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

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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 well-structured orchestration skill with strong actionability and workflow clarity (explicit checkpoints, feedback loops, state recovery). Its main weaknesses are minor redundancy in the overview/composition diagrams and a single monolithic file with no progressive disclosure to reference materials.

Suggestions

Remove the redundant second ASCII diagram (lines 28-33) and the 'Composing with Other Workflows' section, or merge them into a single concise entry-point list to cut repetition.

Split the static patent-type specification tables and jurisdiction-format deliverables into a references/ file (e.g. references/PATENT_TYPES.md) and link to it from the body, reducing the main file length.

Trim the 'Acknowledgements' section — it is decorative and does not guide execution.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete phases, checkpoints, and tables, but includes redundant material — the parallel-branch idea is shown in two ASCII diagrams (lines 28-33 echo lines 23-26) and 'Composing with Other Workflows' repeats the entry-point info, plus a decorative 'Acknowledgements' section.	2 / 3
Actionability	Provides concrete, copy-paste-ready guidance throughout: specific sub-skill invocations with arguments ('/prior-art-search "patent/INVENTION_BRIEF.md"'), named output files, checkpoint message templates, a PATENT_STATE.json schema, and a final report template.	3 / 3
Workflow Clarity	Phases 0-5 are clearly sequenced with explicit '🚦 Checkpoint' / '⛔ STOP HERE' gates, per-phase state persistence, examiner-review feedback loops (MAX_REVIEW_ROUNDS=2), and recovery rules for stale state and missing Codex access.	3 / 3
Progressive Disclosure	Well-organized into clear sections and delegates to sub-skills via slash commands, but with no references/assets bundle everything lives inline in a ~345-line file — content like the patent-type tables and jurisdiction-format deliverables could be split into referenced files for a skill this complex.	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.

A strong description that clearly states capabilities with jurisdiction and patent-type specifics, uses third-person voice, and provides explicit bilingual 'Use when' triggers. It answers both what and when without padding.

Dimension	Reasoning	Score
Specificity	Lists concrete capabilities — 'jurisdiction-formatted filing documents', 'CN (CNIPA), US (USPTO), EP (EPO)', 'invention patents and utility models' — with specific jurisdictions and patent types rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('Full patent drafting pipeline from invention description to jurisdiction-formatted filing documents') and when ('Use when user says...') with explicit trigger guidance.	3 / 3
Trigger Term Quality	Provides natural trigger terms users would actually say in both English ('patent pipeline', 'draft patent') and Chinese ('写专利', '专利申请', '写权利要求书'), covering common variations.	3 / 3
Distinctiveness Conflict Risk	Patent drafting is a clear niche with distinct bilingual triggers; the combination of jurisdiction/patent-type specifics makes conflict with other skills unlikely.	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
Path: skills/patent-pipeline/SKILL.md
Commit: c5f3d5b

Reviewed: about 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.