SKILLEMALL.ai
GitHub ↗ RU Sign in

AF atlas_avatar

Create realtime **passthrough** AI avatar sessions (LiveKit WebRTC — you bring STT/LLM/TTS and publish audio), view-only viewer tokens for multi-viewer watch, and offline lip-sync avatar videos using the Atlas API by North Model Labs. Post offline MP4 renders to Discord (webhook). Use when the user asks for Atlas avatar, talking head, realtime avatar, face animation, video from audio+image, lip sync, BYOB TTS + /v1/generate, watch-only audience, Discord delivery of renders, or GPU avatar rendering.

ClawHub Agent Skills author: infinit3e v1.0.9 MIT-0 7 files · 1 script body ≈ 4 815 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 44/100 · Will not run — References files that are not bundled: scripts/bridges/

GeneratorDiscordMedia and videoAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
91/100
safety, quality, tests
Safety 60%
99
Quality 40%
78
Run on models
none yet
Process rating
F
44/100
Will not run
References files that are not bundled: scripts/bridges/
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 1

✓ No critical or high findings

Medium and low: 1
  • low Exfiltration read-dotenv SKILL.md:43
    Reads a .env file
    cp .env.example .env.local   # set ATLAS_API_KEY (+ optional LLM / ElevenLabs — see example file)

Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning missing-ref reference to a missing file: scripts/bridges/

Process rating: all ten parameters 44/100

Will not run. References files that are not bundled: scripts/bridges/
  • 0Tools and files. 1 referenced file(s) missing: scripts/bridges/
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 11 mutating operations with no state check
  • 40Consistency. Frontmatter name (atlas_avatar) differs from the folder (atlas-avatar)
  • 70When it triggers. States when to use, but not when not to
  • 70Execution cost. Instruction body is 4815 tokens
  • 100Steps. 15 steps
  • 100Failures and branches. 4 branches, has a failure section
  • 100Progress reporting. Reports progress
  • low 11 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (3 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 503: enough signal without eating the budget
  • +4Structure: 28 headings
  • +3Step-by-step instructions: 15 items
  • +4Has examples (20 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)
  • +3All 3 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.

External checks

ClawHub: clean
This skill is a disclosed Atlas avatar helper, but it handles API keys and sends media through external services, so users should install it only with that data flow in mind.
LLM: benign (medium) · VirusTotal: · 29 May 2026