Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add heygen-com/liveavatar-agent-skills --skill liveavatar-demogit clone --depth 1 https://github.com/heygen-com/liveavatar-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/heygen-com/liveavatar-agent-skills/liveavatar-demo)<a href="https://agentmods.dev/skills/heygen-com/liveavatar-agent-skills/liveavatar-demo"><img src="https://agentmods.dev/badge/skills/heygen-com/liveavatar-agent-skills/liveavatar-demo/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/heygen-com/liveavatar-agent-skills/liveavatar-demo"><img src="https://agentmods.dev/badge/skills/heygen-com/liveavatar-agent-skills/liveavatar-demo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00224 | $0.03498 |
| Opus 5 | $0.00112 | $0.01749 |
| Sonnet 5 | $0.00045 | $0.00700 |
| Haiku 4.5 | $0.00022 | $0.00350 |
Grade A, and why
liveavatar-demo scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LiveAvatar Demos
Four curated demos, each a real open-source repo. This skill does every mechanical step: clone, install, provision, configure, launch.
What this skill cannot do — say this up front
You cannot verify that the avatar talks. Every demo ends at a microphone and a human ear. Do not claim success you can't observe, and do not stall waiting for something you can't reach. Name these moments as you hit them:
| Moment | Why it's human-only |
|---|---|
| Supplying API keys | Cannot be fetched or guessed |
Demo 1: npm run setup prompts |
Interactive readline. See the reference — running it wrong orphans a context in the user's account |
| Demo 1: fill name + work email, click Chat with Wayne | The submit button is disabled until both fields are filled |
| Demos 2/3: grant browser mic permission, then speak | No mic, no conversation |
| Demo 4: click Start, allow mic, answer "ready" | The avatar waits for a spoken yes before doing anything |
| Confirming the avatar spoke and lip-synced | Audio + video, in a human's browser |
| Vercel login / deploy (demo 1, Full level only) | Interactive auth |
Everything else is yours. Do it without narrating each command.
Step 1: Get the LiveAvatar API key — before anything else
All four demos need it, and having it early removes most branching. Ask for it now, in your first message, alongside the catalog:
Grab an API key from https://app.liveavatar.com/developers and paste it here. I'll take it from there.
Do not proceed past Step 3 without it. You may clone and install while waiting, so the user is one paste away from a running demo — say that's what you're doing.
Never write a placeholder or fake value into an env file. Every setup script and entrypoint treats whatever is in the file as authoritative, and a bogus key produces a 401 that looks like an account problem.
Step 2: Pick the Demo
Show this table unless the user already named one.
| # | Demo | What it does | Stack | Extra keys needed |
|---|---|---|---|---|
| 1 | AI Sales Agent | Avatar qualifies leads, writes a summary to Notion + Slack on hangup | Next.js 15 / TypeScript, Node 22+ | none for a local run; Anthropic + a public URL for the full sales brain |
| 2 | LiveKit Agent (LiveAvatar-hosted room) | Your own LiveKit STT→LLM→TTS pipeline driving the avatar. LiveAvatar owns the room | Python 3.10+ / LiveKit Agents | LiveKit Cloud key + secret |
| 3 | BYO LiveKit Agent | Same pipeline, avatar joins a room in your LiveKit project. Production-shaped | Python 3.10+ / LiveKit Agents | LiveKit Cloud key + secret + URL, livekit-cli |
| 4 | GPT-Live × Hyperframes × LiveAvatar | Full-duplex speech-to-speech GPT-Live drives the avatar; its tool calls land as animated Hyperframes overlays. One repo, several branches with this exact architecture (language tutor, support agent, poker coach) — built to be one-shotted by an agent, then repurposed | Node 20.12+ / pnpm / TypeScript | OpenAI key that can reach GPT-Live |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed · +15 lines · +49 tokens per session 0edf3f0298b7
- 12d ago First seen · 162 lines · 175 tokens per session scan A 6b9c28cd80da
liveavatar-demo is a skill published in the GitHub repository heygen-com/liveavatar-agent-skills (9 stars, last pushed yesterday), licensed MIT. It adds 224 tokens to every session and 3,498 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…