debug
Stream real-time debug events from the Vocal Bridge voice agent. Shows transcriptions, agent responses, tool calls, and errors.
Works with
--- name: debug description: Stream real-time debug events from the Vocal Bridge voice agent. Shows transcriptions, agent responses, tool calls, and errors. license: Apache-2.0 --- Stream real-time debug events from the voice agent. First ensure CLI is installed: ```bash pip install --upgrade vocal-bridge ``` Then run: ```bash vb debug $ARGUMENTS ``` This command runs continuously until interrupted (Ctrl+C). ## Options - `--poll` - Use HTTP polling instead of WebSocket - `-i 0.5` - Poll interval in seconds (default 0.5, only used with --poll) ## Event Types The debug stream shows: - **USER** - User transcriptions (what the caller said) - **AGENT** - Agent responses (what the agent said) - **TOOL** - Tool calls made by the agent - **RESULT** - Tool call results - **BG QUERY** - Background LLM queries (concierge modes) - **BG RESULT** - Background query results - **ERROR** - Errors encountered - **SESSION** - Session start/end events - **STATE** - State changes - **HOLD** - Hold started/ended ## Prerequisites Debug mode must be enabled in the agent's Capabilities settings at https://vocalbridgeai.com To enable: 1. Go to your agent in the Vocal Bridge dashboard 2. Click 'Edit' 3. Enable 'Debug Mode' in the Capabilities section 4. Save changes
More Debugging skills
diagnosing-bugs
mattpocock/skills
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
explore-code
lllllllama/rigorpilot-skills
Rigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated branch or worktree to transplant modules, adapt a backbone, add LoRA or adapter layers, replace a head, or stitch together meaningful low-risk migration ideas with rollback-aware records in `explore_outputs/`. Do not use for end-to-end exploration orchestration on top of `current_research`, trusted baseline reproduction, conservative debugging, environment setup, verified contribution claims, or default repository analysis.
safe-debug
lllllllama/rigorpilot-skills
Rigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training failure and wants conservative diagnosis before any patching, with debug fixes clearly separated from research contributions. Do not use for broad refactoring, speculative adaptation, automatic exploratory patching, or general repository familiarization.

