paper-lookup

Search 10 academic paper databases via REST APIs for research papers, preprints, and scholarly articles. Covers PubMed, PMC (full text), bioRxiv, medRxiv, arXiv, OpenAlex, Crossref, Semantic Scholar, CORE, Unpaywall. Use when searching for papers, citations, DOI/PMID lookups, abstracts, full text, open access, preprints, citation graphs, author search, or any scholarly literature query. Triggers on mentions of any supported database or requests like "find papers on X" or "look up this DOI".

Quality

89%

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

Quality

Content

78%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, mostly lean instruction skill that delegates per-database endpoint detail to one-level-deep reference files and provides a clear sequenced workflow with error recovery. The main gap is that no example API call is inline, leaving the most executable detail to the references.

Suggestions

Add one or two short inline example calls (e.g., a sample PubMed esearch URL or an Unpaywall lookup) so the body is copy-paste ready for the most common cases before users must open a reference file.

Tighten the 'Loading API keys' and Output Format sections — the three-step key-loading prose and the full markdown report template could be condensed without losing actionability.

Add an explicit verification checkpoint in the Core Workflow (e.g., confirm each database's response parsed/returned expected fields before reporting), to push workflow clarity to a 5.

Dimension	Reasoning	Score
Conciseness	Information-dense tables and no padding of concepts Claude already knows; minor prose sections (e.g., 'Loading API keys' steps, the full output template) could be trimmed slightly without losing clarity.	4 / 5
Actionability	Concrete procedural guidance — specific env var names (NCBI_API_KEY, CORE_API_KEY), identifier formats with examples (10.1038/nature12373, PMC7029759), per-platform fetch tools, and rate limits — but actual endpoint URLs/example calls live in the reference files rather than inline.	4 / 5
Workflow Clarity	A clear 5-step Core Workflow with error-recovery feedback loops (429 retry, try alternative identifiers/databases, report failures) and a 'report no results explicitly' checkpoint; minor validation gaps keep it just below a 5.	4 / 5
Progressive Disclosure	SKILL.md is a clean overview pointing to one-level-deep, clearly signaled references ('references/<db>.md') for each database; all 10 referenced files exist and the 'Available Databases' table makes navigation easy.	5 / 5
	Total	17 / 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.

A strong, third-person description that concretely states capabilities, enumerates all covered databases, and provides explicit trigger guidance with natural user phrasings. It cleanly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Names the domain (10 academic databases via REST APIs) and lists many concrete actions — 'citations, DOI/PMID lookups, abstracts, full text, open access, preprints, citation graphs, author search' — for comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ('Search 10 academic paper databases via REST APIs...') and when ('Use when searching for papers... Triggers on mentions of any supported database...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural keywords including synonyms ('papers', 'preprints', 'scholarly literature', 'open access') and explicit user phrasings like 'find papers on X' and 'look up this DOI', plus all 10 database names users would mention.	5 / 5
Distinctiveness Conflict Risk	A clear, narrow niche (scholarly literature lookup across 10 named databases) with distinct triggers; minimal overlap risk with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/paper-lookup/SKILL.md
Commit: f5ef65b

Reviewed: ~11 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.