Portfolio Optimization
Select balanced combinations from candidate sets by optimizing across multiple objectives simultaneously. This campaign applies portfolio theory concepts — originally from finance but broadly applicable — to any selection problem where you must choose a subset from many candidates while balancing competing concerns.
Strategy Routing
| Signal |
Strategy |
| maximize total value / ROI / impact within budget |
value-maximization |
| maximize coverage / diversity / avoid redundancy |
diversity-maximization |
| balance risk / hedge / diversify failure modes |
risk-balancing |
| sequence / phase / timeline / dependencies |
temporal-sequencing |
| robust under uncertainty / scenario-proof |
robustness-under-uncertainty |
Manifest
Strategies
| Strategy |
Description |
| value-maximization |
Maximize total value within constraints using Knapsack, LP, Cost-benefit, NPV ranking |
| diversity-maximization |
Maximize portfolio diversity using MAP-Elites, Niche coverage, Maximum dispersion |
| risk-balancing |
Balance risk-return using Markowitz mean-variance, CVaR, Risk parity, Kelly criterion |
| temporal-sequencing |
Optimal ordering using Real Options, Critical path, Dependency graph, Staged investment |
| robustness-under-uncertainty |
Perform well across futures using Minimax regret, Robust optimization, Scenario planning |
Tactics
| Tactic |
Description |
| pareto-frontier-construction |
Build and visualize the Pareto frontier, then select from non-dominated solutions |
| niche-coverage-analysis |
Map candidates to niches, score coverage, identify gaps |
| scenario-stress-testing |
Evaluate portfolio performance across multiple future scenarios |
SOPs
| SOP |
Description |
| objective-definition |
Define optimization objectives and constraints from context |
| optimization-run |
Execute multi-objective optimization to produce Pareto front |
| pareto-visualization |
Visualize trade-offs along the Pareto frontier |
| selection-from-frontier |
Select final portfolio from Pareto front given preferences |
| niche-definition |
Define niches within the solution space |
| niche-mapping |
Map candidates to defined niches |
| coverage-scoring |
Score coverage completeness and identify gaps |
| scenario-construction |
Construct distinct future scenarios from uncertainties |
| portfolio-evaluation-per-scenario |
Evaluate a portfolio under a specific scenario |
| portfolio-synthesis |
Synthesize evaluations into final robust portfolio recommendation |
Budget Table
| Dimension |
M-tier Target |
| Candidates considered |
8-20 |
| Objectives optimized |
>=2 simultaneously |
| Scenarios tested |
>=3 distinct futures |
| Pareto points generated |
>=5 non-dominated solutions |
MCP Tools
mcp__wiki-vault__vault_search — retrieve prior portfolio analyses and candidate datamcp__wiki-vault__vault_query_graph — traverse relationships between candidatesmcp__wiki-vault__vault_add_edge — record portfolio decisions and rationale
Context Management
- Pass candidate list and objective weights between strategy and tactics
- Pareto front data flows from optimization-run to visualization and selection
- Scenario definitions are shared across all evaluation SOPs
- Final synthesis aggregates all per-scenario evaluations
Available Strategies
Optional, no fixed order; the final leaf is always a sop.
| Strategy |
When to use |
| diversity-maximization |
Maximize portfolio diversity and coverage using MAP-Elites, Niche coverage, Maximum dispersion, and Anti-clustering methods. |
| risk-balancing |
Balance portfolio risk and return using Markowitz mean-variance, CVaR, Risk parity, and Kelly criterion methods. |
| robustness-under-uncertainty |
Select portfolios that perform well across multiple future scenarios using Minimax regret, Robust optimization, Scenario planning, and Info-gap methods. |
| temporal-sequencing |
Determine optimal ordering and phasing of portfolio investments using Real Options, Critical path, Dependency graph, and Staged investment methods. |
| value-maximization |
Maximize total portfolio value within constraints using Knapsack, Linear programming, Cost-benefit analysis, and NPV ranking methods. |
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. |
| convergence-saturation-detection |
Determines when to stop iterating — coverage threshold met or marginal returns diminishing. Shared across all campaigns. |
| convergence-sensitivity-analysis |
Tests conclusion robustness by perturbing parameters and observing rank changes. Shared across scoring, portfolio, and steel-manning campaigns. |
1---2name: convergence-portfolio-optimization3description: Portfolio Optimization Campaign — select balanced combinations from candidate sets optimizing value, diversity, risk, and robustness using Markowitz, Knapsack, Pareto, Real Options, MAP-Elites, and minimax regret methods.4---56# Portfolio Optimization78Select balanced combinations from candidate sets by optimizing across multiple objectives simultaneously. This campaign applies portfolio theory concepts — originally from finance but broadly applicable — to any selection problem where you must choose a subset from many candidates while balancing competing concerns.910## Strategy Routing1112| Signal | Strategy |13|--------|----------|14| maximize total value / ROI / impact within budget | value-maximization |15| maximize coverage / diversity / avoid redundancy | diversity-maximization |16| balance risk / hedge / diversify failure modes | risk-balancing |17| sequence / phase / timeline / dependencies | temporal-sequencing |18| robust under uncertainty / scenario-proof | robustness-under-uncertainty |1920## Manifest2122### Strategies2324| Strategy | Description |25|----------|-------------|26| value-maximization | Maximize total value within constraints using Knapsack, LP, Cost-benefit, NPV ranking |27| diversity-maximization | Maximize portfolio diversity using MAP-Elites, Niche coverage, Maximum dispersion |28| risk-balancing | Balance risk-return using Markowitz mean-variance, CVaR, Risk parity, Kelly criterion |29| temporal-sequencing | Optimal ordering using Real Options, Critical path, Dependency graph, Staged investment |30| robustness-under-uncertainty | Perform well across futures using Minimax regret, Robust optimization, Scenario planning |3132### Tactics3334| Tactic | Description |35|--------|-------------|36| pareto-frontier-construction | Build and visualize the Pareto frontier, then select from non-dominated solutions |37| niche-coverage-analysis | Map candidates to niches, score coverage, identify gaps |38| scenario-stress-testing | Evaluate portfolio performance across multiple future scenarios |3940### SOPs4142| SOP | Description |43|-----|-------------|44| objective-definition | Define optimization objectives and constraints from context |45| optimization-run | Execute multi-objective optimization to produce Pareto front |46| pareto-visualization | Visualize trade-offs along the Pareto frontier |47| selection-from-frontier | Select final portfolio from Pareto front given preferences |48| niche-definition | Define niches within the solution space |49| niche-mapping | Map candidates to defined niches |50| coverage-scoring | Score coverage completeness and identify gaps |51| scenario-construction | Construct distinct future scenarios from uncertainties |52| portfolio-evaluation-per-scenario | Evaluate a portfolio under a specific scenario |53| portfolio-synthesis | Synthesize evaluations into final robust portfolio recommendation |5455## Budget Table5657| Dimension | M-tier Target |58|-----------|---------------|59| Candidates considered | 8-20 |60| Objectives optimized | >=2 simultaneously |61| Scenarios tested | >=3 distinct futures |62| Pareto points generated | >=5 non-dominated solutions |6364## MCP Tools6566- `mcp__wiki-vault__vault_search` — retrieve prior portfolio analyses and candidate data67- `mcp__wiki-vault__vault_query_graph` — traverse relationships between candidates68- `mcp__wiki-vault__vault_add_edge` — record portfolio decisions and rationale6970## Context Management7172- Pass candidate list and objective weights between strategy and tactics73- Pareto front data flows from optimization-run to visualization and selection74- Scenario definitions are shared across all evaluation SOPs75- Final synthesis aggregates all per-scenario evaluations7677<!-- BEGIN available-tables (generated) -->7879## Available Strategies8081Optional, no fixed order; the final leaf is always a sop.8283| Strategy | When to use |84| --- | --- |85| diversity-maximization | Maximize portfolio diversity and coverage using MAP-Elites, Niche coverage, Maximum dispersion, and Anti-clustering methods. |86| risk-balancing | Balance portfolio risk and return using Markowitz mean-variance, CVaR, Risk parity, and Kelly criterion methods. |87| robustness-under-uncertainty | Select portfolios that perform well across multiple future scenarios using Minimax regret, Robust optimization, Scenario planning, and Info-gap methods. |88| temporal-sequencing | Determine optimal ordering and phasing of portfolio investments using Real Options, Critical path, Dependency graph, and Staged investment methods. |89| value-maximization | Maximize total portfolio value within constraints using Knapsack, Linear programming, Cost-benefit analysis, and NPV ranking methods. |9091## Available SOPs9293Optional, no fixed order; the final leaf is always a sop.9495| SOP | When to use |96| --- | --- |97| 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. |98| 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. |99| convergence-saturation-detection | Determines when to stop iterating — coverage threshold met or marginal returns diminishing. Shared across all campaigns. |100| convergence-sensitivity-analysis | Tests conclusion robustness by perturbing parameters and observing rank changes. Shared across scoring, portfolio, and steel-manning campaigns. |101102<!-- END available-tables (generated) -->
yogsoth-ai