claims-drafting

Draft patent claims for an invention. Use when user says "撰写权利要求", "draft claims", "写权利要求书", "claim drafting", or wants to create patent claims. The core skill of the patent pipeline.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

62%

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

The content is well-structured with a clear, validated multi-step workflow and good use of an examiner feedback loop, but leans verbose and uses template placeholders rather than concrete executable examples. Referenced shared files are absent from the bundle, weakening progressive disclosure.

Suggestions

Tighten the examiner prompt block and consolidate the duplicated jurisdiction/format guidance to reduce token cost without losing essential detail.

Replace [element]/[主题] placeholders with at least one fully worked, concrete claim example per jurisdiction so guidance is copy-paste ready.

Add the referenced shared-references/*.md files to the bundle (or note them as external to the pipeline) so progressive-disclosure references point to real, loadable material.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and task-focused, but sections like the full examiner prompt block and repeated jurisdiction tables add length beyond the essential; it explains some concepts (e.g. antecedent basis rules) Claude largely already knows.	2 / 3
Actionability	Provides concrete guidance via the mcp__codex__codex call template and specific claim format strings, but claim text itself is template/pseudocode ([element 1], [主题]) rather than executable copy-paste examples, leaving key drafting details abstract.	2 / 3
Workflow Clarity	Clear 7-step sequence with explicit validation checkpoints (quality-check checklists, claim-to-specification mapping, examiner review feedback loop with revision rounds up to MAX_CLAIM_REVISION_ROUNDS), satisfying the feedback-loop requirement for batch/iterative work.	3 / 3
Progressive Disclosure	References shared-references files (patent-writing-principles.md, format-cn/us/ep) but these are NOT in the bundle (references/ is empty) and are signaled as one-level-deep loads; no in-bundle files exist to verify, and the body itself is fairly monolithic.	2 / 3
	Total	9 / 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 concise, specific, and bilingual, clearly stating what the skill does and when to use it with explicit natural-language triggers. It is highly distinct and low-conflict within a patent pipeline.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'Draft patent claims for an invention' with multilingual drafting triggers and jurisdiction-specific formats (CN/US/EP) implied by the skill's core action.	3 / 3
Completeness	Clearly answers what (draft patent claims) and when (explicit 'Use when user says...' clause with multiple triggers), satisfying both halves explicitly.	3 / 3
Trigger Term Quality	Strong coverage of natural terms users would say across languages: "撰写权利要求", "draft claims", "写权利要求书", "claim drafting", and "wants to create patent claims".	3 / 3
Distinctiveness Conflict Risk	Clear niche (patent claim drafting) with distinct, specialized triggers unlikely to fire for other skills in the pipeline.	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.