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.

The skill is highly actionable with a clear, well-validated multi-phase workflow, but it is overlong and repetitive, with inline detail that overlaps bundled reference files rather than being deferred to them.

Suggestions

Collapse the duplicated '### Screening and Selection' section (Best Practices) and remove search-guidance repetition across Phase 2, Best Practices, and Integration to tighten conciseness.

Move the inline Citation Style Guide and Database-Specific Search Guidance into the existing references/citation_styles.md and references/database_strategies.md, leaving only a one-line pointer plus quick reference in SKILL.md.

Drop the closing Summary section, which restates the Overview and Resources already covered, to recover token budget.

DimensionReasoningScore

Conciseness

The ~700-line body is mostly actionable but padded: two duplicate '### Screening and Selection' headers appear, search guidance is repeated across Phase 2, Database-Specific, Best Practices, Example Workflow, and Integration, and the closing Summary restates the Overview.

2 / 3

Actionability

Provides fully executable, copy-paste-ready commands throughout — `parallel-cli search`/`extract` invocations, `python scripts/verify_citations.py`, `generate_pdf.py`, `search_databases.py` — with concrete flags and example query strings.

3 / 3

Workflow Clarity

Seven phases are numbered and explicitly sequenced with validation checkpoints, including the citation-verification feedback loop ('Re-run verification until all citations pass') and a final quality checklist covering destructive/batch output.

3 / 3

Progressive Disclosure

References are real and clearly signaled one level deep (references/citation_styles.md, references/database_strategies.md, assets/review_template.md), but substantial inline content (the Citation Style Guide and Database-Specific Search Guidance sections) duplicates material that already lives in those reference files.

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.

The description is specific, uses third person, and explicitly states both capabilities and trigger conditions with natural user phrasings. It is concise yet comprehensive, hitting every dimension at the top of the scale.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'Conduct comprehensive, systematic literature reviews using multiple academic databases' and 'Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles' — matching the score-3 anchor listing several specific actions.

3 / 3

Completeness

Explicitly answers both what (conduct reviews, generate formatted docs/PDFs with verified citations) and when via the explicit 'This skill should be used when...' trigger clause, matching the score-3 anchor.

3 / 3

Trigger Term Quality

Covers natural terms users would say — 'literature reviews', 'meta-analyses', 'research synthesis', 'comprehensive literature searches', 'citations' — giving good breadth of common phrasings.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (systematic literature reviews with citation verification and PDF generation) with distinct triggers and third-person voice, making conflict with other skills unlikely.

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 (707 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/claude-scientific-writer
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.