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.
77
73%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/patent-pipeline/SKILL.mdQuality
Discovery
100%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 strong skill description that clearly defines a specialized patent drafting capability with concrete actions, supported jurisdictions, and patent types. It includes an explicit 'Use when' clause with excellent bilingual trigger terms covering both Chinese and English user queries. The description is concise, specific, and highly distinguishable from other potential skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions and details: 'Full patent drafting pipeline from invention description to jurisdiction-formatted filing documents', specifies supported jurisdictions (CN/CNIPA, US/USPTO, EP/EPO), and patent types (invention patents, utility models). | 3 / 3 |
Completeness | Clearly answers both 'what' (full patent drafting pipeline from invention description to filing documents, supporting multiple jurisdictions and patent types) and 'when' (explicit 'Use when' clause with specific trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms in both English and Chinese: '写专利', 'patent pipeline', '专利申请', 'draft patent', '写权利要求书', plus domain terms like USPTO, CNIPA, EPO, invention patents, utility models. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — patent drafting with specific jurisdiction support and bilingual triggers. Very unlikely to conflict with other skills given the specialized domain and explicit trigger terms. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
47%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 orchestration skill with excellent workflow clarity, explicit checkpoints, and state persistence for long-running tasks. However, it suffers significantly from verbosity — explaining patent fundamentals, including extensive tables about patent types, and providing pipeline relationship diagrams that don't aid execution. The actionability is moderate since it delegates to sub-skills that aren't provided in the bundle, making the skill more of a coordination document than a self-contained executable guide.
Suggestions
Remove the patent type specification tables (invention vs utility model details) — Claude knows these, and the key constraint (utility model = CN only, apparatus claims only) can be stated in one line under Key Rules.
Remove or drastically shorten the Overview section's explanation of how this skill relates to other pipeline tracks (publish/funding/patent) — this context is not needed for execution.
Move the Final Deliverables table and Final Report template into a separate reference file (e.g., OUTPUT_FORMAT.md) to reduce the main skill's length.
Provide the referenced sub-skill files (prior-art-search, claims-drafting, etc.) as bundle files, or at minimum document what each sub-skill is expected to produce so the pipeline can function if sub-skills are missing.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines. It explains patent basics Claude already knows (what invention patents vs utility models are, protection periods, examination types), includes lengthy tables of jurisdiction details, and has extensive ASCII art diagrams showing pipeline relationships to other skills that aren't necessary for execution. The overview section explaining what patents are vs publications is unnecessary context. | 1 / 3 |
Actionability | The skill provides a clear sequence of sub-skill invocations with specific command syntax (e.g., `/prior-art-search "patent/INVENTION_BRIEF.md"`), checkpoint templates, and a state persistence JSON schema. However, the sub-skills themselves are not defined here and no bundle files are provided, so the actual execution depends entirely on undefined external skills. The commands are invocations of other skills rather than executable code. | 2 / 3 |
Workflow Clarity | The workflow is exceptionally well-structured with 6 clearly sequenced phases (0-5), explicit checkpoints marked with 🚦 and ⛔ symbols, user confirmation gates at each phase, state persistence after every phase with recovery logic, and clear options at each checkpoint (go/adjust/stop). The feedback loop for review rounds and the resume-from-interruption mechanism are well-designed. | 3 / 3 |
Progressive Disclosure | The skill references multiple sub-skills (/prior-art-search, /patent-novelty-check, /claims-drafting, etc.) and external files (INVENTION_BRIEF.md, IDEA_REPORT.md), but no bundle files are provided to support these references. The content that could be in separate files (patent type specifications tables, composing with other workflows section, acknowledgements) is inline, making the main file longer than necessary. | 2 / 3 |
Total | 8 / 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
2028ac4
- 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.