crossref-database

Access CrossRef metadata for scholarly works; use when you need to resolve a DOI or search CrossRef to retrieve bibliographic details, citation/reference counts, or funder information for research and citation management.

Quality

71%

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/Evidence Insight/crossref-database/SKILL.md

Quality

Content

58%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 core technical content is accurate, executable, and well-structured with real referenced bundle scripts, giving strong actionability and workflow clarity for a read-only API skill. The principal weakness is a large block of generic process boilerplate that pads the file with guidance Claude already knows, hurting token efficiency.

Suggestions

Remove or collapse the generic boilerplate sections ("When Not to Use", "Required Inputs", "Recommended Workflow", "Output Contract", "Validation and Safety Rules", "Failure Handling", "Quick Validation", "Deterministic Output Rules", "Completion Checklist") — they restate obvious process steps rather than CrossRef-specific guidance and inflate the token budget.

Consolidate the two "Validation Shortcut" / "Quick Validation" blocks that both repeat `python scripts/query_crossref.py --help` into a single concise validation step.

Add one concrete example showing funder extraction (e.g., the flag/field path used to surface `funder` entries) so the documented capability matches an executable invocation.

Dimension	Reasoning	Score
Conciseness	The skill-specific sections are tight, but roughly half the body is generic boilerplate ("When Not to Use", "Required Inputs", "Recommended Workflow", "Output Contract", "Validation and Safety Rules", "Failure Handling", "Quick Validation", "Deterministic Output Rules", "Completion Checklist") that restates obvious process guidance Claude already knows, making it noticeably verbose and padded.	2 / 5
Actionability	Provides concrete, executable commands ("python scripts/query_crossref.py --doi ...", "--query ... --limit 5", "pip install habanero>=1.2.0") with real flags and documented returned fields, leaving only minor gaps (no example showing funder extraction invocation specifically).	4 / 5
Workflow Clarity	Presents a clear validation-first sequence (run --help to verify the path, resolve or search, note availability caveats) with a validation shortcut and expected-output format; this is a read-only API query skill so the destructive/batch cap does not apply, though the explicit error-recovery loop is only lightly sketched in "Failure Handling".	4 / 5
Progressive Disclosure	Well-organized sections with one-level-deep references to real bundle files (scripts/query_crossref.py, scripts/validate_skill.py) that exist and are correctly invoked; structure is clear and navigation is easy, with only minor gaps (no separate reference doc for the full returned-field schema, but the inline coverage is reasonable for a simple skill).	4 / 5
	Total	14 / 20 Passed

Description

83%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, concrete description that clearly states both what the skill does and when to use it, with domain-specific trigger terms (DOI, CrossRef, citation counts, funder info). The main gap is modest trigger-term synonym coverage and slight breadth-induced overlap risk with general citation skills.

Dimension	Reasoning	Score
Specificity	Names the domain (CrossRef metadata for scholarly works) and several concrete actions — "resolve a DOI", "search CrossRef", "retrieve bibliographic details, citation/reference counts, or funder information" — giving multiple specific capabilities with only minor coverage gaps (no explicit mention of canonical URLs or returning search result lists).	4 / 5
Completeness	It explicitly answers both "what" ("Access CrossRef metadata for scholarly works; ... retrieve bibliographic details, citation/reference counts, or funder information") and "when" ("use when you need to resolve a DOI or search CrossRef ... for research and citation management") with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Contains natural trigger phrases users would say ("resolve a DOI", "search CrossRef", "bibliographic details", "citation/reference counts", "funder information", "citation management") with good coverage, though it lacks common synonyms/file extensions beyond "DOI" and "CrossRef".	4 / 5
Distinctiveness Conflict Risk	The CrossRef/DOI niche is fairly distinct with clear triggers, but "research and citation management" is broad enough to risk minor overlap with general citation/bibliography skills; mostly distinct rather than a clear isolated niche.	4 / 5
	Total	17 / 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/crossref-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.