Agent skills for OpenAI Agents SDK

Configure Speak local development with mocked tutors and audio testing.

Configure Speak across dev, staging, and production with separate API

Monitor Speak API health, assessment latency, session metrics, and pronunciation

Production readiness checklist for Speak language learning integrations:

Production architecture for Speak language learning apps: client, API

Production patterns for Speak language learning API: conversation sessions,

Security best practices for Speak API keys, audio data privacy, student

Upgrade Speak SDK versions, migrate between language learning platforms,

Speaking ops: invites, keynotes, panels, Gmail/calendar, conferences.

Right-size and write the spec before building any change.

Use when creating, reviewing, or updating SPEC.md files, running /specout, or entering the ADF SPEC gate.

Use ONLY when the user explicitly invokes spec-brainstorm by name.

How a project's agent-facing documentation is run so it stays true: one job per doc, facts flowing DECISIONS → SPECS → IMPL with the copy…

Use when an agent will work for hours or days across many files and multiple vertical slices.

Use ONLY when the user explicitly invokes spec-implement by name.

Manage spec registry and generate snapshots.

Review the quality of a Spec Kit preset or extension (the folder containing preset.yml or extension.yml, with commands/*.md…

Reverse-engineering specialist that extracts specifications from existing codebases.

Use after saving a non-trivial plan or decision RFC when a fail-closed feasibility, completeness, and alignment review must block execution.

Verifies code implements exactly what documentation specifies for blockchain audits.

Turn Notion specs into implementation plans, tasks, and progress tracking; use when implementing PRDs/feature specs and creating Notion…