SKILLEMALL.ai

AB unattended-live-avatar

Turn one shop portrait and short welcome, product, FAQ, and close scripts into talking-avatar clips a store can loop overnight. This unattended live avatar and night-shift avatar studio can clone or pick a voice, then produce a talking avatar livestream set for welcome, product, FAQ, and close so an unattended livestream or digital human livestream can keep a shop loop presenter on camera. Use it for overnight digital human clips, live room avatar loops, and a night-shift talking-head that keeps the room open.

ClawHub Agent Skills author: beatra-ai v0.1.2 MIT-0 14 files body ≈ 2 498 tokens Open the sourceclawhub.ai analyzed 3 d ago

Turn one shop portrait and short welcome, product, FAQ, and close scripts into talking-avatar clips a store can loop overnight.

As a process B 68/100 · Nearly there — weak spots: result and completion, progress reporting

GeneratorCustomer supportInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
A
94/100
safety, quality, tests
Safety 60%
100
Quality 40%
85
Run on models
none yet
Process rating
B
68/100
Nearly there
Result and completion w 14
0
Progress reporting w 2
0
When it triggers w 12
50
the three weakest of ten parameters · all ten

How to improve

    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 · 0

    ✓ No critical or high findings

    Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 68/100

    • 0Result and completion. Does not say what the result is
    • 0Progress reporting. Says nothing while it works
    • 50When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 18 steps
    • 100Failures and branches. 3 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2498 tokens
    • 100Running it twice. Mutating operations check current state
    • low The skill ranks results itself: that belongs to the system behind the tool, not the model

    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
    • -32 of 3 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 515: enough signal without eating the budget
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 18 items
    • +4Has examples (2 code blocks)
    • +4Reference files are cited in the instructions (8 of 8)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.

    External checks

    ClawHub: suspicious
    The avatar workflow is mostly disclosed, but it needs review because it silently self-updates installed code and requests broader Beatra account permissions than the workflow needs.
    LLM: suspicious (high) · 6 Sept 2026