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

92%

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

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable and well-structured with clear phased workflows, validation checkpoints, and properly signaled one-level references. The main weakness is conciseness: significant cross-section repetition and a tangential schematics section inflate the body well beyond a lean overview.

Suggestions

De-duplicate the search and script-usage examples: keep one canonical set (e.g. under Tools and Scripts) and have earlier phases reference them rather than restating full command blocks.

Remove or relocate the "Visual Enhancement with Scientific Schematics" section — it concerns a different skill and adds noise unrelated to citation management.

Move the inline citation-count standards, venue-quality tiers, and repeated BibTeX templates into the existing reference files, leaving the body as a concise overview with pointers.

Dimension	Reasoning	Score
Conciseness	The body is ~1240 lines with notable redundancy — Google Scholar/PubMed search examples and script usage appear in Phase 1, again under Search Strategies, and again under Tools and Scripts — plus an off-topic "Visual Enhancement with Scientific Schematics" section; it stays on-task but is far from lean.	2 / 3
Actionability	Provides fully executable commands with flags, file paths, BibTeX entry templates, and JSON output examples throughout — copy-paste ready and specific.	3 / 3
Workflow Clarity	Sequenced Phases 1-5 with explicit goals, plus Phase 2.5's numbered scan/search/update/handle steps and the mandatory post-writing verification checks that include validation and feedback loops for batch/destructive operations.	3 / 3
Progressive Disclosure	Overview body points to real one-level-deep reference files (e.g. "see `references/bibtex_formatting.md` for complete guide"), with a Resources section listing all bundled references, scripts, and assets for easy navigation.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 description: concrete capabilities, explicit use-when triggers, natural keywords, and a distinct niche with low conflict risk. Third person is maintained throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries" — matching the anchor for several specific concrete actions.	3 / 3
Completeness	Explicitly states what the skill does and includes a clear "This skill should be used when you need to..." clause answering both what and when with explicit triggers.	3 / 3
Trigger Term Quality	Covers natural terms users would say ("find papers, verify citation information, convert DOIs to BibTeX, ensure reference accuracy") alongside Google Scholar, PubMed, BibTeX, and DOIs, giving good natural-language coverage.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (academic citation management via Scholar/PubMed/BibTeX/DOI) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1251 lines); consider splitting into references/ and linking	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: K-Dense-AI/claude-scientific-writer
Path: .claude/skills/citation-management/SKILL.md
Commit: 4717803

Reviewed: about 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.