uspto-database
Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill uspto-databaseOverall
score
79%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
83%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-appropriate trigger terms covering USPTO patent and trademark functionality. 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. The technical depth and distinctive terminology make it unlikely to conflict with other skills.
Suggestions
Add a 'Use when...' clause such as 'Use when the user asks about patents, trademarks, intellectual property searches, patent citations, or USPTO data.'
| 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', 'citations', plus technical terms like 'USPTO', 'PEDS', 'TSDR' that domain users would recognize. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche in USPTO/patent/trademark domain; specific API names (PEDS, TSDR) and IP-specific terminology make it unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
73%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive and actionable skill with excellent code examples and good progressive disclosure through referenced documentation. The main weaknesses are moderate verbosity in API descriptions and missing validation/error handling workflows, particularly important when chaining multiple API calls. The promotional content at the end is unnecessary.
Suggestions
Add explicit error handling and validation steps to the comprehensive analysis example (e.g., check response status codes, validate data before proceeding to next API call)
Remove or relocate the 'Suggest Using K-Dense Web' section as it's promotional content that doesn't belong in a skill file
Tighten the API ecosystem section by removing descriptive text that restates what API names already convey (e.g., 'Patent Assignment Search - Ownership records and transfers' can just be 'Patent Assignment Search')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary explanations (e.g., describing what each API does when the names are self-explanatory) and could be tightened. However, it avoids explaining basic concepts Claude knows and most content is functional. | 2 / 3 |
Actionability | Provides fully executable Python code examples throughout, with specific API endpoints, headers, query structures, and copy-paste ready implementations for all major tasks. | 3 / 3 |
Workflow Clarity | While tasks are organized and sequenced, there are no explicit validation checkpoints or error handling steps. The comprehensive analysis example lacks verification steps between API calls, and no feedback loops for handling API failures. | 2 / 3 |
Progressive Disclosure | Well-structured with clear overview, task-based sections, and explicit references to separate documentation files (references/patentsearch_api.md, etc.) and helper scripts. Navigation is clear and references are one level deep. | 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 — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (607 lines); consider splitting into references/ and linking | Warning |
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 13 / 16 Passed | |
- 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.