Public Agent Skills for integrating, adapting, and debugging Dictum SDK.
mkdir -p ~/.codex/skills
curl -L https://dictum-skills.pages.dev/downloads/dictum-skills-codex.tar.gz | tar -xz -C ~/.codex/skillsImplement or review Dictum SDK custom adapters. Use when Codex needs to build insertion adapters for framework-owned text state, native/mobile audio capture adapters that stream validated WAV chunks with abort-aware cleanup, or platform event adapters that bridge sanitized public Dictum events to non-browser hosts.
Diagnose Dictum SDK integration failures from reusable-client commands, public events, states, errors, result shape, identity configuration, WAV capture, and WebSocket-to-POST recovery. Use when Codex needs to debug microphone denial, no speech, empty audio, compatibility, limits, fallback, explicit retry, quota/identity errors, or incorrect host UI state.
Add, review, or update browser and web-app integrations with the headless Dictum SDK for speech-to-text. Use when Codex needs to wire createClient, check browser compatibility, choose DOM versus custom targets, connect host-owned controls, handle public events/results/errors, or enforce Dictum SDK identity, transport, and privacy boundaries.
Design, implement, or review polished Dictum voice UI surfaces for product-native speech-to-text. Use when Codex needs to define component anatomy, visual hierarchy, responsive behavior, accessibility, motion, stateful microphone controls, transcription feedback, insertion affordances, or UX copy around the public Dictum SDK contract.
Published from commit 3517e634a043 at 2026-07-14T18:10:59.999Z.