uspto-database

Access USPTO data (Patent Search, PEDS, TSDR, assignments) when you need to query patents/trademarks and retrieve prosecution or status information programmatically.

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Other/uspto-database/SKILL.md

Quality

Content

65%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 lean and actionable with a sensible Search->History->Status workflow and a runnable example. It loses points for missing validation checkpoints on a batch-oriented workflow and for failing to surface the existing references/api_docs.md from the body.

Suggestions

Add an explicit validation/verification step to the workflow (e.g., check returned record counts and errors, retry on failure) so batch query operations have feedback loops, lifting workflow_clarity past the cap.

Link references/api_docs.md from the body (e.g., under Implementation Details or a new API Reference section) so the bundled reference is clearly signaled and one level deep.

Add short runnable examples for PEDS and TSDR mirroring the PatentSearchClient example to close the actionability gaps.

Dimension	Reasoning	Score
Conciseness	The body is efficiently sectioned (When to Use, Key Features, Dependencies, Example Usage, Implementation Details) and assumes Claude's competence, with only minor over-explanation such as 'names may vary by implementation' and 'where available' hedges that could be trimmed, fitting anchor 4.	4 / 5
Actionability	Provides an executable, real example importing PatentSearchClient and concrete script paths in the workflow; minor gaps are that PEDS/TSDR usage and authentication specifics are not shown in runnable code, matching anchor 4.	4 / 5
Workflow Clarity	A clear Search -> History -> Status-checks sequence with script paths is present, but for a batch/automation-oriented skill there are no validation or verification checkpoints (no result checking, no error-recovery loop), so the rubric's batch-operation cap holds it at anchor 3.	3 / 5
Progressive Disclosure	Section structure is reasonable, but references/api_docs.md exists in the bundle and is never linked or signaled from the body, and API/query-model detail is inlined rather than pointed to, matching anchor 3 ('references present but not clearly signaled').	3 / 5
	Total	14 / 20 Passed

Description

73%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 a strong, niche-specific trigger for USPTO data access with clear what/when structure and natural keywords. Its main weakness is the second-person 'when you need to' phrasing, which the rubric penalizes in specificity.

Suggestions

Rephrase in third person to satisfy the rubric's voice rule, e.g. 'Accesses USPTO data ... Use when querying patents or trademarks ...' instead of 'when you need to query'.

Surface the TSDR/assignment retrieval actions explicitly in the description rather than only as a parenthetical subsystem list, to lift specificity toward anchor 5.

Dimension	Reasoning	Score
Specificity	Names the USPTO domain and enumerates subsystems (Patent Search, PEDS, TSDR, assignments) with concrete actions ('query patents/trademarks', 'retrieve prosecution or status information'), which sits at anchor 4, but the second-person phrasing 'when you need to query' triggers the rubric's -1 specificity penalty.	3 / 5
Completeness	Explicitly answers both 'what' (access/query/retrieve USPTO data) and 'when' ('when you need to query patents/trademarks and retrieve prosecution or status information programmatically'); the 'when' is present and reasonably explicit but not maximally specific, matching anchor 4.	4 / 5
Trigger Term Quality	Includes natural terms a user would say ('patents', 'trademarks', 'Patent Search', 'PEDS', 'TSDR', 'prosecution', 'status') with good coverage; a few common synonyms/extensions are absent, fitting anchor 4 rather than the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	A clear niche (USPTO patent/trademark programmatic access) with distinct, specialized triggers (USPTO, PEDS, TSDR) that are unlikely to fire for unrelated skills, matching anchor 5.	5 / 5
	Total	16 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Other/uspto-database/SKILL.md
Commit: 63c61d3

Reviewed: 5 hours ago

Table of Contents

Discovery Implementation Validation

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.