orinachum/test
realtime-api/.agent/skills/test/SKILL.md
Run TTS round-trip tests — pure-logic unit tests and optional integration tests against live TTS/STT services.
$ install --global
skillsauthnpx skillsauth add orinachum/autonomous-intelligence testInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 10, 2026, 9:10 AM6.6s1 file scanned
SKILL.md
- name:
- test
- description:
- Run TTS round-trip tests — pure-logic unit tests and optional integration tests against live TTS/STT services.
Test Realtime-API
Run unit tests and integration tests for the TTS pipeline.
When to use
- After deploying new code
- When the user says "test", "run tests", "verify", "check"
- To validate TTS chunking and sentence splitting logic
Instructions
Quick — pure-logic tests only (no network, instant):
cd /home/spark/git/autonomous-intelligence/realtime-api && bash scripts/test_tts.sh --logic-only
Full — includes TTS/STT round-trip (requires running containers):
cd /home/spark/git/autonomous-intelligence/realtime-api && bash scripts/test_tts.sh
What the tests cover
Pure-logic tests (always run)
- Dash splitting: em-dash-heavy text > 200 chars splits correctly in loose mode
- TTS chunking: 1000+ char comma-heavy text splits into chunks <= 800 chars
- Short text passthrough: text under 800 chars is not split
Integration tests (require TTS + STT containers)
- Whole-mode TTS: full text → TTS → resample → STT round-trip
- Sentence-mode TTS: split → per-sentence TTS → concatenate → STT round-trip
- Duration comparison: whole vs sentence mode within tolerance
After testing
Speak the result:
/home/spark/git/autonomous-intelligence/realtime-api/scripts/speak.sh "All tests passed."
Related Skills
orinachum/speak
development
VerifiedTrustedCommunity
Speak text aloud using the Magpie TTS container in the realtime-api Docker stack. Zero external dependencies — just curl + aplay.
223SKILL.mdUpdated Apr 10, 2026
orinachum/deploy
development
VerifiedTrustedCommunity
Build and deploy the realtime-api Docker container with full verification that deployed code matches local source.
223SKILL.mdUpdated Apr 10, 2026
orinachum/coding
tools
VerifiedTrustedCommunity
Enhanced coding assistance
223SKILL.mdUpdated Apr 10, 2026
orinachum/memory
development
VerifiedTrustedCommunity
Unified memory management for notes, knowledge graph, RAG search, and file analysis. Use when working with: (1) Core memory — protected identity, projects, relationships, and system facts that should never be forgotten, (2) Working notes — per-session ephemeral notes organized by section, (3) MongoDB RAG — vector-search-enabled notes with importance scoring, decay, deduplication, and archival, (4) Neo4j knowledge graph — entities, relationships, merge duplicates, reinforce mentions, Cypher queries, (5) File analysis — deep file reading that extracts knowledge into all memory layers, (6) Service initialization — health-check, start/stop MongoDB, Neo4j, TEI embeddings via docker-compose with partial setup support.
223SKILL.mdUpdated Apr 10, 2026