CtrlK
BlogDocsLog inGet started
Tessl Logo

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.).

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 executable commands and real validation feedback loops. Its weaknesses are token efficiency and progressive disclosure: the body is long and redundant, explains some basic concepts, and duplicates content that already exists in the bundled reference files.

Suggestions

Remove the duplicated '### Screening and Selection' header (the section appears twice) and drop or merge the Summary/Best Practices sections, which restate the Core Workflow phases.

Move the inline Citation Style Guide and Database-Specific Search Guidance sections into references/citation_styles.md and references/database_strategies.md, leaving only a one-line pointer plus a quick reference, so the body stops duplicating the bundled references.

Cut basic-concept explanations Claude already knows (e.g., 'Preprints are not peer-reviewed', 'Boolean operators: AND, OR, NOT') to tighten the token budget.

DimensionReasoningScore

Conciseness

Mostly actionable but padded with redundancy (duplicated '### Screening and Selection' headers, a Summary restating earlier phases, Best Practices overlapping the Core Workflow) and minor over-explanation of concepts Claude knows ('Preprints are not peer-reviewed', 'Boolean operators: AND, OR, NOT'), so it could be tightened rather than earning the lean score-3.

2 / 3

Actionability

Provides fully executable, copy-paste-ready commands throughout — `parallel-cli search ... --include-domains ...`, `python scripts/verify_citations.py`, `cp assets/review_template.md`, `gget search pubmed ...` — with specific flags and example query strings, matching the score-3 anchor.

3 / 3

Workflow Clarity

A clearly sequenced seven-phase workflow with explicit validation checkpoints — the citation-verification feedback loop ('Correct any errors... Re-run verification until all citations pass') and a final Quality Checklist — satisfying the destructive/batch requirement rather than being capped at 2.

3 / 3

Progressive Disclosure

References to bundled files are real and clearly signaled ('Detailed formatting guidelines are in references/citation_styles.md'), but the ~700-line body is monolithic with inline content that should live in those references — the Citation Style Guide and Database-Specific Search Guidance sections duplicate references/citation_styles.md and references/database_strategies.md rather than being appropriately split.

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.

A strong, third-person description that clearly states capabilities, names concrete databases and output formats, and provides an explicit 'should be used when' trigger clause covering natural review-related terms. It answers what, when, and how with minimal fluff and low conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Conduct comprehensive, systematic literature reviews', 'Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles') and names specific databases (PubMed, arXiv, bioRxiv, Semantic Scholar), matching the score-3 anchor of multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers both what ('Conduct... literature reviews', 'Creates... documents and PDFs with verified citations') and when ('This skill should be used when conducting systematic literature reviews, meta-analyses...'), satisfying the explicit-trigger requirement to avoid the completeness cap of 2.

3 / 3

Trigger Term Quality

Covers natural terms users would actually say — 'systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches' — plus common database names, giving good coverage of natural trigger language rather than jargon.

3 / 3

Distinctiveness Conflict Risk

The niche — systematic academic literature reviews across named databases with citation verification — is distinct with clear triggers and is unlikely to fire for unrelated skills.

3 / 3

Total

12

/

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.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (711 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
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.