While testing a voice-to-structured-document workflow on an NVIDIA DGX Spark, the Hermes Agent consistently failed to tr...

While testing a voice-to-structured-document workflow on an NVIDIA DGX Spark, the Hermes Agent consistently failed to trigger the specific voice-memo skill, opting for the default memory tool instead. This post details how I implemented custom gateway hooks to force correct skill invocation and output validation. BackgroundThe setup involved a Telegram-based voice interface connected to a Hermes Agent (v0.20.6) running on a DGX Spark. I used a host-side whisper.cpp server with a ggml-large-v3-turbo-q5_0 model for STT (Speech-to-Text). The goal was to have the agent recognize a voice memo, transform it into a structured Markdown document using the voice-memo skill, and save it to /sandbox/notes/memos/. What happenedIn the first round of testing, transcription succeeded 5/5 times, but the voice-memo skill was triggered 0/5 times. In the second round, after changing the trigger word to 메모 ( What I triedChanging the skill trigger condition in the SKILL.md file to look for the word 메모 (spok...