Source profileQuality 87/100

LazyAGI/LazyMind/skills/review/systematic-document-and-literature-review/SKILL.md

systematic-document-and-literature-review

Use this skill when the user wants a systematic review, thematic synthesis, or cross-document analysis across multiple academic papers OR provided general documents (reports, internal memos, web articles). Retrieves sources via arXiv, internal Knowledge Base (KB), or direct URLs. Analyzes the content within the current context and outputs a fully structured synthesis report directly in the chat.

Source repository stars
55
Declared platforms
0
Static risk flags
1
Last source update
2026-07-28
Source checked
2026-07-28

Decision brief

What it does—and where it fits

Retrieves sources via arXiv, internal Knowledge Base (KB), or direct URLs. Analyzes the content within the current context and outputs a fully structured synthesis report directly in the chat.

Best for

  • A literature survey on an academic topic ("survey transformer attention variants")
  • A thematic synthesis across internal documents ("synthesize the last 5 quarterly reports from the KB and find common trends")
  • A cross-document comparison ("compare the methodologies across these provided architecture design URLs")

Not for

  • Tasks that require unconfirmed production actions or broad system permissions.
  • Environments where the pinned source and install steps cannot be inspected.

Compatibility matrix

Platform support, with evidence labels

PlatformStatusEvidenceWhat to check
CodexNot declaredNo explicit evidencePortability before use
Claude CodeNot declaredNo explicit evidencePortability before use
CursorNot declaredNo explicit evidencePortability before use
Gemini CLINot declaredNo explicit evidencePortability before use
Open the compatibility checker

Installation

Inspect first. Install second.

The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.

Source-detected install commandSource
npx skills add https://github.com/LazyAGI/LazyMind --skill "skills/review/systematic-document-and-literature-review"
Safe inspection promptEditorial

Inspect the Agent Skill "systematic-document-and-literature-review" from https://github.com/LazyAGI/LazyMind/blob/b63cc44f8c68603bc9e802b56d8e243fef2481aa/skills/review/systematic-document-and-literature-review/SKILL.md at commit b63cc44f8c68603bc9e802b56d8e243fef2481aa. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.

Workflow

What the source asks the agent to do

  1. 01

    Workflow

    The workflow has four phases. Follow them in order.

    Source Material: Are we searching an academic database (arxivsearch), an internal Knowledge Base (kbsearch), or reviewing specific URLs (urlfetch)?Scope: How many sources total? (Limit to max 15-20 sources to prevent context overflow).Output Format: APA, IEEE, BibTeX, or Standard Professional Report (default for non-academic documents).
  2. 02

    Phase 1: Plan

    Before doing any retrieval, confirm the following with the user. If any of these are unclear, ask one clarifying question that covers the missing pieces.

    Source Material: Are we searching an academic database (arxivsearch), an internal Knowledge Base (kbsearch), or reviewing specific URLs (urlfetch)?Scope: How many sources total? (Limit to max 15-20 sources to prevent context overflow).Output Format: APA, IEEE, BibTeX, or Standard Professional Report (default for non-academic documents).
  3. 03

    Phase 2: Acquire Sources

    Depending on the Source Material established in Phase 1, follow the appropriate acquisition path:

    Extract 2-3 core keywords from the user's prompt. Do not use overly long phrases.Use relevance sorting unless chronological order is strictly requested.Gather the returned nodes. If context is missing, use kbgetwindownodes or kbgetparentnode to ensure sufficient text for the subagents.
  4. 04

    Phase 3: Analyze & Synthesize (Internal Processing)

    Once you have ingested the source texts into your context, carefully analyze them. You must mentally or explicitly (in your thinking process) extract the following for each source: - Primary objective - Approach or methodology - Key findings - Limitations or next steps

    Primary objectiveApproach or methodologyKey findings
  5. 05

    Phase 4: Output Final Report

    Do not attempt to save to a file. Directly output the final synthesized report in the chat. Use markdown formatting. If the user requested a Standard Professional Report, strictly use the following structure:

    Do not attempt to save to a file. Directly output the final synthesized report in the chat. Use markdown formatting. If the user requested a Standard Professional Report, strictly use the following structure:

Permission review

Static risk signals and limitations

Writes files

medium · line 69

The documentation asks the agent to create, modify, or delete local files.

Do not attempt to save to a file. **Directly output the final synthesized report in the chat.** Use markdown formatting. If the user requested a Standard Professional Report, strictly use the following structure:

Evidence record

Why each signal appears

EvidenceSourceComputedTestedEditorial
SignalValueEvidence typeMeaning
Quality score87/100ComputedDocumentation, specificity, maintenance, and trust rules
Repository stars55SourceRepository attention, not individual Skill quality
Compatibility0 platformsSourceDeclared in the catalog source record
Usage guideautomated source guideEditorialGenerated or reviewed according to the visible evidence level

Pinned source

Provenance and original SKILL.md

Repository
LazyAGI/LazyMind
Skill path
skills/review/systematic-document-and-literature-review/SKILL.md
Commit
b63cc44f8c68603bc9e802b56d8e243fef2481aa
License
Apache-2.0
Collected
2026-07-28
Default branch
main
View the original SKILL.md

Systematic Document & Literature Review Skill

Overview

This skill produces a structured systematic review and synthesis across multiple academic papers or general documents. Given a topic query or a list of specific files/URLs, it gathers the source material, analyzes the content (objectives, methodology, key findings, limitations) sequentially, synthesizes themes, and outputs a final structured report directly to the user.

Distinct from single-document review: This skill does breadth-first synthesis across many sources. If the user hands you exactly one document or one paper URL and asks "review this", route to a standard reading or single-document review skill instead.

When to Use This Skill

Use this skill when the user wants any of the following:

  • A literature survey on an academic topic ("survey transformer attention variants")
  • A thematic synthesis across internal documents ("synthesize the last 5 quarterly reports from the KB and find common trends")
  • A cross-document comparison ("compare the methodologies across these provided architecture design URLs")
  • An overview of trends across a set of files, URLs, or an arXiv time window

Do not use this skill when:

  • The user provides exactly one document/paper and asks to review it.
  • The user asks a factual question that does not require synthesizing multiple sources.

Workflow

The workflow has four phases. Follow them in order.

Phase 1: Plan

Before doing any retrieval, confirm the following with the user. If any of these are unclear, ask one clarifying question that covers the missing pieces.

  • Source Material: Are we searching an academic database (arxiv_search), an internal Knowledge Base (kb_search), or reviewing specific URLs (url_fetch)?
  • Scope: How many sources total? (Limit to max 15-20 sources to prevent context overflow).
  • Output Format: APA, IEEE, BibTeX, or Standard Professional Report (default for non-academic documents).

Phase 2: Acquire Sources

Depending on the Source Material established in Phase 1, follow the appropriate acquisition path:

Path A: Academic Literature (arXiv)

Use the native arxiv_search tool.

  • Extract 2-3 core keywords from the user's prompt. Do not use overly long phrases.
  • Use relevance sorting unless chronological order is strictly requested.

Path B: Internal Documents (Knowledge Base)

Use kb_search or kb_keyword_search to find relevant internal documents.

  • Gather the returned nodes. If context is missing, use kb_get_window_nodes or kb_get_parent_node to ensure sufficient text for the subagents.

Path C: Provided URLs

If the user provides a list of links or file paths:

  • Verify the list (cap at 50).
  • Use url_fetch (for web links) to ingest the content.

Phase 3: Analyze & Synthesize (Internal Processing)

Once you have ingested the source texts into your context, carefully analyze them. You must mentally or explicitly (in your thinking process) extract the following for each source:

  • Primary objective
  • Approach or methodology
  • Key findings
  • Limitations or next steps

Cross-source synthesis: Then, look across all analyzed sources to identify:

  • Themes: 3-5 recurring directions, topics, or problem framings.
  • Convergences: Findings or arguments that multiple documents agree on.
  • Disagreements: Where sources reach different conclusions.
  • Gaps: What the collective set of documents does not address.

Phase 4: Output Final Report

Do not attempt to save to a file. Directly output the final synthesized report in the chat. Use markdown formatting. If the user requested a Standard Professional Report, strictly use the following structure:

# Systematic Review: [Topic Name]

## 1. Executive Summary
[A high-level 3-5 sentence summary of the entire review, highlighting the most critical insights.]

## 2. Thematic Synthesis
### Themes
- **[Theme 1]**: [Explanation based on sources]
- **[Theme 2]**: [Explanation based on sources]
### Convergences & Disagreements
[Where do the documents align? Where do they conflict?]
### Knowledge Gaps
[What is missing from the current literature/documents?]

## 3. Source Annotations
[Briefly list each analyzed source with its core objective and key finding. E.g.:]
* **[Source Title/ID]**: [1-sentence objective]. Key finding: [1-2 sentences].

## 4. References / Analyzed Sources
[List of all URLs, arXiv IDs, or document names analyzed.]

If the user requested APA/IEEE format, adjust the formatting and citation style accordingly.

Alternatives

Compare before choosing