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

91%

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

88%Weight 40%Scale 1-5

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

A highly actionable, well-sequenced patent claims drafting workflow with copy-paste formats, an executable examiner-review tool call, and a clear revision feedback loop. Conciseness and progressive disclosure are slightly held back by a long inline examiner prompt/output template and external shared-reference paths not present in the bundle.

Suggestions

Move the full examiner-review prompt block and the CLAIMS.md output template into a referenced file (e.g. references/examiner-prompt.md) and inline only the key fields, tightening conciseness and improving progressive disclosure.

Either vendor the referenced ../shared-references/patent-format-*.md files into a local references/ directory or confirm they exist in the shared location, so the one-level-deep references are verifiable within the bundle.

Trim redundant restatements (e.g. the Key Rules section repeats antecedent-basis and result-to-be-achieved rules already detailed in Steps 2-3) to recover tokens.

Dimension	Reasoning	Score
Conciseness	The body is efficient and almost entirely domain-specific knowledge Claude would not already know (jurisdiction formats, antecedent basis, numbering rules), but the long examiner-review prompt block and full output template could be trimmed, keeping it just below the lean 5 anchor.	4 / 5
Actionability	Provides copy-paste-ready claim-format templates ("其特征在于", "comprising", "characterised in that"), an executable mcp__codex__codex call with model and config, and concrete quality checklists, matching the fully-executable anchor.	5 / 5
Workflow Clarity	Seven clearly sequenced steps with an explicit validation feedback loop (Step 5 examiner review -> Step 6 revision up to MAX_CLAIM_REVISION_ROUNDS) and checklists, matching the anchor for clear sequence with validation and error-recovery loops.	5 / 5
Progressive Disclosure	Good structure with a dedicated Shared References section signaling one-level-deep files (patent-writing-principles.md, jurisdiction format files), but those referenced paths point outside the bundle (../shared-references/) and are not present in the local references/ directory, leaving minor organization/verifiability gaps versus the clean 5 anchor.	4 / 5
	Total	18 / 20 Passed

Description

95%Weight 40%Scale 1-5

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 with excellent trigger coverage (bilingual synonyms) and a clear what/when structure. The only minor gap is that it names a single action rather than enumerating the several concrete drafting sub-actions.

Dimension	Reasoning	Score
Specificity	States one clear concrete action ("Draft patent claims for an invention") but does not enumerate multiple distinct actions (revise, format per jurisdiction, review), so it falls short of comprehensive coverage at 5 yet is clearer than the partial 3 anchor.	4 / 5
Completeness	Explicitly answers both what ("Draft patent claims for an invention") and when ("Use when user says ...") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Provides comprehensive natural trigger terms across English and Chinese synonyms ("撰写权利要求", "draft claims", "写权利要求书", "claim drafting", "create patent claims"), matching the anchor for full coverage including synonyms.	5 / 5
Distinctiveness Conflict Risk	Patent claim drafting is a narrow, distinctive niche with specialized triggers ("claim drafting", "patent pipeline") unlikely to overlap with other skills, matching the minimal-conflict anchor.	5 / 5
	Total	19 / 20 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/claims-drafting/SKILL.md
Commit: 0472e53

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.