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.
77
73%
Does it follow best practices?
Impact
81%
1.84xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/citation-management/SKILL.mdQuality
Discovery
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.
This is a strong skill description that clearly communicates its purpose, lists specific capabilities, and includes explicit trigger guidance. It covers natural user terms comprehensively and occupies a distinct niche that minimizes conflict with other skills. The description is well-structured, concise, and uses appropriate third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: search Google Scholar and PubMed, extract metadata, validate citations, generate BibTeX entries. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (search databases, extract metadata, validate citations, generate BibTeX) and 'when' with an explicit 'This skill should be used when...' clause listing specific trigger scenarios like finding papers, verifying citations, converting DOIs, and ensuring reference accuracy. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Google Scholar', 'PubMed', 'papers', 'citations', 'BibTeX', 'DOIs', 'reference', 'scientific writing', 'academic research'. Good coverage of terms across the citation management domain. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche around academic citation management with distinct triggers like 'BibTeX', 'DOIs', 'Google Scholar', 'PubMed', and 'citation validation'. Unlikely to conflict with general writing or document skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill demonstrates strong workflow clarity with well-sequenced phases and validation checkpoints, but is severely undermined by extreme verbosity and redundancy. Content is repeated across workflow descriptions, tool documentation, and example sections. The irrelevant 'Visual Enhancement with Scientific Schematics' section and explanations of concepts Claude already knows (venue tiers, what MeSH terms are, what DOIs are) waste significant token budget.
Suggestions
Cut the document by 60-70%: remove the 'Visual Enhancement with Scientific Schematics' section entirely, collapse the Tools section into a brief reference table since usage is already shown in workflows, and eliminate the redundant 'Best Practices' and 'Common Pitfalls' sections that repeat workflow guidance.
Move detailed content (PubMed field tags, Google Scholar operators, BibTeX entry type definitions, venue tier tables) into the referenced files (references/*.md) instead of duplicating them inline.
Remove explanatory content Claude already knows: what DOIs are, what MeSH terms do, what CrossRef is, citation count significance tables, and author reputation indicators.
Keep only one complete example workflow and make the others one-line references to example files, reducing the massive example section.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~600+ lines. Massive redundancy: every script's usage is documented 2-3 times (once in workflow, once in tools section, once in examples). The 'Visual Enhancement with Scientific Schematics' section is entirely irrelevant to citation management. Tables of citation thresholds, venue tiers, and author reputation indicators explain concepts Claude already knows. Best practices sections repeat obvious advice. | 1 / 3 |
Actionability | Provides concrete CLI commands and BibTeX examples that appear executable, but all scripts referenced (search_google_scholar.py, validate_citations.py, etc.) are assumed to exist without any indication they're bundled or how to obtain them. The commands are specific but may not correspond to real tools, making them potentially non-executable in practice. | 2 / 3 |
Workflow Clarity | The 5-phase workflow is clearly sequenced with explicit validation steps (Phase 4), feedback loops (auto-fix then re-validate), and the example workflows show numbered steps with validation checkpoints before final output. The 'Building a Bibliography' example explicitly includes validate-then-review steps. | 3 / 3 |
Progressive Disclosure | References to external files exist (references/google_scholar_search.md, references/pubmed_search.md, etc.) which is good, but the SKILL.md itself is a monolithic wall of text that inlines enormous amounts of detail that should be in those reference files. The tools section repeats what's already in the workflow section. Content that belongs in reference files is duplicated inline. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1114 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 9 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
25e1c0f
- 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.