Knowledge Acquisition
Systematic research knowledge acquisition engine. Five campaigns, each a self-contained autonomous research activity domain. You provide a research intent — the engine routes to the right campaign, selects a strategy, and executes autonomously with quantitative budget enforcement.
Pre-condition
North-star-crystallization must be complete before entering any campaign. Research intent must be fully crystallized.
Four-Level Hierarchy
ENTRY.md (this file)
→ Campaign (5): self-contained research activity domain
→ Strategy: selected by analysis purpose/intent
→ Tactic: multi-step orchestration pattern (reusable across strategies)
→ SOP: single operation (import or subagent)
Campaign Routing
| Signal |
Campaign |
| literature review, survey, paper search, PRISMA, snowball |
→ literature-survey |
| patent analysis, prior art, white space, claims, IPC |
→ patent-mining |
| benchmark analysis, evaluation methods, metric flaws, leaderboards, saturation |
→ benchmark-archaeology |
| cross-study statistical synthesis, effect size, heterogeneity, publication bias, GRADE |
→ meta-analysis |
| SOTA compilation, performance comparison, baseline reproduction, progress curves |
→ baseline-establishment |
Multi-Campaign Orchestration
Campaigns can be composed:
- Serial: literature-survey → baseline-establishment (survey first, then collect performance data)
- Parallel: patent-mining ∥ benchmark-archaeology (independent analyses on the same topic)
- Conditional: literature-survey → IF gaps found → meta-analysis (evidence synthesis on identified gaps)
The orchestrator decides composition based on the crystallized North Star statement.
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 Integration
- Campaign start: context-init (load/create campaign context file)
- After each strategy completes: context-checkpoint (append findings to campaign context file)
- One context file per campaign: all strategy outputs accumulate in a single campaign-scoped file
Dependencies
| Dependency |
What It Provides |
| web-browsing |
web-search + web-research |
| literature-engine |
literature-overview + literature-search + literature-research |
| subagent-spawning |
Subagent dispatch conventions |
| context-management |
Checkpoint protocol |
Available Campaigns
Optional, no fixed order; the final leaf is always a sop.
| Campaign |
When to use |
| baseline-establishment |
SOTA Performance Baseline Campaign — 5 strategies for systematically collecting, standardizing, and analyzing performance data across methods. Produces standardized comparison tables, progress curves, and headroom analysis. |
| benchmark-archaeology |
Evaluation Methodology Archaeology Campaign — 5 strategies for systematic analysis of AI/ML benchmarks, metrics, and leaderboards. Reveals construct validity issues, saturation, data contamination, and evaluation protocol inconsistencies. |
| literature-survey |
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. |
| meta-analysis |
Cross-Study Statistical Synthesis Campaign — 5 strategies for systematic collection and methodological planning of multi-study evidence synthesis. Covers pairwise, network, cumulative meta-analysis, heterogeneity investigation, and bias detection. Stops at protocol design (no computation). |
| patent-mining |
Systematic Patent Analysis Campaign — 5 strategies for patent landscape analysis, prior art search, white space identification, competitive intelligence, and claim analysis. Produces structured patent intelligence reports. |
1---2name: knowledge-acquisition3description: Research Knowledge Acquisition Engine with 5 campaigns (literature-survey, patent-mining, benchmark-archaeology, meta-analysis, baseline-establishment). Use this skill whenever a user needs to systematically acquire research knowledge — academic literature, patent landscapes, benchmark evaluations, cross-study statistical synthesis, or SOTA performance baselines. Pre-condition: north-star-crystallization must be complete.4---56# Knowledge Acquisition78Systematic research knowledge acquisition engine. Five campaigns, each a self-contained autonomous research activity domain. You provide a research intent — the engine routes to the right campaign, selects a strategy, and executes autonomously with quantitative budget enforcement.910## Pre-condition1112North-star-crystallization must be complete before entering any campaign. Research intent must be fully crystallized.1314## Four-Level Hierarchy1516```17ENTRY.md (this file)18 → Campaign (5): self-contained research activity domain19 → Strategy: selected by analysis purpose/intent20 → Tactic: multi-step orchestration pattern (reusable across strategies)21 → SOP: single operation (import or subagent)22```2324## Campaign Routing2526| Signal | Campaign |27|--------|----------|28| literature review, survey, paper search, PRISMA, snowball | → literature-survey |29| patent analysis, prior art, white space, claims, IPC | → patent-mining |30| benchmark analysis, evaluation methods, metric flaws, leaderboards, saturation | → benchmark-archaeology |31| cross-study statistical synthesis, effect size, heterogeneity, publication bias, GRADE | → meta-analysis |32| SOTA compilation, performance comparison, baseline reproduction, progress curves | → baseline-establishment |3334## Multi-Campaign Orchestration3536Campaigns can be composed:37- **Serial**: literature-survey → baseline-establishment (survey first, then collect performance data)38- **Parallel**: patent-mining ∥ benchmark-archaeology (independent analyses on the same topic)39- **Conditional**: literature-survey → IF gaps found → meta-analysis (evidence synthesis on identified gaps)4041The orchestrator decides composition based on the crystallized North Star statement.4243## MCP Tools4445| MCP Server | Tools |46|------------|-------|47| brave-search | brave_web_search, brave_news_search, brave_llm_context |48| apify | rag-web-browser, google-scholar-scraper |49| alphaxiv | discover_papers, get_paper_content, answer_pdf_queries, read_files_from_github_repository |50| semantic-scholar | ss_paper, ss_paper_batch, ss_references, ss_citations, ss_recommendations, ss_relevance_search, ss_author, ss_author_papers |5152## Context Management Integration5354- **Campaign start**: context-init (load/create campaign context file)55- **After each strategy completes**: context-checkpoint (append findings to campaign context file)56- **One context file per campaign**: all strategy outputs accumulate in a single campaign-scoped file5758## Dependencies5960| Dependency | What It Provides |61|-----------|-----------------|62| web-browsing | web-search + web-research |63| literature-engine | literature-overview + literature-search + literature-research |64| subagent-spawning | Subagent dispatch conventions |65| context-management | Checkpoint protocol |6667<!-- BEGIN available-tables (generated) -->6869## Available Campaigns7071Optional, no fixed order; the final leaf is always a sop.7273| Campaign | When to use |74| --- | --- |75| baseline-establishment | SOTA Performance Baseline Campaign — 5 strategies for systematically collecting, standardizing, and analyzing performance data across methods. Produces standardized comparison tables, progress curves, and headroom analysis. |76| benchmark-archaeology | Evaluation Methodology Archaeology Campaign — 5 strategies for systematic analysis of AI/ML benchmarks, metrics, and leaderboards. Reveals construct validity issues, saturation, data contamination, and evaluation protocol inconsistencies. |77| literature-survey | 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. |78| meta-analysis | Cross-Study Statistical Synthesis Campaign — 5 strategies for systematic collection and methodological planning of multi-study evidence synthesis. Covers pairwise, network, cumulative meta-analysis, heterogeneity investigation, and bias detection. Stops at protocol design (no computation). |79| patent-mining | Systematic Patent Analysis Campaign — 5 strategies for patent landscape analysis, prior art search, white space identification, competitive intelligence, and claim analysis. Produces structured patent intelligence reports. |8081<!-- END available-tables (generated) -->
yogsoth-ai