BC cover-performance-preflight
Review an existing YouTube thumbnail, social media cover, article cover, or podcast cover design, then turn the findings into a practical thumbnail-optimization and cover-improvement plan. This AI thumbnail analyzer identifies the visual hook, focal hierarchy, title-to-image fit, text-safe contrast, mobile readability, and crop resilience, then produces targeted edit directions and two or three video cover improvement candidates ready to compare. It can optionally read the field your cover is entering: the titles and public counts of what already ranks for the same topic on YouTube, TikTok, Douyin, and REDnote; on YouTube, a competitor's actual thumbnail image; and your own YouTube channel's recent thumbnails. That turns competitor thumbnail analysis, a thumbnail benchmark, and a cover comparison into evidence sitting beside the review instead of one cover being judged alone. Surfaces with no public data — a WeChat article cover, a podcast cover, and others — simply skip that step.
Review an existing YouTube thumbnail, social media cover, article cover, or podcast cover design, then turn the findings into a practical…
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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: 15. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 57/100
- 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. 9 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 12 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2807 tokens
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 996: 120–800 characters recommended
- +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
- +4Structure: 7 headings
- +3Step-by-step instructions: 12 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (9 of 9)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.