AC synthesia
The Synthesia craft skill — produce avatar video (training, onboarding, explainers, localized series, faceless educational content) with the consent-first architecture and honest fit boundaries. Use when someone wants to make videos with Synthesia/AI avatars, create a personal avatar/digital twin, localize one video into many languages, build training/L&D video at scale, or asks whether an avatar should replace them on camera. Uses the HUMAN framework. Reads the content skill + brand-profile + voice-builder first. The agent scripts and plans (API where connected); the HUMAN approves every video; WoopSocial publishes. Spines: the fit test (avatars win at scale/localization/training, lose to a real face for trust-led content); consent-first likeness; the script is most of avatar quality — lock copy before generating. Never impersonate, fake endorsements, or skip AI-disclosure. Distinct from heygen, talking-head-and-piece-to-camera, ai-video/luma, ai-voiceover, and descript.
The Synthesia craft skill — produce avatar video (training, onboarding, explainers, localized series, faceless educational content) with the consent-first…
As a process C 54/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- 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: 6. 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 54/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 8 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 85Steps. 9 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1847 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low No test case covers injection arriving through data
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)
- +3Description length 986: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 9 headings
- +3Step-by-step instructions: 9 items
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.