patent-review

Get an external patent examiner review of a patent application. Use when user says "专利审查", "patent review", "审查意见", "examiner review", or wants critical feedback on patent claims and specification.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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

A thorough, actionable skill body with a clear multi-round workflow and validation gates. Its main weakness is conciseness and progressive disclosure, since the bulky inline prompt templates bloat the single-file overview.

Suggestions

Move the Round-1 and Round-2 examiner prompt templates into separate referenced files (e.g. references/round1_prompt.md) and keep a concise summary in SKILL.md to improve progressive disclosure.

Trim filler lines such as 'This is a real examination' and 'Be rigorous and specific' from the prompts to tighten conciseness without losing the office-action structure.

Add a brief validation step that confirms the Codex MCP server is reachable before Round 1, so the prerequisite check is an explicit workflow checkpoint.

Dimension	Reasoning	Score
Conciseness	It is mostly efficient and avoids over-explaining concepts Claude knows, but the two large inline prompt templates and filler lines like 'This is a real examination' could be tightened, matching the score-2 anchor.	2 / 3
Actionability	It provides copy-paste-ready MCP invocation blocks with config, full prompt scaffolds, and an exact report format including a markdown table, giving fully executable guidance.	3 / 3
Workflow Clarity	The five-step sequence has explicit checkpoints: CRITICAL issues must be fixed before proceeding, a Round-1→Round-2 feedback loop via threadId, and a score-below-5 rework gate, matching the score-3 anchor.	3 / 3
Progressive Disclosure	No bundle files exist and the body is self-contained with well-organized sections, but the large inline examiner-prompt templates could be split into referenced files, leaving it at the score-2 anchor rather than a clean overview pointing one level deep.	2 / 3
	Total	10 / 12 Passed

Description

90%

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, well-targeted description that pairs a concrete action with explicit, multilingual 'Use when' triggers. It is slightly limited on specificity by naming one primary action rather than enumerating several.

Dimension	Reasoning	Score
Specificity	It names the domain (patent application) and a concrete action ('Get an external patent examiner review'), but lists a single primary action rather than multiple distinct concrete actions, so it falls short of the score-3 anchor.	2 / 3
Completeness	It clearly answers both 'what' (get an external patent examiner review of a patent application) and 'when' via an explicit 'Use when' clause with concrete triggers, matching the score-3 anchor.	3 / 3
Trigger Term Quality	It includes natural terms a user would actually say across both languages — '专利审查', 'patent review', '审查意见', 'examiner review' — plus 'critical feedback on patent claims and specification', giving good coverage.	3 / 3
Distinctiveness Conflict Risk	It targets a clear niche (patent examiner review via Codex MCP) with distinct multilingual triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Commit: 82076e5

Reviewed: 5 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.