AB WeChat Article Summarize
Read one or more WeChat public account article links from mp.weixin.qq.com, extract cleaned full text and optional image links, summarize each article in Chinese with summarize, and generate a structured markdown file saved to a user-chosen directory. Use when the user shares WeChat article URLs and wants single-article notes, multi-article daily reports, article summaries, image extraction, or a structured markdown digest. Before processing, first confirm summarize is configured and working, ask whether to include images, and ask where to save the final file.
As a process B 71/100 · Nearly there — weak spots: consistency, 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: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens)
Process rating: all ten parameters 71/100
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (WeChat Article Summarize) differs from the folder (wechat-article-summarize)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 56 steps, 1 vague phrases
- 100Failures and branches. 4 branches, has a failure section
- 100Execution cost. Instruction body is 1226 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)
- +1No license
- +2Single-language instructions
- +3Description length 566: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 56 items
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
- +3All 7 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.