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

73%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 delivers a well-sequenced, actionable workflow with real bundled scripts and explicit validation feedback loops. Its main weaknesses are redundancy (duplicated headers/sections and a restated summary) and inlined content that overlaps with existing reference files.

Suggestions

Remove the duplicate 'Screening and Selection' header at line 414 (its bullets copy 'Search Strategy') and merge into the single correct 'Screening and Selection' block at line 420.

Delete or drastically shrink the 'Summary' section (lines 566-578) since it restates the Overview, and trim the 'Example Workflow' to only the commands not already shown in the phase sections.

Move the bulk of the 'Database-Specific Search Guidance' (lines 261-343) into references/database_strategies.md and keep only a short pointer plus per-database one-liners in SKILL.md.

Dimension	Reasoning	Score
Conciseness	Mostly useful domain methodology, but contains clear redundancy: a duplicate 'Screening and Selection' header (lines 414 and 420) whose first instance verbatim copies the 'Search Strategy' bullets, a Summary section that restates the Overview, and an Example Workflow that repeats commands already shown in the phases.	3 / 5
Actionability	Provides concrete, executable invocations of the bundled scripts (verify_citations.py, generate_pdf.py, search_databases.py) with documented flags; minor gaps where 'pubmed search' and 'search biorxiv' are aspirational CLI calls rather than verified executable tools.	4 / 5
Workflow Clarity	A clear 7-phase sequence (Planning through Document Generation) with an explicit citation-verification feedback loop ('Re-run verification until all citations pass') and a Quality Checklist; validation is present so the destructive/batch cap does not apply.	5 / 5
Progressive Disclosure	Good structure with clearly signaled one-level-deep references (e.g., 'see references/citation_styles.md') and a Resources section listing all real bundle files; however, extensive database-specific guidance is inlined despite references/database_strategies.md existing as a separate file.	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 strong: it explicitly states both the capability (multi-database literature review with citation verification and PDF/markdown output) and a concrete 'should be used when' trigger clause, all in third person. Trigger term coverage is good but could add a few synonyms and file extensions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — searching multiple academic databases, creating markdown documents and PDFs, verifying citations, and formatting in multiple citation styles — with comprehensive coverage and no vague filler.	5 / 5
Completeness	Explicitly answers both 'what' ('Conduct comprehensive, systematic literature reviews... Creates professionally formatted markdown documents and 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	Strong natural keywords users would say ('systematic literature reviews', 'meta-analyses', 'research synthesis', 'comprehensive literature searches'), but missing common synonyms (e.g., 'scoping review', 'evidence synthesis') and file extensions (.bib, .ris).	4 / 5
Distinctiveness Conflict Risk	Clear niche (academic systematic literature reviews across named databases) with distinct triggers ('systematic literature review', 'meta-analysis', 'research synthesis') that are unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (579 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	14 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/literature-review/SKILL.md
Commit: d5ae560

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.