systematic-literature-review

Use this skill when the user wants a systematic literature review, survey, or synthesis across multiple academic papers on a topic. Also covers annotated bibliographies and cross-paper comparisons. Searches arXiv and outputs reports in APA, IEEE, or BibTeX format. Not for single-paper tasks — use academic-paper-review for reviewing one paper.

Quality

88%

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

77%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, highly actionable multi-phase workflow with strong validation checkpoints, undermined by two issues: redundant restatement of the subagent guidance inflates token cost, and the three citation templates referenced in Phase 4 are not present in the bundle, breaking progressive disclosure.

Suggestions

Add the missing templates/apa.md, templates/ieee.md, and templates/bibtex.md files to the bundle so the Phase 4 references resolve; the skill currently instructs Claude to read files that do not exist.

Collapse the three bottom Notes items about subagent_enabled / the task tool / string-prefix parsing into a single pointer, since each is already covered inline in Phase 3 — this trims the conciseness gap.

Tighten the query-phrasing section by leading with the decision table and cutting the surrounding prose that re-derives why phrase matching fails on long queries.

Dimension	Reasoning	Score
Conciseness	The core workflow is efficient, but several sections are padded: the Phase 3 subagent/concurrency guidance is restated across three separate Notes items at the bottom, and the query-phrasing and round-strategy material is over-explained relative to what Claude needs.	3 / 5
Actionability	Provides copy-paste-ready execution: an exact arxiv_search.py invocation with every flag, a complete subagent prompt template, a precise batching decision table, filename templates, and the present_files call — covering the common cases fully.	5 / 5
Workflow Clarity	Five clearly sequenced phases with explicit validation and error-recovery checkpoints at every fragile point (one clarifying question, run search once, script-failure stop, prefix-stripping, batch-failure tolerance, synthesis-not-listing guard) — robust feedback loops for this batch operation.	5 / 5
Progressive Disclosure	Top-level structure is good and the arXiv mechanics are correctly offloaded to a real bundled script, but the referenced templates/apa.md, templates/ieee.md, and templates/bibtex.md do not exist in the bundle, so the report-structure content that should live one level deep is missing rather than appropriately split.	3 / 5
	Total	16 / 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.

The description is a strong example: it states concrete capabilities, includes natural trigger terms with synonyms, answers both what and when explicitly, and disambiguates from a sibling skill via a negative trigger. No meaningful gaps to penalize.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Searches arXiv', 'outputs reports in APA, IEEE, or BibTeX format', 'systematic literature review, survey, or synthesis', 'annotated bibliographies and cross-paper comparisons' — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (searches arXiv, synthesizes across papers, outputs formatted reports) and 'when' via a clear 'Use this skill when the user wants...' trigger clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage with synonyms users actually say — 'literature review, survey, or synthesis', 'annotated bibliographies', 'cross-paper comparisons', and the three citation format names.	5 / 5
Distinctiveness Conflict Risk	Carves a clear niche with an explicit negative trigger — 'Not for single-paper tasks — use academic-paper-review for reviewing one paper' — minimizing conflict risk with the adjacent single-paper skill.	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
relative_links	Relative link issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: bytedance/deer-flow
Path: skills/public/systematic-literature-review/SKILL.md
Commit: 2a261d2

Reviewed: about 18 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.