SKILLEMALL.ai

BF avatar-runtime

Embeds and controls a virtual avatar using the avatar-runtime npm package. Provides Live2D rendering, VRM 3D, vector fallback, and control-driven expression/body/scene animation via a provider-agnostic session bridge. Use when the user asks for a virtual avatar, face-control animation, Live2D character, avatar widget embedding, or when starting/stopping an avatar session.

ClawHub Agent Skills author: neil v0.2.1 MIT-0 3 files body ≈ 2 905 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process F 56/100 · Will not run — References files that are not bundled: scripts/ensure-default-vrm-sample.sh, scripts/ensure-default-live2d-sample.sh, assets/vrm/slot/default.vrm

GeneratorInfrastructureAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
87/100
safety, quality, tests
Safety 60%
95
Quality 40%
74
Run on models
none yet
Process rating
F
56/100
Will not run
References files that are not bundled: scripts/ensure-default-vrm-sample.sh, scripts/ensure-default-live2d-sample.sh, assets/vrm/slot/default.vrm
Tools and files w 18
0
Result and completion w 14
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

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
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash(curl:*)
    allowed-tools: Bash(node:*) Bash(curl:*) Bash(npm:*) Bash(bash:*)

Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: scripts/ensure-default-vrm-sample.sh
  • warning missing-ref reference to a missing file: scripts/ensure-default-live2d-sample.sh
  • warning missing-ref reference to a missing file: assets/vrm/slot/default.vrm
  • warning missing-ref reference to a missing file: assets/live2d/slot/
  • note frontmatter-key unknown frontmatter key "env-vars"

Process rating: all ten parameters 56/100

Will not run. References files that are not bundled: scripts/ensure-default-vrm-sample.sh, scripts/ensure-default-live2d-sample.sh, assets/vrm/slot/default.vrm
  • 0Tools and files. 4 referenced file(s) missing: scripts/ensure-default-vrm-sample.sh, scripts/ensure-default-live2d-sample.sh, assets/vrm/slot/default.vrm
  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 2 mutating operations with no state check
  • 70When it triggers. States when to use, but not when not to
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 9 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2905 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 15 top-level sections: this looks like several domains in one skill

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
  • +2Single-language instructions
  • +3Description length 374: enough signal without eating the budget
  • +4Structure: 18 headings
  • +3Step-by-step instructions: 9 items
  • +4Has examples (16 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.

External checks

ClawHub: clean
This skill is a transparent avatar-runtime wrapper, with expected risks from running npm code and optional provider API keys.
LLM: benign (medium) · VirusTotal: · 29 May 2026