AB oral-seeding-video-maker
Make a spoken recommendation video from nothing but a topic. This talking-style seeding video maker and short video script generator picks the script pattern that fits your product or subject, writes the hook, the body beats, and the closing ask with the on-screen action and the spoken line written separately, then produces ready-to-edit still beat frames, a narration track in a voice you choose, an optional music bed, and one vertical clip animated from the opening frame with the full narration. Use it for product seeding posts, creator recommendation videos, review-style shorts, service explainers, and account-building content for Douyin, WeChat Channels, Xiaohongshu, TikTok, Reels, and Shorts — with no footage, no camera, and nothing to upload.
Make a spoken recommendation video from nothing but a topic.
As a process B 66/100 · Nearly there — weak spots: result and completion, 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: 16. 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 66/100
- 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
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 19 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2969 tokens
- 100Running it twice. Mutating operations check current state
- low 10 top-level sections: this looks like several domains in one skill
- 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 757: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 19 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (10 of 10)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.