Write detailed embodiment descriptions for patent specifications. Use when user says "撰写实施例", "write embodiment", "实施例描述", "detailed description", or wants to describe how to practice an invention.
68
83%
Does it follow best practices?
Impact
—
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 skill description with excellent trigger term coverage in both Chinese and English, a clear 'Use when' clause, and a distinct niche in patent embodiment writing. Its main weakness is that the 'what' portion could be more specific about the concrete actions performed beyond just 'write detailed embodiment descriptions'.
Suggestions
Expand the capability description to list more specific actions, e.g., 'Write detailed embodiment descriptions for patent specifications, including step-by-step method implementations, apparatus configurations, and example variations.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (patent specifications) and one action (write detailed embodiment descriptions), but does not list multiple concrete actions such as drafting claims, generating figures descriptions, or structuring sub-embodiments. | 2 / 3 |
Completeness | Clearly answers both 'what' (write detailed embodiment descriptions for patent specifications) and 'when' (explicit 'Use when' clause with specific trigger phrases and a conceptual trigger scenario). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms in both Chinese and English: '撰写实施例', 'write embodiment', '实施例描述', 'detailed description', and the conceptual trigger 'describe how to practice an invention'. Good bilingual coverage of terms users would actually say. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of patent-specific terminology, bilingual Chinese/English triggers, and the narrow focus on embodiment descriptions makes this highly distinctive and unlikely to conflict with other skills. | 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 well-structured, highly actionable skill for patent embodiment writing that provides concrete templates, formatting rules, and domain-specific conventions Claude wouldn't inherently know. The workflow is clear with good validation checkpoints, and the critical rules about avoiding experimental data are important guardrails. Minor weaknesses include some verbosity in the repeated warnings about experimental data and the monolithic structure that could benefit from splitting advanced guidance into separate files.
Suggestions
Consolidate the multiple 'no experimental data' warnings into a single concise rule with one good/bad example pair, rather than repeating the point across Key Rules with multiple examples.
Consider extracting the detailed reference numeral formatting rules and the claim support verification table template into a separate reference file to improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and contains domain-specific knowledge Claude wouldn't inherently know (patent embodiment writing conventions, reference numeral formatting, US best mode requirement). However, some sections are somewhat verbose — the repeated emphasis on 'no experimental data' with multiple examples could be consolidated, and the explanatory framing ('they are the patent equivalent of experiment sections') adds minor padding. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: specific formatting rules for reference numerals (first mention vs. subsequent), exact output file paths, table templates for planning and verification, example text patterns for opening paragraphs and variations, and clear examples of correct vs. incorrect embodiment language. The pseudocode example and step descriptions are copy-paste ready templates. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced with logical progression: plan → write → integrate numerals → verify claim support → handle special cases → output. Step 4 provides an explicit verification/validation checkpoint (claim support verification table) with a feedback loop ('If any claim element lacks embodiment support, add the necessary description'), which is critical for this type of document generation task. | 3 / 3 |
Progressive Disclosure | The skill references input files from a clear directory structure (patent/INVENTION_DISCLOSURE.md, patent/CLAIMS.md, patent/figures/numeral_index.md) and specifies output location, showing awareness of a broader system. However, all content is inline in a single file with no references to supporting documents for advanced topics (e.g., detailed reference numeral conventions, claim type-specific guidance), and the file is fairly long — some sections like the Key Rules could potentially be separated. | 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 | |
66b974e
Table of Contents
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.