literature-review

Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).

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

67%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.

A well-structured, actionable skill body with a clear seven-phase workflow and genuine bundle references one level deep. Its main weakness is conciseness: a duplicated section header/bullets and a restating Summary add avoidable tokens.

Suggestions

Remove the duplicated 'Screening and Selection' block (lines ~104-108 repeat Search Strategy bullets) and merge the real screening guidance into a single section.

Trim or cut the Summary section, which restates points already made in Best Practices and Integration with Other Skills.

Show executable invocations for the core scripts (search_databases.py, verify_citations.py) with example arguments so the main workflow is fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concept over-explanation, but the 'Screening and Selection' header and several bullets are duplicated verbatim (Search Strategy bullets repeated), and the Summary section largely restates earlier content — more than minor padding.	3 / 5
Actionability	Provides copy-paste-ready commands (generate_schematic.py, install/deps, --check-deps) and names scripts, but the core search_databases.py and verify_citations.py invocations are referenced without shown arguments, leaving minor gaps.	4 / 5
Workflow Clarity	The seven-phase workflow is clearly sequenced with an explicit citation-verification checkpoint and reproducibility documentation, though error-recovery feedback loops (e.g., what to do when verification fails) are only implicit.	4 / 5
Progressive Disclosure	Clear overview with well-signaled, one-level-deep references to real bundle files (core_workflow.md, search_and_citation.md, example_workflow.md, citation_styles.md, scripts/*, assets/review_template.md), though lengthy inlined listings (Integration with Other Skills, venue styles) could live in a reference.	4 / 5
	Total	15 / 20 Passed

Description

100%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, third-person description that concretely states capabilities, names specific databases and citation styles, and provides an explicit 'use when' trigger clause covering multiple natural phrasings. It is comprehensive without being padded.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — multi-database searching (PubMed, arXiv, bioRxiv, Semantic Scholar), generating markdown/PDF documents, and verifying citations in multiple styles (APA, Nature, Vancouver) — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (conduct reviews across databases; produce markdown/PDFs with verified citations) and when ('This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis…') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers the natural phrases researchers actually say — 'systematic literature reviews', 'meta-analyses', 'research synthesis', 'comprehensive literature searches' — as synonyms/variations of the core intent.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (systematic academic literature review with verified citations across biomedical/scientific/technical domains) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	20 / 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/scientific-agent-skills
Path: skills/literature-review/SKILL.md
Commit: 49c6e97

Reviewed: 12 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.