CtrlK
BlogDocsLog inGet started
Tessl Logo

patent-pipeline

Full patent drafting pipeline from invention description to jurisdiction-formatted filing documents. Supports CN (CNIPA), US (USPTO), EP (EPO). Supports invention patents and utility models. Use when user says "写专利", "patent pipeline", "专利申请", "draft patent", "写权利要求书", or wants to draft a complete patent application.

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

63%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.

A well-structured, highly actionable orchestration skill with clear phases, checkpoints, and state persistence. Its main weaknesses are verbosity from duplicated diagrams and restated content, and the absence of progressive disclosure — everything lives in one monolithic file.

Suggestions

Remove the duplicated pipeline diagram (lines 28-33) and the redundant 'Composing with Other Workflows' entry-point list, since both repeat content already present in the Overview and Phase 0 sections.

Consolidate the 'Patent Type Specifications' tables with the Constants block so protection/terms/timeline facts appear once instead of being restated.

Add the explicit ⛔ STOP-and-confirm checkpoint to Phases 4-5 (or document why they auto-proceed) to match the validation rigor of Phases 1-3.

DimensionReasoningScore

Conciseness

Mostly efficient task-specific material, but the pipeline diagram appears twice (lines 16-21 and 28-33), patent-type tables restate the constants section, and the entry-point examples repeat Phase 0 context-gathering — more than minor padding.

3 / 5

Actionability

Provides concrete, copy-paste-ready sub-skill invocation commands, an exact state JSON schema, file paths, and output tables; minor gaps are template placeholders like '[X] patent references found' in checkpoint blocks.

4 / 5

Workflow Clarity

Clear 6-phase sequence with explicit STOP checkpoints and feedback loops (adjust→re-check, review rounds) plus state persistence, but Phases 4-5 lack the explicit ⛔ user-confirmation checkpoint present in Phases 1-3 — a minor validation gap.

4 / 5

Progressive Disclosure

Has clear section headers but is a single ~340-line monolith with no bundle files or one-level-deep references; substantial reference-style content (type-spec tables, checkpoint templates, state schema) is inlined rather than split into separate files.

3 / 5

Total

14

/

20

Passed

Description

100%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 exemplary: third-person voice, concrete capabilities, bilingual natural trigger terms, and explicit what/when guidance. It scores at the top of every dimension with no vague fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — full drafting pipeline, jurisdiction-formatted filing (CN/US/EP), and invention/utility model types — giving comprehensive coverage of the skill's scope, matching the anchor-5 example.

5 / 5

Completeness

Explicitly answers both 'what' (full patent drafting pipeline from invention description to jurisdiction-formatted filing) and 'when' (a concrete 'Use when user says...' clause with trigger phrases), matching anchor 5.

5 / 5

Trigger Term Quality

Provides comprehensive bilingual natural trigger phrases ('写专利', 'patent pipeline', '专利申请', 'draft patent', '写权利要求书') plus a behavioral trigger, matching the anchor-5 standard of synonyms and variations.

5 / 5

Distinctiveness Conflict Risk

Patent drafting is a clear niche with distinctive bilingual triggers ('专利申请', '写权利要求书') unlikely to collide with other skills, matching the anchor-5 minimal-conflict criterion.

5 / 5

Total

20

/

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.