Agent Native

architect-review-live-calls

This skill reviews an agent's recent finished conversations from the ElevenLabs API to surface problems in production.

by ElevenLabsOfficial publisherNot reviewed

Identity proven by GitHub's verified organisation badge (elevenlabs)

Agents
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, claude.ai and API
License
No license stated
Pin
c7eef3cpinned Oct 9, 2026
Context cost
about 3,200 tokenswhen the skill loads
GitHub stars
1on elevenlabs/plugin
Scripts
None found

What it does

“Review an agent's recent finished conversations to find what is actually going wrong in production, then route each finding to a fix. Use when the user says 'we just launched this agent, how is it doing', 'review the last 3 days of calls', 'check how the agent is performing', 'monitor agent {id}', 'what are callers running into', 'why are calls failing', or asks for a post-launch health check or a weekly call review.”
The author's description, from SKILL.md

Generated summary from the skill's own text

This skill reviews an agent's recent finished conversations from the ElevenLabs API to surface problems in production. It fetches call metadata and transcripts, aggregates key metrics like termination reasons and tool usage, clusters findings by root cause, then routes each cluster to the appropriate fix skill.

When to use it

  • Agent recently launched and needs a health check
  • Reviewing last N days of calls for performance issues
  • Checking what specific problems callers encountered
  • Comparing current call quality against a baseline

When not to

  • Monitoring live in-flight conversations in real time
  • Agent has zero calls in the window
  • Editing agent config or fixing problems directly

Install

No license stated: install from the publisher's repository, and ask the author before you reuse or share it.

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add elevenlabs/plugin --skill architect-review-live-calls

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install elevenlabs/plugin architect-review-live-calls@c7eef3cbcf1ff3ef12066a4e8ea964749d8e94be

Installs the commit we checked (c7eef3c).

Copy by hand

Download the folder at c7eef3c and put it in .claude/skills/architect-review-live-calls for Claude Code and in .agents/skills/architect-review-live-calls for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at c7eef3c

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "architect-review-live-calls" by ElevenLabs.

Source, pinned to commit c7eef3cbcf1ff3ef12066a4e8ea964749d8e94be:
https://github.com/elevenlabs/plugin/tree/c7eef3cbcf1ff3ef12066a4e8ea964749d8e94be/architect/skills/architect-review-live-calls

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/architect-review-live-calls/ for Claude Code and .agents/skills/architect-review-live-calls/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Its license is restricted or not stated. Show me the license terms from the repository before you copy anything.

Listing and checks: https://www.agentnative.dev/skills/elevenlabs/architect-review-live-calls

SKILL.md at the pin

The license of this skill does not let us show its files here.

View SKILL.md on GitHub at c7eef3c

Files

1 file, 13 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at c7eef3c
All 44 skills from ElevenLabs

More from ElevenLabs

  • agents

    Build voice AI agents with natural conversation capabilities using ElevenLabs platform.

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 6.4K tokens · pinned 6 days ago

  • dubbing

    This skill dubs audio and video into other languages using ElevenLabs' Dubbing API, preserving original speakers' voices.

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 3.1K tokens · pinned 6 days ago

  • music

    This skill generates music from text prompts using the ElevenLabs Music API, supporting instrumental tracks, songs with lyrics, and fine-grained control…

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 3.3K tokens · pinned 6 days ago

  • setup-api-key

    This skill guides users through obtaining and configuring an ElevenLabs API key for text-to-speech integrations.

    Claude Code, Codex, Cursor +4 · about 840 tokens · pinned 6 days ago

  • sound-effects

    This skill generates sound effects from text descriptions using ElevenLabs API, supporting various audio formats, custom durations up to 30 seconds, looping…

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 830 tokens · pinned 6 days ago

  • speech-engine

    This skill integrates ElevenLabs Speech Engine to add real-time voice conversations to custom agent runtimes.

    Claude Code, Codex, Cursor +4 · about 2.4K tokens · pinned 6 days ago

All Observability skills

Related in Observability

  • debugging-executions

    Debug workflow execution failures by inspecting failed nodes, re-running executions, and comparing expected versus actual values.

    by n8nOfficial publisher

    Claude Code, Codex, Cursor +3 · about 2.5K tokens · pinned 6 days ago

  • instance-awareness

    This skill teaches the agent to resolve ambiguous requests by reading the instance's activity log and workflow history instead of asking the user to clarify.

    by n8nOfficial publisher

    Claude Code, Codex, Cursor +3 · about 1.3K tokens · pinned 6 days ago

  • creating-replay-vision-scanners

    Guides agents through creating Replay Vision scanners, LLM probes that watch session recordings on a schedule and log findings as observations.

    by PostHogOfficial publisher

    Claude Code, Codex, Cursor +4 · about 3.3K tokens · pinned 6 days ago

  • exploring-replay-vision-observations

    This skill guides agents through reading observations from Replay Vision scanners, understanding their findings across session recordings, and taking action…

    by PostHogOfficial publisher

    Claude Code, Codex, Cursor +4 · about 3.3K tokens · pinned 6 days ago

  • exploring-scouts

    Explore and understand PostHog Signals scouts through read-only tools, examining fleet configuration, recent runs, performance metrics, and durable team…

    by PostHogOfficial publisher

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 11K tokens · pinned 6 days ago

  • investigating-replay

    Gathers session recording metadata, user profile, event timeline, and linked error issues in parallel to give a complete investigation when a user provides a…

    by PostHogOfficial publisher

    Claude Code, Codex, Cursor +4 · about 2.3K tokens · pinned 6 days ago

Open roles at ElevenLabs

5 of 26 open roles on the jobs board

See all 26 roles at ElevenLabs on the jobs board

The skills listed here are third-party software, collected from public GitHub repositories as a catalog of recent skills and provided as is. Agent Native does not write or control them and is not responsible for any harm, loss or damage caused by installing or using them. Labels and checks describe what we saw at one commit and are not a guarantee. Read a skill's files before you run it. Terms of use