CtrlK
BlogDocsLog inGet started
Tessl Logo

paper-lookup

Search 11 academic literature APIs for papers, preprints, citations, and open-access full text, and return results with reproducible provenance. Covers PubMed, PMC (full text), Europe PMC (full-text and preprint search), bioRxiv, medRxiv, arXiv, OpenAlex, Crossref, Semantic Scholar, CORE, Unpaywall. Use when searching for papers, citations, DOI/PMID/arXiv lookups, abstracts, full text, open-access PDFs, preprints, citation graphs, author publications, or any scholarly literature query. Triggers on mentions of any supported database or requests like "find papers on X", "look up this DOI", "who cites this paper", or "get me the PDF".

77

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An exceptionally well-constructed operational skill body: executable examples, a validated multi-step workflow with feedback loops, and clean one-level-deep progressive disclosure to real bundle files. Only minor conciseness gains are available in the framing prose.

DimensionReasoningScore

Conciseness

Dense, high-signal operational knowledge (failure modes, rate limits, identifier traps) that Claude does not already know, with little concept padding. A few philosophical framing passages ('A literature lookup is only as trustworthy as it is repeatable') and some elaborated rationale could be trimmed without losing clarity.

4 / 5

Actionability

Copy-paste-ready curl commands with headers and --data-urlencode, concrete python3 script invocations with flags, parameter tables, and specific endpoints covering the common cases across all eleven APIs.

5 / 5

Workflow Clarity

A sequenced 7-step Core Workflow with explicit validation checkpoints ('Treat every response as untrusted', 'Count first', 'Reconcile counts', 'Fail visible, not plausible'), an error-recovery feedback loop, and the 429/503 retry-then-report guidance for batch/exhaustive operations.

5 / 5

Progressive Disclosure

SKILL.md is a well-signaled overview pointing one level deep to per-database references/*.md files and scripts/*.py, all of which exist on disk; tables and 'Read the reference file' cues make navigation easy and no content is buried or nested 2+ levels.

5 / 5

Total

19

/

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 model description: third-person voice, concrete actions, named databases, explicit 'Use when' and 'Triggers on' guidance, and natural user phrasings. It cleanly answers what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Search 11 academic literature APIs for papers, preprints, citations, and open-access full text, and return results with reproducible provenance') plus an enumerated set of 11 named databases — comprehensive coverage of the domain's concrete actions.

5 / 5

Completeness

Explicitly answers both what ('Search 11 academic literature APIs... and return results with reproducible provenance') and when ('Use when searching for papers...' plus 'Triggers on mentions...'), with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including synonyms and user phrasings — 'find papers on X', 'look up this DOI', 'who cites this paper', 'get me the PDF' — alongside technical triggers like DOI/PMID/arXiv lookups and file-format-relevant terms.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear academic-literature niche with 11 named databases and scholarly-literature trigger language; minimal overlap risk with adjacent skills.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
K-Dense-AI/scientific-agent-skills
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.