Name: patent
Rating: 62.4 (1 reviews)
Author: alirezarezvani

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

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.gemini/skills/patent/SKILL.md

The canonical home for this skill is patent in alirezarezvani/claude-skills

Quality

Content

56%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.

The body is well-structured with a clear sequenced workflow and explicit validation, but its actionability and progressive disclosure are undermined by missing bundle files (referenced scripts and reference docs do not exist) and some inline detail that belongs in those references. Conciseness is adequate but padded by pedagogical rationale blocks.

Suggestions

Ship the referenced bundle files (references/sub_use_case_routing.md, references/cpc_classification_canon.md, references/legal_disclaimer_discipline.md, and scripts/sub_use_case_router.py, citation_tracker.py, family_resolver.py) so the body's links and commands resolve.

Move the per-sub-use-case query patterns and the full DOCX 8-section spec into references, keeping only the routing summary and a concise section list inline, to tighten conciseness and complete progressive disclosure.

Replace prose query descriptions ('3 narrow queries on invention-specific terminology') with one concrete example query string per pattern so the guidance is copy-paste executable.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's intelligence (it never explains patent basics), but the per-question 'Why I'm asking' rationale blocks, the repeated legal-disclaimer statements, and the sub-use-case table that duplicates the routing reference add tokens that could be trimmed.	3 / 5
Actionability	Concrete commands are given (e.g., 'python scripts/sub_use_case_router.py --sub-use-case novelty ...' and a zip-integrity validation one-liner), but the referenced scripts do not exist in the bundle and the per-source query patterns are prose rather than literal query strings, leaving the guidance only partially executable.	3 / 5
Workflow Clarity	Seven phases are clearly sequenced from grill-me intake through delivery, with explicit validation (Phase 7 zip-integrity check and section confirmation), a retry/stop feedback loop, and an error-handling table and anti-patterns acting as checklists.	4 / 5
Progressive Disclosure	Sections are well-organized and references are clearly signaled as one-level-deep links, but the three referenced reference files and three scripts are absent from the bundle, so navigation is broken, and substantial detail (query patterns, DOCX section spec) remains inlined rather than split out.	3 / 5
	Total	13 / 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.

The description is specific, complete, and distinctive, with explicit what/when trigger guidance and clear scope boundaries; its only minor weakness is trigger-term synonym coverage. It uses third-person voice throughout with no first/second-person violations.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Searches Google Patents, Espacenet, USPTO, and optionally Lens.org', 'claim-text extracted', 'CPC-class-aware landscape', 'family-resolved hits', 'FTO flags', 'full audit log', 'editable Word document (.docx)' — giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both what (multi-source patent search producing a verdicted .docx) and when ('Use when the user asks for patent searching or analysis' with concrete example trigger phrases), and also bounds scope by excluding trademark/copyright/trade-secret.	5 / 5
Trigger Term Quality	Includes natural phrases users would say — 'prior art search for [invention]', 'freedom to operate analysis for [product]', 'patent searching or analysis' — plus the five named sub-use-cases, but a few common synonyms (e.g., 'patent landscape', 'novelty search') are only implied rather than enumerated.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — patent prior-art and landscape intelligence routed through five distinct sub-use-cases — with an explicit out-of-scope statement, so it is unlikely to trigger for the wrong skill.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 5 missing	Warning
referenced_paths_exist	Referenced path issues: 18 missing	Warning

	Total	14 / 16 Passed

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

Reviewed: ~11 hours 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.