AF talking-circle
Create animated talking-circle videos (Telegram-style round video messages) from avatar frame images and audio. Supports audio-to-video and text-to-video via ElevenLabs or SaluteSpeech (Sber) TTS. Use when the user wants to generate lip-synced circular avatar animations, talking circles, or round video messages.
As a process F 62/100 · Will not run — References files that are not bundled: examples/sbercat/, examples/sbercat/reference.png, examples/sbercat/neutral.png
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: examples/sbercat/ - warning
missing-refreference to a missing file: examples/sbercat/reference.png - warning
missing-refreference to a missing file: examples/sbercat/neutral.png - warning
missing-refreference to a missing file: examples/sbercat/slight.png - warning
missing-refreference to a missing file: examples/sbercat/wide.png - warning
missing-refreference to a missing file: examples/sbercat/blink.png - warning
missing-refreference to a missing file: examples/sbercat/example.mp4
Process rating: all ten parameters 62/100
- 0Tools and files. 7 referenced file(s) missing: examples/sbercat/, examples/sbercat/reference.png, examples/sbercat/neutral.png
- 0Result and completion. Does not say what the result is
- 30Running it twice. 11 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 47 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 6 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3103 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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
- +1No license
- +2Single-language instructions
- +3Description length 313: enough signal without eating the budget
- +4Structure: 30 headings
- +3Step-by-step instructions: 47 items
- +4Has examples (7 code blocks)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.