patent

Patent prior-art and landscape intelligence skill — not generic patent help. Commits to one of five sub-use-cases via forcing intake (novelty search / freedom-to-operate / competitive landscape / acquisition diligence / litigation prior-art) before any search runs. Searches Google Patents, Espacenet, USPTO, and optionally Lens.org for citation-graph signals. Output is an editable Word document (.docx) with verdict, ranked closest art (claim-text extracted), CPC-class-aware landscape, family-resolved hits, geographic coverage, FTO flags where applicable, strategy recommendations, and full audit log. Use when the user asks for patent searching or analysis (e.g., 'prior art search for [invention]', 'freedom to operate analysis for [product]'). Produces search signal, not legal advice — always recommends consulting a patent attorney before filing or licensing decisions. Trademark, copyright, and trade-secret questions are out of scope.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, mostly executable workflow with strong sequencing, validation checkpoints, and clean progressive disclosure into real bundle files. Tightening the intake rationale prose and making Phase 3 query patterns copy-paste ready would push it higher.

Suggestions

Trim or relocate the repeated '*Why I'm asking:*' rationale blocks to shorten intake without losing the grill-me discipline.

Replace the descriptive Phase 3 query patterns with concrete, parameterized example queries (or delegate them to a script) so the search step is copy-paste executable.

Add an explicit 'if zip-integrity or section check fails → fix and re-run' loop to the Phase 7 validation to make the final feedback loop fully explicit.

Dimension	Reasoning	Score
Conciseness	Dense and assumes competence (no explanation of what a patent is), but the repeated 'Why I'm asking:' rationale blocks and some DOCX-section prose add minor over-explanation that could be trimmed.	4 / 5
Actionability	Provides executable commands (the sub_use_case_router.py invocation with full args, family_resolver.py, and the zip-integrity validation one-liner), but Phase 3 query patterns remain descriptive ('3 narrow queries on invention-specific terminology') rather than copy-paste ready.	4 / 5
Workflow Clarity	Phases 1–7 are clearly sequenced with explicit checkpoints — a stop condition after Q6, a 1 q/sec rate-limit discipline, retry policy with a 3-failure halt, an end-of-run validation step, and a full error-handling table providing feedback loops for a batch document-generation task.	5 / 5
Progressive Disclosure	Body is a clear overview pointing to three real, one-level-deep reference files and three real scripts, each linked inline and summarized in dedicated Tooling/References sections; all referenced paths were verified to exist.	5 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that names concrete capabilities, explicit triggers, and clear scope boundaries. The only minor gap is slightly thinner coverage of casual synonym trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'verdict, ranked closest art (claim-text extracted), CPC-class-aware landscape, family-resolved hits, geographic coverage, FTO flags' — plus commitment to one of five named sub-use-cases and four named search sources, giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (detailed output and behavior) and 'when' via 'Use when the user asks for patent searching or analysis (e.g., ...)', with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases like 'prior art search for [invention]' and 'freedom to operate analysis for [product]', with good coverage but a few common synonyms and shorthand variations absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (patent prior-art/landscape intelligence) and explicitly fences off scope — 'Trademark, copyright, and trade-secret questions are out of scope' — minimizing conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: alirezarezvani/claude-skills
Path: research/patent/skills/patent/SKILL.md
Commit: 19392f7

Reviewed: ~1 hour ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.