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%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear sequenced workflow and explicit error-recovery checkpoints, but it is slightly verbose in places and references template files that are missing from the bundle.

Suggestions

Add the referenced templates/apa.md, templates/ieee.md, and templates/bibtex.md to the bundle, or remove the links and inline the citation rules, so progressive disclosure navigation is not broken.

Collapse the repeated Phase 3 subagent rationale and the Notes section restating the subagent_enabled prerequisite into a single statement to reduce redundancy.

Trim the repeated emphasis on batching/concurrency rules in Phase 3 (stated in prose, table, and Notes) to a single canonical explanation.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands and decision tables, but the Phase 3 rationale is restated across multiple sections and the Notes repeat the subagent-enabled prerequisite already explained in the workflow, so it could be tightened.	2 / 3
Actionability	Provides an executable arxiv_search.py invocation, an exact subagent prompt template, a batch/round decision table, and a precise output filename convention — fully copy-paste ready.	3 / 3
Workflow Clarity	Five phases are clearly sequenced with explicit validation checkpoints and feedback loops: script-failure handling, bad-batch recovery ('log it, note which papers, continue'), and 'tell the user and stop' guardrails.	3 / 3
Progressive Disclosure	References to templates/apa.md, templates/ieee.md, and templates/bibtex.md are well-signaled and one level deep, but those files do not exist in the bundle, so the referenced navigation paths are broken.	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 concise, specific, and uses third-person voice with concrete actions and natural trigger terms. It clearly answers both what and when, and explicitly distinguishes itself from the single-paper review skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'systematic literature review, survey, or synthesis', 'annotated bibliographies', 'cross-paper comparisons', 'Searches arXiv', 'outputs reports in APA, IEEE, or BibTeX format' — matching the top anchor.	3 / 3
Completeness	Explicitly answers both what (SLR across papers via arXiv with formatted output) and when ('Use this skill when the user wants...'), plus a negative boundary for single-paper tasks.	3 / 3
Trigger Term Quality	Uses natural user-facing terms ('literature review', 'survey', 'synthesis', 'annotated bibliographies', 'cross-paper comparisons') that a user would actually say when needing this skill.	3 / 3
Distinctiveness Conflict Risk	Clear niche with explicit routing to 'academic-paper-review' for single-paper tasks and a distinct scope from generic web research, so it is unlikely to trigger for the wrong skill.	3 / 3
	Total	12 / 12 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: cd9432b

Reviewed: about 13 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.