BC cn-seo-optimizer
Chinese SEO compliance checker with API backend + content prediction calibration — 违禁词扫描+SEO合规检测+内容预测校准 (Chinese advertising law compliance + SEO optimizer + prediction calibration). Scan content for 广告法违禁词 via API, predict content performance (5 dimensions), and calibrate over time. Features: (1) API-powered banned word detection with 200+ word database, (2) Content prediction system: compliance risk, engagement potential, brand safety, SEO visibility, AI citation probability, (3) Calibration loop: predict → publish → review → calibrate → get more accurate, (4) Platform-specific SEO rules for 5 major Chinese platforms, (5) Safe replacement suggestions, (6) Executable scripts. Free tier: 20 checks/month. ONLY skill combining API backend + SEO compliance + prediction calibration. Use when: checking 违禁词, 广告法合规, content prediction, SEO compliance, 小红书优化, 抖音文案, 淘宝标题, Baidu SEO, 京东 listings, content calibration. Triggers: SEO tool, 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, content prediction, calibration, 预测校准, 内容预测, 合规预测, SEO API, compliance API, predict API.
As a process C 59/100 · 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: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1083 chars, limit 1024
Process rating: all ten parameters 59/100
- 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
- 30Running it twice. 10 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 107 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3944 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 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)
- +3Description length 1083: 120–800 characters recommended
- -240 emoji in the instructions: noise for the model
- -42 reference files, but SKILL.md never points to them: the model will not open them
- -32 of 4 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 33 headings
- +3Step-by-step instructions: 107 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 50.