BB review-japanese-patent-claims-ip
Review claims in a Japanese patent application or a PCT/Paris-route application intended for Japan across six dimensions: Japanese Patent Act/JPO compliance, evidence-backed novelty and inventive-step pre-screening, claim architecture and drafting quality, JPO examination risk, foreign-origin and translation risk, and strategic protection. Use when the user provides Japanese or foreign-language application materials and asks for a JPO-oriented claim review, amendment options, prosecution-readiness assessment, prior-art comparison, or a complete English HTML claims report.
Review claims in a Japanese patent application or a PCT/Paris-route application intended for Japan across six dimensions: Japanese Patent Act/JPO compliance…
As a process B 78/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 3, column 14: description: Review claims in a Japanese patent application or a PCT/Paris-rout… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
body-longSKILL.md body ≈ 6976 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "copyright"
Process rating: all ten parameters 78/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 6 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50Failures and branches. 0 branches, has a failure section
- 70Execution cost. Instruction body is 6976 tokens
- 85Steps. 357 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100When it triggers. States when to use and when not to
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Consistency. Name and required fields are in place
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 578: enough signal without eating the budget
- +4Structure: 37 headings
- +3Step-by-step instructions: 357 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.