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

88%

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

77%

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 a clear, well-validated multi-phase workflow and properly signaled bundle references. Its main weaknesses are verbosity from heavy cross-section repetition and a large amount of detail kept inline that should live in the reference files.

Suggestions

Consolidate the repeated script usage examples: keep one canonical set of commands in "Tools and Scripts" and have the workflow phases and example workflows reference them instead of re-listing full invocations.

Move the detailed search strategies, best-practices prose, and the four full example workflows into the existing reference files, leaving SKILL.md as a concise overview that points to them.

Trim the "Visual Enhancement with Scientific Schematics" section or relocate it; its marketing-style language ("Nano Banana Pro will automatically generate") is off-topic for a citation skill and adds noise.

Dimension	Reasoning	Score
Conciseness	The ~1240-line body repeats script usage across "Core Workflow", "Tools and Scripts", and "Example Workflows", includes a tangential schematics marketing section ("Nano Banana Pro will automatically generate"), and explains concepts Claude already knows (MeSH, E-utilities), so it is mostly actionable but could be tightened rather than being lean.	2 / 3
Actionability	It provides fully executable commands with concrete flags (e.g., "python scripts/search_pubmed.py --query … --date-start 2020 --output …") and complete BibTeX examples that are copy-paste ready, matching the score-3 anchor.	3 / 3
Workflow Clarity	Phases 1–5 are clearly sequenced, with Phase 2.5 and Phase 4 providing explicit validation checkpoints and a validate→fix→re-validate feedback loop plus post-writing checklists, satisfying the score-3 anchor.	3 / 3
Progressive Disclosure	References are real, one-level-deep, and well-signaled ("see references/google_scholar_search.md"), but the SKILL.md itself is a 1240-line monolith with search strategies, best practices, and example workflows kept inline that belong in the reference files, fitting the score-2 anchor of content that should be separate being inline.	2 / 3
	Total	10 / 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.

The description is specific, uses third person, and clearly answers both what the skill does and when to use it with natural trigger phrases. It is a strong, low-conflict description with no notable weaknesses.

Dimension	Reasoning	Score
Specificity	"Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries" lists multiple specific concrete actions, matching the score-3 anchor rather than the partial coverage of score 2.	3 / 3
Completeness	It explicitly states what the skill does and adds an explicit "This skill should be used when you need to…" trigger clause, answering both what and when rather than leaving when implied.	3 / 3
Trigger Term Quality	"find papers, verify citation information, convert DOIs to BibTeX, ensure reference accuracy in scientific writing" are natural phrases a user would actually say, giving good coverage rather than just some relevant keywords.	3 / 3
Distinctiveness Conflict Risk	The citation-management niche (Google Scholar, PubMed, DOIs, BibTeX) has distinct triggers unlikely to conflict with other skills, unlike the generic overlap of score 2.	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/scientific-agent-skills
Path: skills/citation-management/SKILL.md
Commit: 757b63b

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.