SKILLEMALL.ai

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.

ClawHub Agent Skills author: yuanzhian-patsnap v1.0.0 MIT-0 2 files body ≈ 7 392 tokens Open the sourceclawhub.ai analyzed 3 d ago

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

AnalyzerWordData and analyticsInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
A
90/100
safety, quality, tests
Safety 60%
100
Quality 40%
76
Run on models
none yet
Process rating
A
84/100
Runs to the end
Running it twice w 4
30
When it triggers w 12
50
Inputs and preconditions w 11
70
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • 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-long SKILL.md body ≈ 7392 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown 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.

External checks

ClawHub: clean
This skill is a disclosed patent-research workflow that uses PatSnap connectors and local report generation in ways that match its stated purpose.
LLM: benign (high) · VirusTotal: · 13 Aug 2026