figure-description
Process user-provided patent figures and generate formal drawing descriptions. Use when user says "附图处理", "figure description", "附图说明", "drawings description", or wants to describe patent figures with reference numerals.
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 a clear 'Use when' clause, strong bilingual trigger terms, and a distinctive niche. Its main weakness is that the 'what' portion could be more specific about the concrete actions performed (e.g., identifying components, mapping reference numerals, formatting descriptions per patent office standards).
Suggestions
Add more specific concrete actions to the 'what' portion, e.g., 'identifies components in patent figures, maps reference numerals to part names, and generates formatted drawing descriptions per patent office standards.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (patent figures) and two actions (process figures, generate drawing descriptions), but doesn't elaborate on specific sub-actions like extracting reference numerals, formatting output, or handling multiple figure types. | 2 / 3 |
Completeness | Clearly answers both 'what' (process patent figures and generate formal drawing descriptions) and 'when' (explicit 'Use when' clause with specific trigger phrases and a conceptual trigger about describing patent figures with reference numerals). | 3 / 3 |
Trigger Term Quality | Includes excellent natural trigger terms in both Chinese ('附图处理', '附图说明') and English ('figure description', 'drawings description'), plus the conceptual trigger 'describe patent figures with reference numerals'. Good coverage of how users would naturally phrase this request. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — patent figure descriptions with reference numerals is very specific and unlikely to conflict with other skills. The bilingual trigger terms further narrow the scope. | 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-crafted skill with a clear, multi-step workflow that provides concrete guidance for patent figure description generation. Its strengths are the explicit numeral assignment conventions, jurisdiction-specific templates, and the validation cross-reference step. Minor weaknesses include some verbosity that could be trimmed and the lack of supporting bundle files for progressive disclosure of jurisdiction-specific templates.
Suggestions
Consider extracting the CN and US/EP jurisdiction-specific templates into separate reference files (e.g., `templates/cn_figure_desc.md` and `templates/us_figure_desc.md`) to improve progressive disclosure and reduce main file length.
Remove the comparison line about `/paper-figure` — it's unnecessary context that doesn't help Claude execute this skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some content that could be tightened. The examples in Steps 4 and 5 are helpful but somewhat verbose, and the distinction from `/paper-figure` is unnecessary context. The constants section and input section are efficient, but the overall length could be reduced. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: specific directory paths, numeral assignment conventions with exact ranges, output file paths, format templates for both CN and US/EP jurisdictions, and complete table schemas for the reference numeral index and cross-reference verification. | 3 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced with explicit validation in Step 6 (cross-referencing claims to ensure coverage) and clear flagging mechanisms for missing figures or numerals. The feedback loop of identifying gaps and flagging them as [MISSING] provides error recovery guidance. | 3 / 3 |
Progressive Disclosure | The skill references external files (INVENTION_DISCLOSURE.md, CLAIMS.md) as inputs and specifies output file paths, but all content is inline in a single file. Given the length (~100 lines of substantive content), the CN vs US/EP jurisdiction templates and the detailed examples could potentially be split into separate reference files. However, no bundle files exist to support this. | 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
66b974e
- 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.