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.
85
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description with excellent trigger term coverage in both Chinese and English, and a clear 'Use when' clause that makes it easy for Claude to select. The main weakness is that the 'what' portion is somewhat thin—it could benefit from listing more specific actions beyond just 'draft patent claims.' The note about being 'the core skill of the patent pipeline' adds useful context for skill selection priority.
Suggestions
Expand the specificity of capabilities by listing concrete sub-actions, e.g., 'Drafts independent claims, dependent claims, method claims, and apparatus claims based on invention disclosures.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (patent claims) and one action (draft patent claims), but does not list multiple specific concrete actions like 'draft independent claims, dependent claims, method claims, apparatus claims' or similar granular capabilities. | 2 / 3 |
Completeness | Clearly answers both 'what' (draft patent claims for an invention) and 'when' (explicit 'Use when' clause with specific trigger phrases and the general condition of wanting to create patent claims). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms in both Chinese and English: '撰写权利要求', 'draft claims', '写权利要求书', 'claim drafting', and 'create patent claims'. These cover common variations a user would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Patent claim drafting is a very specific niche with distinct bilingual trigger terms. It is unlikely to conflict with other skills unless there are multiple patent-related skills, and even then the mention of 'core skill of the patent pipeline' and specific claim-drafting focus provides clear differentiation. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill for patent claim drafting with excellent workflow clarity including validation checkpoints and a revision feedback loop. The jurisdiction-specific formatting guidance and critical warnings about common mistakes add genuine value. The main weakness is moderate verbosity — some sections explain concepts Claude likely knows, and the monolithic structure could benefit from offloading detailed content (like the examiner prompt template) to referenced files.
Suggestions
Trim explanations of basic patent concepts Claude already knows (e.g., what antecedent basis is, what 'comprising' means) to just the rules/constraints.
Consider moving the full examiner review prompt template and the detailed jurisdiction format table into separate referenced files to reduce the main skill's token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long (~200 lines) and includes some content Claude already knows (e.g., explaining what antecedent basis means, basic claim drafting conventions). However, the jurisdiction-specific formatting tables and the critical warnings about empirical content and numbering are genuinely useful additions. Some sections like the dependent claim rules could be tightened. | 2 / 3 |
Actionability | The skill provides highly concrete, executable guidance: specific claim formats per jurisdiction with exact phrasing (其特征在于, characterised in that), exact MCP tool call syntax for the examiner review, quality checklists, output file format with markdown template, and clear examples of correct vs. incorrect claim content. The guidance is copy-paste ready for each jurisdiction. | 3 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced with explicit validation checkpoints: quality checklists after Step 2, claim-to-specification mapping in Step 4, cross-model examiner review in Step 5, and a revision loop with up to 3 rounds in Step 6. The feedback loop (review → fix → re-review) is well-defined with clear termination conditions. | 3 / 3 |
Progressive Disclosure | The skill references four shared reference files (patent-writing-principles.md, patent-format-cn/us/ep.md) which is good structure, but no bundle files are provided to verify they exist. The main SKILL.md itself is quite long and some content (like the full examiner review prompt or the detailed jurisdiction table) could potentially be split into referenced files. The references are one-level deep and clearly signaled, which is positive. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
2028ac4
- Reviewed
Table of Contents
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.