AA conduct-patent-research-ip
Conduct an evidence-backed patent research program from a technical problem and preliminary solution through iterative patent searching, technology-route analysis, project novelty pre-screening, FTO-oriented risk screening, competitor monitoring, recent-publication surveillance, and self-contained HTML plus DOCX reporting. Use when a user asks for patent research, project-initiation novelty review, technical-route analysis, patent risk screening, competitor patent tracking, or a comprehensive patent-search report.
Conduct an evidence-backed patent research program from a technical problem and preliminary solution through iterative patent searching, technology-route…
As a process A 84/100 · Runs to the end — weak spots: running it twice
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
body-longSKILL.md body ≈ 7392 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "copyright"
Process rating: all ten parameters 84/100
- 30Running it twice. 2 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 7392 tokens
- 85Steps. 250 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Result and completion. Output format and completion criterion are stated
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 18 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)
- +1No license
- +2Single-language instructions
- +3Description length 519: enough signal without eating the budget
- +4Structure: 58 headings
- +3Step-by-step instructions: 250 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.