Causal Modeling
Build causal models for research domains. Identifies variables, maps causal mechanisms, collects supporting evidence, analyzes potential interventions, and validates the resulting causal graph.
Manifest
| Level |
Count |
Skills |
| Strategy |
5 |
variable-identification, mechanism-mapping, evidence-collection, intervention-analysis, model-validation |
| Tactic |
3 |
counterfactual-reasoning, evidence-weighing, feedback-loop-detection |
| SOP |
10 |
variable-page-creation, mechanism-edge-creation, evidence-linking, contradiction-flagging, confidence-scoring, intervention-page-creation, loop-documentation, model-gap-detection, causal-chain-query, validation-report |
Budget Table
| Metric |
Small |
Medium |
Large |
| Variables identified |
8 |
20 |
40 |
| Causal edges created |
15 |
40 |
80 |
| Evidence pages linked |
10 |
30 |
60 |
| Interventions analyzed |
2 |
5 |
10 |
| Feedback loops documented |
1 |
3 |
6 |
Strategy Sequence (Reference, Not Prescription)
- variable-identification — identify key variables in the causal system
- mechanism-mapping — map causal mechanisms between variables
- evidence-collection — gather evidence supporting/refuting causal claims
- intervention-analysis — analyze what happens when variables are manipulated
- model-validation — validate the causal model for consistency and completeness
MCP Tools Used
vault_search — find existing variables and mechanismsvault_add_edge — create causal edges (derived_from, supported_by, contradicts)vault_query_graph — trace causal chainsvault_graph_stats — assess model coveragevault_lint — validate structural integrity
Context-Management
Guiding Principles
- Correlation is not causation. Every causal edge must have mechanistic justification, not just statistical association.
- Confounders are everywhere. Actively search for confounding variables that could explain observed relationships.
- Interventions reveal truth. The strongest evidence for causation comes from intervention studies.
- Feedback loops are the norm. Most real systems have circular causation. Document loops explicitly.
- Confidence is calibrated. Strong mechanism + strong evidence = high confidence. Weak either = low confidence.
Available Strategies
Optional, no fixed order; the final leaf is always a sop.
| Strategy |
When to use |
| evidence-collection |
Gather evidence for causal claims |
| intervention-analysis |
Analyze interventions and manipulations on the causal system |
| knowledge-structuring-variable-identification |
Identify key variables in the causal system |
| mechanism-mapping |
Map causal mechanisms between variables |
| model-validation |
Validate causal model consistency |
Available Tactics
Optional, no fixed order; the final leaf is always a sop.
| Tactic |
When to use |
| counterfactual-reasoning |
Tactic for reasoning about what would happen if variables were different — supports causal identification and intervention analysis. |
| evidence-weighing |
Tactic for assessing the strength and relevance of evidence for causal claims — distinguishes correlation from causation. |
| feedback-loop-detection |
Tactic for identifying circular causation — detect feedback loops, classify as reinforcing or balancing, document loop structure. |
| knowledge-compilation |
Tactic for compiling research findings into vault pages — orchestrates page creation, updates, edge linking, and index maintenance. Minimum yield ≥3 page operations per invocation. |
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: causal-modeling3description: Campaign for building causal models — identify variables, map mechanisms, collect evidence, analyze interventions, validate models. Produces causal graphs in the wiki vault.4---56# Causal Modeling78Build causal models for research domains. Identifies variables, maps causal mechanisms, collects supporting evidence, analyzes potential interventions, and validates the resulting causal graph.910## Manifest1112| Level | Count | Skills |13|-------|-------|--------|14| Strategy | 5 | variable-identification, mechanism-mapping, evidence-collection, intervention-analysis, model-validation |15| Tactic | 3 | counterfactual-reasoning, evidence-weighing, feedback-loop-detection |16| SOP | 10 | variable-page-creation, mechanism-edge-creation, evidence-linking, contradiction-flagging, confidence-scoring, intervention-page-creation, loop-documentation, model-gap-detection, causal-chain-query, validation-report |1718## Budget Table1920| Metric | Small | Medium | Large |21|--------|-------|--------|-------|22| Variables identified | 8 | 20 | 40 |23| Causal edges created | 15 | 40 | 80 |24| Evidence pages linked | 10 | 30 | 60 |25| Interventions analyzed | 2 | 5 | 10 |26| Feedback loops documented | 1 | 3 | 6 |2728## Strategy Sequence (Reference, Not Prescription)29301. **variable-identification** — identify key variables in the causal system312. **mechanism-mapping** — map causal mechanisms between variables323. **evidence-collection** — gather evidence supporting/refuting causal claims334. **intervention-analysis** — analyze what happens when variables are manipulated345. **model-validation** — validate the causal model for consistency and completeness3536## MCP Tools Used3738- `vault_search` — find existing variables and mechanisms39- `vault_add_edge` — create causal edges (derived_from, supported_by, contradicts)40- `vault_query_graph` — trace causal chains41- `vault_graph_stats` — assess model coverage42- `vault_lint` — validate structural integrity4344## Context-Management4546<HARD-GATE>47- Call `context-init` at campaign start48- Call `context-checkpoint` after each strategy completes49- Call `knowledge-compilation` after each strategy50</HARD-GATE>5152## Guiding Principles5354- **Correlation is not causation.** Every causal edge must have mechanistic justification, not just statistical association.55- **Confounders are everywhere.** Actively search for confounding variables that could explain observed relationships.56- **Interventions reveal truth.** The strongest evidence for causation comes from intervention studies.57- **Feedback loops are the norm.** Most real systems have circular causation. Document loops explicitly.58- **Confidence is calibrated.** Strong mechanism + strong evidence = high confidence. Weak either = low confidence.5960<!-- BEGIN available-tables (generated) -->6162## Available Strategies6364Optional, no fixed order; the final leaf is always a sop.6566| Strategy | When to use |67| --- | --- |68| evidence-collection | Gather evidence for causal claims |69| intervention-analysis | Analyze interventions and manipulations on the causal system |70| knowledge-structuring-variable-identification | Identify key variables in the causal system |71| mechanism-mapping | Map causal mechanisms between variables |72| model-validation | Validate causal model consistency |7374## Available Tactics7576Optional, no fixed order; the final leaf is always a sop.7778| Tactic | When to use |79| --- | --- |80| counterfactual-reasoning | Tactic for reasoning about what would happen if variables were different — supports causal identification and intervention analysis. |81| evidence-weighing | Tactic for assessing the strength and relevance of evidence for causal claims — distinguishes correlation from causation. |82| feedback-loop-detection | Tactic for identifying circular causation — detect feedback loops, classify as reinforcing or balancing, document loop structure. |83| knowledge-compilation | Tactic for compiling research findings into vault pages — orchestrates page creation, updates, edge linking, and index maintenance. Minimum yield ≥3 page operations per invocation. |8485## Available SOPs8687Optional, no fixed order; the final leaf is always a sop.8889| SOP | When to use |90| --- | --- |91| 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. |92| 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. |9394<!-- END available-tables (generated) -->
yogsoth-ai