AB talking-avatar-video
Create a talking avatar from one portrait and a short script or speech track. This AI presenter and digital human video workflow can prepare narration with a selected voice or use a supplied recording, then direct a stable talking-head clip with restrained expression, natural movement, clear delivery, and focused lip-sync review. Use it for AI spokesperson videos, product explainers, training, course lessons, announcements, onboarding, social talking-head content, and photo-to-talking-video messages, with narration-driven facial motion and a focused review of identity, clarity, lip sync, and motion stability.
Create a talking avatar from one portrait and a short script or speech track.
As a process B 73/100 · Nearly there — weak spots: running it twice, progress reporting
How to improve
- 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 73/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 6 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 19 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3391 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 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)
- -32 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 616: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 19 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (8 of 8)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.