AB wechat-article-visual-story
Write the WeChat article and make its pictures in one pass. Give a topic, what you are promoting, and who it is for — this WeChat Official Account article generator returns title candidates written for the feed, the digest line, a full article body structured for how people actually read on a phone, then renders the 2.35:1 cover and a set of in-body images that hold one look from top to bottom. Use it for WeChat Official Account posts, brand and product articles, promotional long-form, founder and expert columns, case studies, content marketing programmes, and any long-form post where the writing and the pictures have to be produced together rather than handed between two people.
Write the WeChat article and make its pictures in one pass.
As a process B 66/100 · Nearly there — weak spots: result and completion, progress reporting
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: 16. 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 66/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 16 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2306 tokens
- 100Running it twice. Mutating operations check current state
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
- -32 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 688: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (10 of 10)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.