AC covercraft-skill
Use this skill when the user wants to analyze, design, optimize, recreate-in-spirit, or batch-produce thumbnails/covers for Bilibili, YouTube, Xiaohongshu, Douyin, WeChat Channels, public-account articles, courses, AI tools, knowledge IP, or product content. The skill produces strategy-first cover briefs, no-text image-generation prompts, platform-specific layout specs, portrait-consistent asset directions, A/B variants, technical QC, and iteration plans. It learns visual logic from references without copying protected designs.
Use this skill when the user wants to analyze, design, optimize, recreate-in-spirit, or batch-produce thumbnails/covers for Bilibili, YouTube, Xiaohongshu…
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 25. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "zh_name" - note
frontmatter-keyunknown frontmatter key "language"
Process rating: all ten parameters 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 337 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3301 tokens
- 100Running it twice. No mutating operations
- low 18 top-level sections: this looks like several domains in one skill
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 533: enough signal without eating the budget
- +4Structure: 77 headings
- +3Step-by-step instructions: 337 items
- +4Has examples (6 code blocks)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.