BC patent-mining
Retrieves and interprets patent data with the conventions that make counts and claims defensible, covering Google Patents, Lens, EPO Open Patent Services, USPTO data through PatentsView and the Open Data Portal, and WIPO PATENTSCOPE, together with kind codes, DOCDB and INPADOC families, priority versus filing versus publication dates, CPC and IPC classification, claim structure, assignee normalization and the limits of chemistry in patents, and records every query with the date it was run. Use for prior-art checks, freedom-to-operate scoping, technology landscapes, assignee or inventor analyses and patent-derived chemistry; use literature-review for scholarly sources and research-lookup for one quick fact.
Retrieves and interprets patent data with the conventions that make counts and claims defensible, covering Google Patents, Lens, EPO Open Patent Services…
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "summary" - note
edit-residuethe text marks something as outdated (lines 25): check that old rules are not kept next to new ones — the full check reads the text for contradictions
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. 4 mutating operations with no state check
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 27 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1576 tokens
- high The skill tells the model to perform an irreversible action with no human approval
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)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +3Description length 715: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 27 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.