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

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%

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 drafting workflow with concrete jurisdiction-specific templates, validation, and a revision loop. The main weakness is conciseness: the inline examiner prompt, output template, and a redundant closing 'Key Rules' section add length without proportional value.

Suggestions

Move the full examiner-review prompt block and the CLAIMS.md output template into reference files and replace them with a brief inline summary plus a Load pointer.

Trim or remove the trailing 'Key Rules' section, since its points (antecedent basis, comprising, no result-to-be-achieved language) already appear in Step 2; keep only genuinely new rules.

Confirm the ../shared-references/*.md files exist in the deployed pipeline; they are correctly signaled but could not be verified in this isolated review snapshot.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept padding, but the inline ~30-line examiner prompt block, the ~30-line output template, and the trailing 'Key Rules' section (which restates antecedent-basis/comprising/no-result-language points already covered) could be tightened, matching the level-2 'Mostly efficient but includes some unnecessary explanation or could be tightened' rather than the lean level-3.	2 / 3
Actionability	Provides copy-paste-ready format strings with exact phrases (其特征在于, comprising, characterised in that), concrete RIGHT/WRONG claim examples, a full examiner-review prompt, and explicit quality-check checklists, matching the level-3 'Fully executable ... specific examples; copy-paste ready' for an instruction skill.	3 / 3
Workflow Clarity	Seven clearly sequenced steps with explicit validation (Step 5 cross-model examiner review) and a feedback loop (Step 6 revision loop bounded by MAX_CLAIM_REVISION_ROUNDS), plus checklists in Step 2, matching the level-3 'Clear sequence with explicit validation steps; feedback loops for error recovery'.	3 / 3
Progressive Disclosure	Body is an overview that pushes detailed format rules to a dedicated 'Shared References' section with well-signaled, one-level-deep Load statements for four reference files, matching the level-3 'Clear overview with well-signaled one-level-deep references'.	3 / 3
	Total	11 / 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 description with explicit what/when structure, third-person voice, and rich multilingual trigger terms. Its only weakness is specificity: it names a single action rather than enumerating the concrete sub-tasks the skill performs.

Suggestions

List multiple concrete actions to lift specificity, e.g. 'Draft, revise, and cross-review patent claims across CN/US/EP jurisdictions; map claims to specification; run examiner review.'

Dimension	Reasoning	Score
Specificity	Names the domain (patent claims) and one concrete action ("Draft patent claims for an invention"), but does not enumerate multiple distinct actions, matching the anchor 'Names domain and some actions, but not comprehensive' rather than the level-3 'Lists multiple specific concrete actions'.	2 / 3
Completeness	Explicitly answers both what ("Draft patent claims for an invention") and when with an explicit 'Use when' clause, so it is not capped at 2 per the missing-trigger guideline and matches the level-3 anchor.	3 / 3
Trigger Term Quality	Provides good multilingual coverage of natural terms users would say ("撰写权利要求", "draft claims", "写权利要求书", "claim drafting", "wants to create patent claims"), matching the level-3 'Good coverage of natural terms users would say'.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (patent claim drafting) with specific, domain-distinct triggers unlikely to fire for other skills, matching the level-3 'Clear niche with distinct triggers; unlikely to conflict'.	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
Path: skills/claims-drafting/SKILL.md
Commit: c5f3d5b

Reviewed: about 2 hours 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.