AF review-fto-report-quality-ip
Review the quality, reproducibility, legal reasoning, and decision usefulness of an existing freedom-to-operate (FTO), patent-infringement-risk, or event IP risk report. Use for three-layer evidence review, four-dimension scoring, independent multi-route search comparison, omission analysis, fatal-defect screening, remediation planning, or HTML assessment generation. The skill audits a supplied report; it does not replace a jurisdiction-specific legal opinion.
Review the quality, reproducibility, legal reasoning, and decision usefulness of an existing freedom-to-operate (FTO), patent-infringement-risk, or event IP…
As a process F 61/100 · Will not run — References files that are not bundled: assets/fto_report.css, assets/harness_report.css
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7166 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: assets/fto_report.css - warning
missing-refreference to a missing file: assets/harness_report.css - note
frontmatter-keyunknown frontmatter key "copyright"
Process rating: all ten parameters 61/100
- 0Tools and files. 2 referenced file(s) missing: assets/fto_report.css, assets/harness_report.css
- 0Failures and branches. Linear process with no failure handling
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 7166 tokens
- 100Steps. 212 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 20 top-level sections: this looks like several domains in one skill
- 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)
- +1No license
- +2Single-language instructions
- +3Description length 464: enough signal without eating the budget
- +4Structure: 53 headings
- +3Step-by-step instructions: 212 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.