AC thumbnail-design
Design YouTube video thumbnails that earn the click — mobile-legible, one focal point, honest. Use when someone wants to design a YouTube thumbnail, improve CTR, brief a thumbnail, choose thumbnail text, or plan thumbnail A/B testing. Designs and briefs high-CTR thumbnails and writes the A/B test plan: a thumbnail is a promise, not a poster, designed as a unit with the title and legible on mobile. Uses the CLICK framework. Reads brand-profile + the video/title first. A HUMAN or an image/design tool (nano-banana/ideogram/Canva/designer) creates the final raster; the YouTube custom thumbnail is uploaded NATIVELY in Studio (WoopSocial has no thumbnail field) and Test & Compare is native; TikTok/IG-Reel covers use WoopSocial's cover field via those format skills. No clickbait, no unconsented real-person/deepfake faces, CTR never fabricated. Distinct from youtube-publishing-and-metadata (the metadata) and nano-banana/ideogram (which generate the raster this briefs).
Design YouTube video thumbnails that earn the click — mobile-legible, one focal point, honest.
As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 58/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 8 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 100Tools and files. No external tools needed
- 100Steps. 10 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1386 tokens
- 100Progress reporting. Reports progress
- 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 975: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 9 headings
- +3Step-by-step instructions: 10 items
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.