citation-management

Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.

Quality

83%

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

75%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 highly actionable with executable commands and a well-sequenced, validated workflow, supported by a real one-level reference bundle. Its main weakness is conciseness — several sections (schematics, integrations, summary, duplicate resource listings) add tokens without proportional value.

Suggestions

Trim or relocate the 'Visual Enhancement with Scientific Schematics' section, which is tangential to citation management and consumes ~30 lines for a cross-skill reference.

Consolidate the 'Reference Files' and 'Resources/Bundled Resources' lists into a single reference enumeration to remove duplication.

Cut the 'Summary' section, which restates capabilities already covered in the Overview and When-to-Use sections.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and task-focused, but padded/redundant sections — 'Visual Enhancement with Scientific Schematics', 'Integration with Other Skills', 'Summary', and a 'Resources/Bundled Resources' block that re-lists the same references and scripts already enumerated in 'Reference Files' — push it above the lean ideal.	3 / 5
Actionability	Every phase ships copy-paste-ready bash commands with concrete flags and examples (e.g. 'python scripts/extract_metadata.py --pmid 34265844'), covering the common search/extract/format/validate cases.	5 / 5
Workflow Clarity	A clear five-phase sequence with explicit validation (Phase 4) and a mandatory Phase 2.5 enrichment checkpoint before formatting, but the awkward 2.5 numbering and some implicit retry steps leave minor validation gaps.	4 / 5
Progressive Disclosure	Body is an overview pointing to ten one-level-deep reference files (all verified to exist) with clear links, but the duplicate reference listing across 'Reference Files' and 'Resources' is a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

92%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 specific, complete, and distinct: it names concrete capabilities and provides an explicit 'use when' trigger clause. The only minor gap is trigger-term synonym coverage, which keeps trigger quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Search Google Scholar and PubMed', 'extract accurate metadata', 'validate citations', 'generate properly formatted BibTeX entries' — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Clearly answers both 'what' (search, extract, validate, generate BibTeX) and 'when' via the explicit 'This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX...' trigger clause.	5 / 5
Trigger Term Quality	Good natural-term coverage ('find papers', 'verify citation information', 'convert DOIs to BibTeX', 'ensure reference accuracy') but misses some synonyms and extensions like 'references', 'PMID', or 'bibliography'.	4 / 5
Distinctiveness Conflict Risk	A clear niche — academic citation management tied to Google Scholar, PubMed, and BibTeX — with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 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
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: K-Dense-AI/claude-scientific-writer
Path: .claude/skills/citation-management/SKILL.md
Commit: 14ee3e3

Reviewed: 1 day 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.