patent-assistant

Assists R&D teams with patent technical disclosure drafting and patent/novelty search analysis; use when users ask to write a patent disclosure, structure an invention description, search related patents, or assess novelty.

Quality

67%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/patent-assistant/SKILL.md

Quality

Content

50%

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

A well-structured, actionable skill body with real bundle scripts and clear workflows, but it keeps detailed templates and reference tables inline and omits validation checkpoints. Splitting heavy reference material into separate files and adding explicit verify steps would lift it across dimensions.

Suggestions

Move the full worked disclosure example and the IPC classification table into separate reference files (e.g., references/disclosure-template.md and references/ipc-guide.md), keeping only concise pointers in SKILL.md.

Document scripts/generate_disclosure.py in the body with an executable invocation example, mirroring the patent_search.py CLI block, so the drafting workflow is concrete rather than prose-only.

Add an explicit validation/review checkpoint to the drafting and search workflows (e.g., "verify all checklist fields are filled before finalizing" or "confirm search results cover all key features") to introduce a feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with well-organized sections, but the full ~50-line worked disclosure example and the inline IPC table add length that a capable model could largely infer or that could live in a reference file.	2 / 3
Actionability	Concrete CLI commands and a disclosure template are provided, but the drafting workflow is described as prose ("ask if missing") without referencing the existing scripts/generate_disclosure.py, and search output is labeled only as "conceptual."	2 / 3
Workflow Clarity	Both the drafting and search workflows are sequenced into numbered steps, but there are no explicit validation checkpoints or feedback loops despite batch search operations, capping clarity at 2 per the rubric.	2 / 3
Progressive Disclosure	Content is organized into clear sections and the referenced scripts/patent_search.py is a real file, but the detailed disclosure template and IPC reference table are inlined in SKILL.md rather than split into dedicated reference files.	2 / 3
	Total	8 / 12 Passed

Description

85%

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, third-person description that clearly defines a distinctive patent-assistant niche with explicit what-and-when triggers. Trigger-term coverage is the weakest area, missing common variations users might say like "prior art" or "patent search."

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions—"patent technical disclosure drafting," "patent/novelty search analysis," "structure an invention description," "search related patents," and "assess novelty"—rather than vague language.	3 / 3
Completeness	It explicitly states what the skill does (drafting and search analysis) and when to use it via the "use when users ask to write a patent disclosure, structure an invention description, search related patents, or assess novelty" clause, covering both what and when.	3 / 3
Trigger Term Quality	Natural trigger phrases like "write a patent disclosure," "search related patents," and "assess novelty" are present, but common variations such as "patent search," "prior art," or "claims" are absent.	2 / 3
Distinctiveness Conflict Risk	The patent-disclosure niche is clearly defined with distinct, domain-specific triggers that are unlikely to overlap with or trigger unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Commit: 7cc5680

Reviewed: 3 days 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.