agentleFS
Sign inStart free
iansteitz1-engiansteitz1-eng/aria-skills/call-scrub/SKILL.md

call-scrub

Skill0 starsChanged 2 months agoApache-2.0View on GitHub

Pull and analyze your ElevenLabs Conversational-AI voice calls — list recent conversations, or scrub one transcript to surface every tool the agent called, the result it got, errors, and timing. The fast way to debug "why did that call misbehave" without replaying audio. BYOK (your own ElevenLabs API key); read-only; stdlib only. Use when the user says "scrub that call", "what happened on the call", "pull the call transcript", "debug the voice call", "what tools fired".

  • Reads credentials

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When a Conversational-AI call goes sideways, the audio doesn't tell you *which tool returned an error* or *where it timed out*.

    line 19
  2. Very specific:

    No API key → clear FATAL + exit 2.

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

call-scrub

Debug a voice call by reading what actually happened — tool calls, results, errors — not by re-listening.

export ELEVENLABS_API_KEY=...                          # BYOK (your key)
python3 call_scrub.py                                  # list recent conversations
python3 call_scrub.py --agent-id agent_xxx --limit 20  # filter to one agent
python3 call_scrub.py --conversation-id conv_xxx       # scrub one call's tool activity

Why

When a Conversational-AI call goes sideways, the audio doesn't tell you which tool returned an error or where it timed out. This reads the transcript via the EL API and lays out every CALL and its -> result, flagging anything that looks like an error/fail/timeout (⚠). We built it debugging our own voice stack; it's the first thing to reach for after a bad call.

Behavior

  • Default / --list: recent conversations (started, id, msgs, duration, status).
  • --conversation-id: the full tool-call/result trail + an error count.
  • No API key → clear FATAL + exit 2. Read-only; nothing is written.

Requires

  • An ElevenLabs API key (env ELEVENLABS_API_KEY or --api-key). No Python packages.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free