literature-review

Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles.

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/literature-review/SKILL.md

Quality

Content

81%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 highly actionable, well-sequenced workflow with strong validation feedback loops and a verified bundle structure, held back from a top score by redundant inlined sections (Summary, Best Practices, Common Pitfalls) that pad the document and overlap the reference files.

Suggestions

Remove or aggressively trim the Summary, Best Practices, and Common Pitfalls sections, which restate content already in the 7-phase workflow.

De-duplicate the Citation Style Guide against references/citation_styles.md by keeping only a one-line pointer plus a single example inline.

Tighten the Visual Enhancement section by dropping promotional tool descriptions and keeping only the schematic-generation command and figure-type list.

Dimension	Reasoning	Score
Conciseness	Most sections are actionable and efficient, but several padded sections restate workflow content — the Summary recap, Best Practices, Common Pitfalls, and promotional phrasing in the Visual Enhancement section ('Nano Banana Pro will automatically generate, review, and refine') — so it could be tightened.	3 / 5
Actionability	Provides copy-paste-ready commands with full flags (e.g., 'python scripts/search_databases.py combined_results.json --deduplicate --format markdown --output aggregated_results.md', 'python scripts/verify_citations.py my_literature_review.md') plus concrete quality tools (Cochrane, Newcastle-Ottawa, AMSTAR 2) covering the common cases.	5 / 5
Workflow Clarity	The 7-phase workflow is clearly sequenced with explicit validation checkpoints (database-failure handling, citation re-verification), a feedback loop ('Re-run verification until all citations pass'), and a final Quality Checklist.	5 / 5
Progressive Disclosure	References are real, well-signaled, and one level deep (references/citation_styles.md, references/database_strategies.md, scripts/*.py, assets/review_template.md all exist and are linked), but the ~600-line SKILL.md inlines content that overlaps the reference files (Citation Style Guide duplicates citation_styles.md) and includes redundant recap sections.	4 / 5
	Total	17 / 20 Passed

Description

78%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, specific description with excellent trigger-term coverage and a clear niche, weakened only by the absence of an explicit 'Use when' trigger clause, which caps completeness at 3.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers (e.g., 'Use when conducting a systematic, scoping, or meta-analytic literature review across multiple databases, or when generating a citation-verified review document').

Include review-type synonyms (meta-analysis, scoping review) in the description to broaden natural trigger coverage.

Clarify the boundary from citation-formatting-only tasks to reduce overlap with reference-style skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the skill's scope — 'Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.)', 'Creates professionally formatted markdown documents and PDFs', and 'verified citations in multiple citation styles' — with named databases and output formats giving comprehensive coverage.	5 / 5
Completeness	The 'what' is clear (multi-database literature reviews producing markdown/PDFs with verified citations), but there is no 'Use when...' clause or equivalent explicit trigger guidance, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	Includes natural terms users would say ('literature reviews', 'systematic') plus comprehensive synonyms/alternatives via named databases (PubMed, arXiv, bioRxiv, Semantic Scholar) and format types (markdown, PDFs, citations, citation styles).	5 / 5
Distinctiveness Conflict Risk	The 'systematic literature reviews' niche with named academic databases is mostly distinct, but 'verified citations in multiple citation styles' creates minor overlap risk with citation-management/reference-style skills.	4 / 5
	Total	17 / 20 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 (612 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Academic Writing/literature-review/SKILL.md
Commit: 63c61d3

Reviewed: 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.