CtrlK
BlogDocsLog inGet started
Tessl Logo

patent-review

Get an external patent examiner review of a patent application. Use when user says "专利审查", "patent review", "审查意见", "examiner review", or wants critical feedback on patent claims and specification.

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

81%Weight 40%Scale 1-5

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

The body is well-structured, actionable, and includes a genuine review feedback loop with score-based gating. It is token-heavy due to verbatim prompt/report templates, and progressive disclosure is solid though the prompts could optionally be externalized.

Suggestions

Move the two large verbatim reviewer prompts and the report markdown template into a ./references/ file (e.g., reviewer_prompt.md and report_template.md), keeping only a concise summary plus a link in SKILL.md to improve progressive_disclosure and conciseness.

Tighten or remove redundant prompt lines such as "Be rigorous and specific. This is a real examination." since the persona framing already conveys rigor.

Specify how the [all claims] / [key sections] placeholder slots should be assembled (e.g., concatenation order or size limits) to close the minor actionability gaps.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes Claude's competence (cites statutes without explaining them); the two large verbatim prompt blocks and full report template are necessary scaffolding with only minor redundant lines, matching anchor 4 rather than the lean anchor 5.

4 / 5

Actionability

Provides concrete executable MCP calls with model, config, and full prompt templates plus a triage scheme and report template, with only minor gaps (placeholder assembly, threadId reuse), matching anchor 4.

4 / 5

Workflow Clarity

A clear 5-step sequence with an explicit examine→fix→re-examine feedback loop (Round 2 checks whether rejections are overcome and flags new issues), score-based gating, and proceeding rules, matching anchor 5.

5 / 5

Progressive Disclosure

No bundle files exist and all content is inlined under clear section headers with no nested references — good single-file organization; the large prompt blocks could arguably be split into a reference file, keeping it at anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

82%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is clear, bilingual, and explicitly answers both what the skill does and when to trigger it, with strong distinctiveness. Specificity is the weakest dimension: it states the overall purpose rather than enumerating several concrete capabilities.

DimensionReasoningScore

Specificity

Names the domain and 1-2 concrete actions ("external patent examiner review", "critical feedback on patent claims and specification") but does not enumerate several specific actions, matching anchor 3.

3 / 5

Completeness

Explicitly states both what (external patent examiner review) and when (concrete "Use when user says…" trigger phrases), matching anchor 5.

5 / 5

Trigger Term Quality

Good bilingual trigger coverage ("专利审查", "patent review", "审查意见", "examiner review", "critical feedback on patent claims and specification") with a few natural synonyms (e.g., "office action", "OA") missing, matching anchor 4.

4 / 5

Distinctiveness Conflict Risk

A clear niche (patent examination) with distinctive bilingual triggers and minimal overlap with other skills, matching anchor 5.

5 / 5

Total

17

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.