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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

72%

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

A well-structured, actionable patent-figure workflow with concrete templates and a verification checkpoint. Its main weaknesses are some redundant content (duplicate index tables, repeated rules) and an implicit rather than explicit error-recovery loop in the verification step.

Suggestions

Remove the duplicate Reference Numeral Index example in Step 5 or Step 7, keeping it in one place, and trim Key Rules to only conventions not already stated in the workflow.

Turn Step 6's flagging into an explicit feedback loop: after flagging a missing figure or numeral, state to regenerate the affected description/index and re-verify before finalizing output.

Slightly raise the description specificity by naming the concrete sub-operations (numeral assignment per 100-series, jurisdiction-specific templates, claim cross-reference index) rather than the two broad verbs currently used.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concept padding Claude already knows, but the Reference Numeral Index table is shown twice (Step 5 and Step 7 Output) and the Key Rules section reiterates conventions already stated in the workflow, so it could be tightened.	2 / 3
Actionability	Provides concrete, copy-paste-ready output templates for both CN and US/EP jurisdictions, explicit file paths, numeral-range tables, and a structured claim-cross-reference table — actionable guidance rather than vague direction.	3 / 3
Workflow Clarity	A clearly sequenced 7-step process with an explicit verification checkpoint (Step 6 cross-reference table), but the recovery loop is implicit — flagged missing figures/numerals are surfaced to the user without a fix-and-re-validate step, so it falls short of the top anchor's feedback loop.	2 / 3
Progressive Disclosure	Self-contained single-file skill with no bundle files present and no need for external references; content is cleanly organized into Constants, Inputs, numbered Workflow steps, and Key Rules, matching the well-organized-sections expectation.	3 / 3
	Total	10 / 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, well-formed description with explicit trigger guidance in both English and Chinese and a clearly scoped patent-figure niche. The only mild weakness is specificity, which summarizes the work in two broad actions rather than enumerating the several concrete sub-operations the skill performs.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ('Process user-provided patent figures and generate formal drawing descriptions') but stops short of listing multiple specific operations like numeral assignment or index generation that the body actually performs.	2 / 3
Completeness	Explicitly answers both 'what' (process figures, generate drawing descriptions) and 'when' via an explicit 'Use when user says...' clause, matching the top anchor.	3 / 3
Trigger Term Quality	Good multilingual coverage of natural trigger phrases a user would actually say ('附图处理', 'figure description', '附图说明', 'drawings description', 'describe patent figures with reference numerals').	3 / 3
Distinctiveness Conflict Risk	Clear niche (patent figures with reference numerals) with domain-specific triggers unlikely to fire for unrelated skills; the body even distinguishes it from /paper-figure.	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
Commit: 82076e5

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.