BC geo-optimization-tool
GEO tool with API-powered engine database for generative engine optimization (生成式引擎优化工具+AI搜索引擎数据库API). Track AI search visibility and AI citation tracking across 8 engines: DeepSeek, Kimi, Doubao, Tongyi + ChatGPT, Perplexity, Gemini, Claude. Features: (1) API-powered GEO engine database with market share data, (2) Content audit framework for AI citation optimization, (3) Executable geo-engines.sh script for CLI access, (4) ONLY skill covering Chinese AI engines with API backend. GEO market $10.1B→$73B, 47% brands lack GEO strategy. Use when: GEO audit, GEO monitoring, AI search optimization tool, generative engine optimization tool, checking brand visibility in AI search, optimizing for AI citations, AI search visibility tracking, 品牌AI搜索可见度, AI引用优化, GEO监测, 生成式搜索优化, AI搜索排名, DeepSeek优化, Kimi优化. Triggers: GEO tool, GEO audit, generative engine optimization, AI search visibility, brand monitoring AI, AI citation tracking, Perplexity optimization, ChatGPT visibility, AI SEO, DeepSeek, Kimi, Doubao, 2026 GEO, 生成式引擎优化工具, AI搜索优化, 品牌AI可见度, AI引用分析, 中国AI搜索, DeepSeek优化, Kimi优化, 豆包优化, 通义优化, GEO监测工具, GEO API, engine database API.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1134 chars, limit 1024
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 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. 1 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 41 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1780 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1134: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 16 headings
- +3Step-by-step instructions: 41 items
- +4Has examples (4 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.