AB identify-patent-white-space-ip
Identify candidate patent white-space signals from a patent map, technology-effect matrix, technology-application matrix, cluster map, roadmap, or sparse portfolio region; test whether the signal is a search or classification artifact; assess the value of the underlying problem; diagnose route breaks and primary contradictions; and propose two to four principle-level resolution directions. Use for structured innovation-opportunity exploration from patent-map evidence. Require explicit user confirmation after candidate selection and after problem-value assessment; do not perform downstream technical validation, commercial validation, FTO, patentability, or filing-strategy justification.
Identify candidate patent white-space signals from a patent map, technology-effect matrix, technology-application matrix, cluster map, roadmap, or sparse…
As a process B 75/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "copyright"
Process rating: all ten parameters 75/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 166 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3899 tokens
- 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 694: enough signal without eating the budget
- +4Structure: 31 headings
- +3Step-by-step instructions: 166 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.