BC seo-compliance-checker
SEO compliance checker with real-time API backend for Chinese content — 违禁词扫描+SEO合规检测+安全替换建议 (Advertising law compliance + SEO optimizer with API-powered banned word detection). Scan content for 广告法违禁词 via API, check keyword density, optimize titles for Baidu/小红书/抖音/淘宝/京东. Features: (1) API-powered banned word detection with 200+ word database covering 绝对化用语/医疗效果承诺/虚假宣传/金融承诺/诱导消费, (2) Platform-specific SEO rules for 5 major Chinese platforms, (3) Safe replacement suggestions for every banned word, (4) Keyword density analysis with optimal ranges, (5) Two executable scripts: check.sh for scanning, suggestions.sh for alternatives. Free tier: 20 checks/month. Use when: writing 小红书 posts, checking 违禁词, optimizing 淘宝 titles, creating 抖音 captions, Baidu SEO, 京东 product listings, 广告法合规, keyword density check, Chinese content compliance, advertising law compliance, content compliance checker, banned words scanner, SEO compliance, Chinese SEO, advertising law API. Triggers: SEO compliance, Chinese SEO, 违禁词检查, 小红书优化, 百度排名, 淘宝标题优化, 抖音文案, 广告法合规, keyword density Chinese, Chinese content compliance, banned words scanner, advertising law compliance, content compliance checker, 中国广告法, 极限词检查, 绝对化用语, 2026 SEO, advertising law API, compliance API, SEO checker, compliance checker.
As a process C 62/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches
How to improve
- Shorten the description to 1024 characters.
- 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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1281 chars, limit 1024
Process rating: all ten parameters 62/100
- 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
- 20When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 115 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2941 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)
- +3Description length 1281: 120–800 characters recommended
- -230 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +4Structure: 27 headings
- +3Step-by-step instructions: 115 items
- +3Output format is stated explicitly
- +4Has examples (6 code blocks)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.