uspto-database
Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches.
85
77%
Does it follow best practices?
Impact
91%
1.62xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/uspto-database/SKILL.mdQuality
Discovery
82%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 description with excellent specificity and domain-specific trigger terms that clearly identify its USPTO/IP niche. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill over others.
Suggestions
Add a 'Use when...' clause such as 'Use when the user asks about patents, trademarks, prior art research, patent examination status, or needs to search USPTO databases.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, IP analysis, and prior art searches. | 3 / 3 |
Completeness | Clearly answers 'what' with specific USPTO API capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance to indicate when Claude should select this skill. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'patent', 'trademark', 'prior art', 'office actions', 'USPTO', 'IP analysis', plus technical terms like 'PEDS' and 'TSDR' that domain experts would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche in USPTO/patent/trademark domain. Terms like 'USPTO', 'PEDS', 'TSDR', 'office actions' are unique to intellectual property work and unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%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, actionable skill with excellent code examples and good progressive disclosure to reference files. The main weaknesses are some verbosity in introductory sections and missing validation/error handling guidance in multi-step workflows. The skill would benefit from consolidating redundant overview content and adding explicit error handling patterns.
Suggestions
Consolidate the 'Overview' and 'When to Use This Skill' sections to eliminate redundancy and reduce token usage
Add error handling examples for common failure modes (rate limits, missing data, API errors) in the workflow examples
Add validation checkpoints to the 'Comprehensive Patent Analysis' example (e.g., check API responses before proceeding, handle None results)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary verbosity, such as explaining what APIs do when the section headers already make this clear. The overview section and 'When to Use This Skill' section have significant overlap and could be consolidated. | 2 / 3 |
Actionability | Provides fully executable Python code examples throughout, with concrete API calls, proper imports, and copy-paste ready snippets. Direct API usage examples include complete headers, URLs, and query structures. | 3 / 3 |
Workflow Clarity | While individual tasks are well-documented, the comprehensive analysis example lacks explicit validation checkpoints. There's no error handling guidance for API failures, rate limit hits, or missing data scenarios in the workflows. | 2 / 3 |
Progressive Disclosure | Excellent structure with clear overview, task-based sections, and well-signaled references to detailed documentation files (references/*.md) and helper scripts (scripts/*.py). Navigation is straightforward with one-level-deep references. | 3 / 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (606 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 9 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
71add64
- 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.