Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Debug Voice · cursor | DecimalAI

codingby cursor

Debug Voice

cursor/debug-voice

Source cursor/plugins ↗License Not recorded

Use when the user runs /debug-voice, says voice mode has flaws, asks to see or capture what happened in a Grok realtime voice session, or a voice integration has no debug logging yet. Proposes a plan, then installs a dev-only log pipeline (client logger → local NDJSON) in the app's own language and conventions, then runs the fix loop: match the user's report to log signatures, fix one thing, re-test.

SkillScore86Maintained

Automatic

Coding pack

Last verified 10/10/2026

What it changes

Passed 19 of 22 test cases with the skill, and 9 of 22 without it.

Without skill41%

With skill86%

Checks it passed that the model alone missed

Ensures audio buffer byte alignment.
Truncates strings exceeding 400 characters.
Stores log files in the .voice-logs directory.

and 13 more in the full report

10 fixed9 passed either way3 still failing0 broke

Pass-rate lift: +45 pp
Tokens: +57%
Agent turns: 0%
Response time: -56%

Model gemini-3.6-flashMeasured 10/10/2026v119 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/cursor-debug-voice/SKILL.md https://app.decimal.ai/s/cursor-debug-voice/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add cursor-debug-voice, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/cursor-debug-voice/ and pins it in .decimal/skills.lock

decimalai skills add cursor-debug-voice

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/cursor-debug-voice/SKILL.md https://app.decimal.ai/s/cursor-debug-voice/SKILL.md

Raw file: /s/cursor-debug-voice/SKILL.md ↗ · machine-readable summary at /s/cursor-debug-voice.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 10

Prompt

In what directory and file format should the dev sink append incoming session logs, and how should session log filenames be formatted?

What was checked, without and with the skill
Checked	Without skill	With skill
Stores log files in the .voice-logs directory.	Missed	Passed
Formats session log filenames as 8-character lowercase hex strings with the .ndjson extension.	Missed	Passed

case-14 · gemini-3.6-flash · 10/10/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md187 linessingle file

Debug Voice

Make a voice session readable after the fact, then fix from evidence. The agent cannot hear the app; the log is its ears, the user is its judge. No audio, no tokens, never in prod.

Works for any stack. The pipeline is a small contract (below); implement it in whatever the app already uses.

Workflow

Map the app (read only).
Plan: write the change list, show it, stop. Nothing is edited until the user aligns.
Install the agreed pieces in the app's language, framework, and conventions.
Verify the sink, hand the app to the user.
Fix loop from the log.

1. Map

Find, and note the paths:

Voice client: where realtime events are received and sent, mic capture, audio playback, token fetch.
Server: framework, how routes are declared, where shared server code lives, how env is read, what "production" means here.
Conventions: language(s), module system, formatter, where scripts or tasks live (package.json, Makefile, pyproject, justfile), .gitignore.
Client kind: browser, mobile, desktop, CLI. A non-browser client still POSTs the same JSON; a single-process app can skip HTTP and append to the file directly.
Where audio deltas are handled. They must be counted, never logged.

2. Plan, then stop

Fill this in with real paths and the app's language, post it, and wait for a yes or a trimmed list. Do not edit files before that.

## Debug voice: plan

Add
- <path>: client logger (batch, redact, flush) in <language>
- <path>: dev-only sink `POST /api/voice/log` → `.voice-logs/<sessionId>.ndjson`
- <path> (optional): summary command `<cmd>`; otherwise read the NDJSON with jq

Modify
- <voice client file>: hook points start, token, mic, env, ws.*, client/server events,
  audio.in (2 s windows), audio.out.first, audio.out, play.stop, stop
- <token route>: append `server.token { ok, status, ms, upstream }` (never the token)

Track record

Benchmark

19 / 22

test cases passed, vs 9 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 9/15/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

cursor / plugins

grok-voice/skills/debug-voice/SKILL.md

View on GitHub ↗

Imported 9/15/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Debug Voice

Workflow

1. Map

2. Plan, then stop

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills