AB video-gen
Generate a video from a story-telling narration script plus the author's photos, using Seedance 2.0 image-to-video via OpenRouter's asynchronous video API: pre-render gates (face-scan, narrative order, risk-POC), then per-clip submit -> poll -> download, then ffmpeg assembly. Multi-clip projects default to silent clips plus one continuous soundtrack (synthesized or royalty-free/PD); subtitle voiceover is the fallback (no OpenRouter TTS). Verified working 2026-08-15 (POC: 4s 480p clip, $0.28, ~3 min). Use when the user asks to render a narration script into a video, generate a 视频, or run the death-in-Mexico project's video pipeline. Related terms: Seedance, 视频生成, OpenRouter, image-to-video.
As a process B 74/100 · 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: 2. 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 74/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4127 tokens
- 100Steps. 59 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (11 tags): a typed call is more reliable
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)
- +1No license
- +2Single-language instructions
- +3Description length 698: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 59 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.