BB patent-gap-supply-chain
Competitive intelligence workflow that infers supply-chain relationships from patent gaps — with trade secret assessment, competitive triangulation, negative verification, patent quality scoring, evidence freshness tracking, reverse workflow (supplier→client), and financial cross-validation. 通过"专利缺口"反推产业链关系的竞争情报工作流，集商业秘密评估、竞对三角验证、 负向验证、专利质量评分、证据时效追踪、反向工作流（供应商→客户）、财务数据交叉验证于一体。 Use when researching tech/hardware/manufacturing/pharma stocks, analyzing industry supply chains, identifying suppliers or customers, investigating patent gaps, or inferring supply-chain relationships from patent ownership. Supports both forward (patent gap → supplier) and reverse (technology owner → downstream clients) analysis directions. 触发场景：科技股研究、行业分析、产业链推断、 供应商识别、客户挖掘、专利缺口分析、专利归属查询、技术依赖分析、上下游推断 / Triggers: patent gap analysis, supply chain inference, supplier identification, customer identification, technology dependency, competitive intelligence, tech stock research, industry analysis, trade secret assessment, negative verification, patent quality, financial cross-validation, reverse supply-chain analysis. The skill starts from a patent gap (or known technology owner), evaluates trade secret likelihood, activates five verification leads with competitive triangulation, runs negative verification to rule out false positives, scores patent quality, tracks evidence freshness, then cross-validates against financial disclosures, outputting a confidence-scored supply-chain inference report.
Competitive intelligence workflow that infers supply-chain relationships from patent gaps — with trade secret assessment, competitive triangulation, negative…
As a process B 70/100 · Nearly there — weak spots: result and completion, progress reporting
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: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1486 chars, limit 1024 - note
frontmatter-keyunknown frontmatter key "agent_created" - note
frontmatter-keyunknown frontmatter key "disable"
Process rating: all ten parameters 70/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 53 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3082 tokens
- 100Running it twice. No mutating operations
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 1486: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 12 headings
- +3Step-by-step instructions: 53 items
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.