AC veo-3
Use to write great prompts for Google Veo (Veo 3.1) to generate or animate video for social media — the video-prompt-craft mini-skill, the video counterpart to nano-banana. Run when the user wants a Veo / AI video prompt, a short video clip for a post (b-roll, product-in-motion, hook visual, spokesperson/UGC clip, ad), to animate a still image into video, or a vertical Reel/TikTok/Short clip. Reads brand-profile for brand style. Veo's standout is native synchronized audio in one pass, plus image-to-video and native 9:16 vertical. Teaches the prompt anatomy, audio prompting, the image-to-video pipeline, and the 8-second constraint + extension/stitching. Honest: iterate cheap then finalize, disclose AI video (SynthID watermark), never generate real identifiable people or copyrighted IP. This is the prompt-craft layer — the API/connection and the generate -> upload to WoopSocial Media -> attach flow live in tools/integrations/veo.md; the consuming pack is reels-script's veo-prompt-pack.
Use to write great prompts for Google Veo (Veo 3.1) to generate or animate video for social media — the video-prompt-craft mini-skill, the video counterpart…
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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 62/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 31 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1479 tokens
- low 10 top-level sections: this looks like several domains in one skill
- medium 8 test cases, all positive: not one "should refuse" or "should ask first"
- 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 998: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +4Structure: 11 headings
- +3Step-by-step instructions: 31 items
- +4Reference files are cited in the instructions (4 of 4)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.