A hypothesis is not a guess — it is a precisely engineered bridge between what we know and what we need to test. The difference between having an idea and having a hypothesis is the difference between pointing at the horizon and drawing a map to get there.
Goal-Driven Hypothesis & Research Question Formation Engine for Academic Research
Hypothesis Formation transforms upstream gaps and insights into testable hypotheses and precise research questions. You provide prioritized gaps — it ranks them, derives hypotheses with falsifiability criteria, and formulates framework-guided research questions with scope, success criteria, and sub-question decomposition. Three autonomous campaigns, each with quantitative budget enforcement.
- 🎯 Gap Prioritization — multi-criteria ranking of research gaps using AHP weighting, PiCMe assessment, pairwise comparison, portfolio optimization, and sensitivity testing
- 🔬 Hypothesis Formulation — transforms insights into structured hypotheses via deductive, inductive, and abductive reasoning. Produces competing hypotheses with falsifiability criteria and boundary conditions
- 📐 Research Question Formation — framework-guided formulation (PICO/SPIDER/SPICE/ECLIPSE), scope calibration, sub-question decomposition, and FINER criteria validation
Each campaign is a self-contained research activity domain. The entry point routes to the correct campaign based on user intent, then the campaign autonomously selects strategies and executes with quantitative budget enforcement.
ENTRY.md (root)
→ Campaign (3): self-contained research activity domain
→ Strategy: selected by research context and constraints
→ Tactic: multi-step orchestration pattern
→ SOP: single operation (import or subagent)Every strategy embeds quantitative floors (dimensions evaluated, hypotheses produced, FINER criteria passed). Budget gates prevent premature exit. Context checkpoints after every strategy completion.
Skills teach principles and provide default reference flows — CC reads, internalizes, and constructs its own approach for each specific research task. Hard constraints are minimal: Budget Gate, Minimum Yield, HARD-GATE, context-checkpoint.
┌───────────────────────────────────────────────────────────────┐
│ ENTRY POINT (ENTRY.md) │
│ Routes to campaign based on research intent │
├───────────────────────────────────────────────────────────────┤
│ CAMPAIGN (3) │
│ gap-prioritization, hypothesis-formulation, research-question│
├───────────────────────────────────────────────────────────────┤
│ STRATEGY (15) │
│ 5 per campaign, selected by context │
├───────────────────────────────────────────────────────────────┤
│ TACTIC (10) │
│ 3 + 4 + 3, orchestrate SOPs into workflows │
├───────────────────────────────────────────────────────────────┤
│ SOP (44) │
│ 5 import + 2 shared + 37 campaign-specific │
│ Single-responsibility subagent operations │
└───────────────────────────────────────────────────────────────┘| Strategy | When to Use |
|---|---|
| multi-criteria-ranking | Default — 5-20 gaps, systematic multi-dimensional scoring |
| evidence-based-prioritization | Gaps from rigorous literature review with strong evidence |
| stakeholder-weighted-ranking | Multiple stakeholders with different priority weights |
| portfolio-optimization | 20+ gaps, portfolio-level risk/reward optimization |
| rapid-triage | 50+ gaps, quick filtering to manageable set |
| Strategy | When to Use |
|---|---|
| deductive-hypothesis-generation | Mature theory exists, gap is theory-reality deviation |
| inductive-hypothesis-generation | No theory, but data patterns or empirical observations |
| abductive-hypothesis-generation | Anomalous observations that defy existing explanations |
| competing-hypothesis-construction | Need multiple alternatives to avoid confirmation bias |
| hypothesis-operationalization | Have directional hypothesis, need to formalize |
| Strategy | When to Use |
|---|---|
| framework-guided-formulation | Clear research type, standard framework available |
| scope-calibration | Question too broad or too narrow |
| decomposition-formulation | Complex question, single study can't answer |
| comparative-formulation | Need to compare A vs B systematically |
| feasibility-constrained-formulation | Ideal question exceeds available resources |
| Dependency | What It Provides |
|---|---|
| web-browsing | web-search + web-research (2 import SOPs) |
| literature-engine | paper-overview + paper-search + paper-research (3 import SOPs) |
| subagent-spawning | Subagent dispatch conventions |
| context-management | context-init + context-checkpoint protocol |
| Server | Purpose |
|---|---|
| brave-search | Web search for frameworks, methods, background |
| apify | Deep web scraping, Google Scholar |
| alphaxiv | Paper discovery, content, PDF Q&A |
| semantic-scholar | Paper metadata, citations, recommendations |
- Clone this repo alongside its dependencies:
git clone https://github.com/yogsoth-ai/hypothesis-formation.git
git clone https://github.com/yogsoth-ai/web-browsing.git
git clone https://github.com/yogsoth-ai/literature-engine.git
git clone https://github.com/yogsoth-ai/context-management.git
git clone https://github.com/yogsoth-ai/subagent-spawning.git-
Copy
.mcp.example.jsonto.mcp.jsonand fill in your API keys -
Deploy skills to your Claude Code skills directory
-
Use via the entry point:
/hypothesis-formation I have 10 gaps from my literature survey on [topic]. Help me prioritize and formulate hypotheses.
| Component | Count |
|---|---|
| Campaigns | 3 |
| Strategies | 15 |
| Tactics | 10 |
| Subagent SOPs | 37 |
| Import SOPs | 5 |
| Shared SOPs | 2 |
| Total skill directories | 72 |
Apache-2.0