AC anti-ai-foolish
Pre-publish AI-flavor gatekeeper for Chinese long-form articles (公众号/自媒体评论). Detects and removes AI-writing tells using 1,108 rules that were A/B-validated on 52 real Tencent Zhuque detector-labeled fragments. Use whenever the user asks to 去AI味, 去AI, 降AI率, 终检/检查一篇文章 before publishing, or mentions an article was flagged or rejected by WeChat (微信打回) or Zhuque (朱雀) as AI-generated — even if they only say "这篇文章帮我看看".
Pre-publish AI-flavor gatekeeper for Chinese long-form articles (公众号/自媒体评论).
As a process C 61/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, running it twice
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: 26. 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 61/100
- 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
- 30Running it twice. 8 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 27 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1231 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
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 416: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 27 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (3 of 4)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 98.