Literature Survey
Autonomous literature survey engine. Five research paradigms, each a self-contained playbook with quantitative budget enforcement. You provide a research question — it searches, screens, reads, categorizes, identifies gaps, and produces a structured survey output.
Strategy Routing
| Signal |
Strategy |
| panoramic mapping of a new field, broad overview, field mapping |
→ scoping-survey |
| exhaustive coverage, PRISMA, systematic review |
→ systematic-survey |
| precise sub-question, specific mechanism, deep dive |
→ deep-survey |
| theory-driven, argument building, narrative |
→ narrative-review |
| seed papers, citation chain, lineage tracing |
→ snowball |
Manifest
Strategies (5)
- scoping-survey
- systematic-survey
- deep-survey
- narrative-review
- snowball
Tactics (3)
- prisma-screening
- citation-chaining (shared: patent-mining, baseline-establishment)
- narrative-framing
Subagent SOPs (11)
- survey-synthesis
- define-search-protocol
- categorize-papers (shared: meta-analysis, baseline-establishment)
- extract-data
- quality-assessment
- seed-selection
- saturation-detection (shared: patent-mining, benchmark-archaeology)
- taxonomy-mapping
- prisma-flowchart
- thematic-coding
- gap-identification (shared: benchmark-archaeology, baseline-establishment)
Import SOPs (5, shared across all campaigns)
- web-search
- web-research
- paper-overview
- paper-search
- paper-research
Budget Table
| Strategy |
web-search |
web-research |
paper-overview |
paper-search |
paper-research |
| scoping-survey |
100 |
10 |
100 |
20 |
0 |
| systematic-survey |
50 |
5 |
60 |
40 |
30 |
| deep-survey |
30 |
5 |
40 |
40 |
20 |
| narrative-review |
80 |
15 |
50 |
40 |
20 |
| snowball |
20 |
3 |
30 |
30 |
20 |
All values ±10% flexibility. Deviations require explicit reasoning.
MCP Tools
| MCP Server |
Tools |
| brave-search |
brave_web_search, brave_news_search, brave_llm_context |
| apify |
rag-web-browser, google-scholar-scraper |
| alphaxiv |
discover_papers, get_paper_content, answer_pdf_queries, read_files_from_github_repository |
| semantic-scholar |
ss_paper, ss_paper_batch, ss_references, ss_citations, ss_recommendations, ss_relevance_search, ss_author, ss_author_papers |
Context Management
- Campaign start: context-init
- After each strategy completes: context-checkpoint (append to literature-survey context file)
Available Strategies
Optional, no fixed order; the final leaf is always a sop.
| Strategy |
When to use |
| deep-survey |
Precise, targeted investigation of a specific sub-problem — few papers, all read in full depth. High paper-research ratio (50% deep-read rate). Use when the user knows exactly what they need to understand and requires detailed technical analysis with equations, hyperparameters, and specific claims extracted. |
| narrative-review |
Theory-driven literature review for building arguments and frameworks. Flexible, subjective, and narrative-focused — selects evidence strategically to support a thesis. High web-research budget for blogs, opinion pieces, and industry perspectives. Use when the user is writing a position paper, survey introduction, or constructing a coherent narrative around a research theme. |
| scoping-survey |
Broad landscape mapping strategy — quickly understand what exists in a field. Prioritizes breadth over depth with high paper-overview volume and minimal deep reading. Use when entering a new field or needing orientation before committing to deeper investigation. |
| snowball |
Citation-chain-driven literature survey starting from seed papers. Traces research lineage in both forward (who cited this) and backward (what this cited) directions until saturation. High deep-read ratio (67%). Use when the user already has key papers and wants to find everything connected to them — ancestors, descendants, and branch points. |
| systematic-survey |
Exhaustive PRISMA-style literature survey — comprehensive coverage of all related work on a specific question. Multi-stage screening, citation chaining, quality assessment, and structured data extraction. Use when the user needs to demonstrate complete literature coverage or conduct rigorous gap analysis. |
Available SOPs
Optional, no fixed order; the final leaf is always a sop.
| SOP |
When to use |
| context-checkpoint |
Append research process and results to the current Phase's context file. Covers both process and results with genuine substance. Use this skill at plan-designated checkpoint points — typically after each strategy completes or at key decision nodes within a research Phase. |
| context-init |
Create a new context file for a research Phase. Called once at Phase start to initialize the file that subsequent context-checkpoint calls will append to. Use this skill whenever a new research Phase begins and a fresh context file is needed. |
1---2name: literature-survey3description: Autonomous Literature Survey Campaign — 5 research paradigms (scoping, systematic, deep, narrative, snowball) with quantitative budget enforcement. Selects and executes the right survey paradigm based on research intent.4---56# Literature Survey78Autonomous literature survey engine. Five research paradigms, each a self-contained playbook with quantitative budget enforcement. You provide a research question — it searches, screens, reads, categorizes, identifies gaps, and produces a structured survey output.910## Strategy Routing1112| Signal | Strategy |13|--------|----------|14| panoramic mapping of a new field, broad overview, field mapping | → scoping-survey |15| exhaustive coverage, PRISMA, systematic review | → systematic-survey |16| precise sub-question, specific mechanism, deep dive | → deep-survey |17| theory-driven, argument building, narrative | → narrative-review |18| seed papers, citation chain, lineage tracing | → snowball |1920## Manifest2122### Strategies (5)23- scoping-survey24- systematic-survey25- deep-survey26- narrative-review27- snowball2829### Tactics (3)30- prisma-screening31- citation-chaining (shared: patent-mining, baseline-establishment)32- narrative-framing3334### Subagent SOPs (11)35- survey-synthesis36- define-search-protocol37- categorize-papers (shared: meta-analysis, baseline-establishment)38- extract-data39- quality-assessment40- seed-selection41- saturation-detection (shared: patent-mining, benchmark-archaeology)42- taxonomy-mapping43- prisma-flowchart44- thematic-coding45- gap-identification (shared: benchmark-archaeology, baseline-establishment)4647### Import SOPs (5, shared across all campaigns)48- web-search49- web-research50- paper-overview51- paper-search52- paper-research5354## Budget Table5556| Strategy | web-search | web-research | paper-overview | paper-search | paper-research |57|----------|-----------|-------------|---------------|-------------|---------------|58| scoping-survey | 100 | 10 | 100 | 20 | 0 |59| systematic-survey | 50 | 5 | 60 | 40 | 30 |60| deep-survey | 30 | 5 | 40 | 40 | 20 |61| narrative-review | 80 | 15 | 50 | 40 | 20 |62| snowball | 20 | 3 | 30 | 30 | 20 |6364All values ±10% flexibility. Deviations require explicit reasoning.6566## MCP Tools6768| MCP Server | Tools |69|------------|-------|70| brave-search | brave_web_search, brave_news_search, brave_llm_context |71| apify | rag-web-browser, google-scholar-scraper |72| alphaxiv | discover_papers, get_paper_content, answer_pdf_queries, read_files_from_github_repository |73| semantic-scholar | ss_paper, ss_paper_batch, ss_references, ss_citations, ss_recommendations, ss_relevance_search, ss_author, ss_author_papers |7475## Context Management7677- Campaign start: context-init78- After each strategy completes: context-checkpoint (append to literature-survey context file)7980<!-- BEGIN available-tables (generated) -->8182## Available Strategies8384Optional, no fixed order; the final leaf is always a sop.8586| Strategy | When to use |87| --- | --- |88| deep-survey | Precise, targeted investigation of a specific sub-problem — few papers, all read in full depth. High paper-research ratio (50% deep-read rate). Use when the user knows exactly what they need to understand and requires detailed technical analysis with equations, hyperparameters, and specific claims extracted. |89| narrative-review | Theory-driven literature review for building arguments and frameworks. Flexible, subjective, and narrative-focused — selects evidence strategically to support a thesis. High web-research budget for blogs, opinion pieces, and industry perspectives. Use when the user is writing a position paper, survey introduction, or constructing a coherent narrative around a research theme. |90| scoping-survey | Broad landscape mapping strategy — quickly understand what exists in a field. Prioritizes breadth over depth with high paper-overview volume and minimal deep reading. Use when entering a new field or needing orientation before committing to deeper investigation. |91| snowball | Citation-chain-driven literature survey starting from seed papers. Traces research lineage in both forward (who cited this) and backward (what this cited) directions until saturation. High deep-read ratio (67%). Use when the user already has key papers and wants to find everything connected to them — ancestors, descendants, and branch points. |92| systematic-survey | Exhaustive PRISMA-style literature survey — comprehensive coverage of all related work on a specific question. Multi-stage screening, citation chaining, quality assessment, and structured data extraction. Use when the user needs to demonstrate complete literature coverage or conduct rigorous gap analysis. |9394## Available SOPs9596Optional, no fixed order; the final leaf is always a sop.9798| SOP | When to use |99| --- | --- |100| context-checkpoint | Append research process and results to the current Phase's context file. Covers both process and results with genuine substance. Use this skill at plan-designated checkpoint points — typically after each strategy completes or at key decision nodes within a research Phase. |101| context-init | Create a new context file for a research Phase. Called once at Phase start to initialize the file that subsequent context-checkpoint calls will append to. Use this skill whenever a new research Phase begins and a fresh context file is needed. |102103<!-- END available-tables (generated) -->
yogsoth-ai