce a report mapping endpoint coverage.
Review whether an Attio integration is ready for production using code and operational evidence. Check authentication, permissions, retries, webhooks, monitoring, and rollback, then produce a GO or NO-GO decision with blockers and named approvers.
Prepare AssemblyAI diagnostic evidence for incident triage and support requests. Extract approved metadata such as status changes, timestamps, SDK versions, and error codes, while excluding credentials, signed URLs, audio, transcript text, prompts, and customer content.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)