BB wan-3-0-prime-reference-to-video
Wan 3.0 Prime Reference to Video generates video clips from reference images, reference videos and reference audio on RunComfy. Wan 3.0 Prime Reference to Video binds up to 10 reference images, 5 reference videos and 5 reference audio clips to a prompt that names them as Image 1, Video 1 and Audio 1, so a character, product or location stays consistent across a 2 to 30 second shot at 480p, 720p or 1080p with a synchronized audio track. Wan 3.0 Prime Reference to Video runs on the fast Wan 3.0 Prime tier (wan3.0-video-prime) and is billed per counted second, where reference videos add duration and reference images and audio do not. This skill documents the full Wan 3.0 Prime Reference to Video input schema, pricing, prompting patterns and the routing rules for Wan 3.0 Prime text-to-video, Wan 3.0 Prime image-to-video, Wan 2.7 and Seedance 2.0 Pro. Calls `runcomfy run wan-ai/wan-3.0-prime/reference-to-video` through the local RunComfy CLI. Triggers on "wan 3 prime reference to video", "wan 3.0 prime", "wan3 prime", "reference to video", "ref2v", "keep the same character across shots", "video from reference images", or any explicit ask to generate video from references with Wan 3.0 Prime.
Wan 3.0 Prime Reference to Video generates video clips from reference images, reference videos and reference audio on RunComfy. Wan 3.0 Prime Reference to…
As a process B 67/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Shorten the description to 1024 characters.
- 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
- error
description-longdescription is 1205 chars, limit 1024 - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "emoji" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "clawdis"
Process rating: all ten parameters 67/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 29 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3595 tokens
- 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
- low The response is described with custom markup (3 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1204: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Structure: 15 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (7 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 47.