patent-pipeline

Full patent drafting pipeline from invention description to jurisdiction-formatted filing documents. Supports CN (CNIPA), US (USPTO), EP (EPO). Supports invention patents and utility models. Use when user says "写专利", "patent pipeline", "专利申请", "draft patent", "写权利要求书", or wants to draft a complete patent application.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

The body is highly actionable with a clearly sequenced, validated workflow and good checkpoint discipline, but it is somewhat verbose and monolithic with no progressive disclosure into bundled reference files. Tightening duplicated diagrams and splitting reference material would raise the weaker dimensions.

Suggestions

Remove the duplicate idea-discovery branching diagram (lines 23-33) — one diagram conveys the same information and saves tokens.

Move the patent-type specification tables and the PATENT_STATE.json schema into a reference file (e.g. references/PATENT_TYPES.md) referenced one level deep, improving progressive disclosure.

Collapse the repeated 'Options: go / adjustments / stop' and STOP-HERE boilerplate into a single stated convention to reduce token redundancy across phases.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining basics Claude knows, but duplicates the idea-discovery branching in two ASCII diagrams and repeats checkpoint phrasing, so it could be tightened. Not a 3 because not every token earns its place.	2 / 3
Actionability	Provides concrete executable slash-commands with arguments, a complete JSON state schema, output-file tables, and copy-ready checkpoint templates — fully actionable rather than abstract.	3 / 3
Workflow Clarity	Phases are explicitly sequenced with STOP-HERE validation checkpoints, state persistence for resume, novelty assessment, and two examiner-review rounds — clear feedback loops for a fragile multi-step operation.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the SKILL.md is monolithic; content like patent-type specs and the state schema is inline rather than split into one-level-deep reference files. Not a 1 because sections are well-organized, but not a 3 absent clear external reference navigation.	2 / 3
	Total	10 / 12 Passed

Description

100%

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, trigger-rich, and fully answers both 'what' and 'when' with a clear bilingual Use-when clause. It is concise and uses third person throughout. No weaknesses to address.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'drafting pipeline from invention description to jurisdiction-formatted filing documents' with named jurisdictions (CN/US/EP) and patent types — matching the anchor 'lists multiple specific concrete actions'.	3 / 3
Completeness	Explicitly answers both what it does and when to use it via a clear 'Use when user says...' clause with concrete triggers, satisfying the top anchor.	3 / 3
Trigger Term Quality	Includes natural trigger terms users would say in both English and Chinese ('patent pipeline', 'draft patent', '写专利', '专利申请', '写权利要求书'), giving good coverage rather than jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (patent drafting) with jurisdiction-specific and bilingual triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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.