portfolio-optimization
Purpose
Formalize objectives/constraints, construct a Pareto frontier, stress across scenarios, and select a robust portfolio.
Input contract
required: [candidate_set, objective_vector, resource_constraints, scenario_set]
optional: [assumptions, prior_findings, evidence_updates]
constraints: [consume named scientific objects; preserve provenance; keep unresolved uncertainty visible]
Execution protocol
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
- You MUST load skill
define-objective to declare outcome directions, hard constraints, stakeholder scope, horizon, and permissible tradeoffs before comparing candidates.
- You MUST load skill
optimize-pareto-frontier to remove infeasible candidates and retain only points not dominated across the normalized objective dimensions.
- You MUST load skill
construct-scenario to stress each surviving candidate or portfolio under a fixed scenario and expose impact, tradeoffs, and failure triggers.
- You MUST load skill
evaluate-scenario-impact to evaluate the current portfolio inside each scenario using stable criteria, explicit missingness, and counterexamples.
- You MUST load skill
select-from-frontier to apply the preference policy and document the chosen point, sacrificed objectives, and nearest alternatives.
- You MUST load skill
measure-portfolio-diversity to quantify coverage and reveal concentration and niche collapse.
- You MUST load skill
map-dependencies to map dependencies, cycles, critical paths, and independent branches before committing to an execution order.
- You MUST load skill
sequence-work to topologically order the dependent work while surfacing fail-fast and high-risk branches.
- You MUST load skill
evaluate-optionality to compare immediate, deferred, staged, and information-gathering actions by reversibility, delay cost, and trigger conditions.
- You MUST load skill
evaluate-scenario-robustness to aggregate scenario results and state which portfolio assumptions remain fragile.
If the selected portfolio needs a strong challenge before commitment, consider adversarial-deliberation as the next tactic.
Deviation: reorder only when a dependency is already satisfied or unavailable; record the reason and confidence effect.
Output contract
produces: [pareto_frontier, selected_portfolio, scenario_risk_summary]
delta_fields: [findings, decisions]
Thresholds and quality gates
- Each output is traceable to an input object, operation, and evidence reference.
- Scope, assumptions, and unresolved alternatives remain explicit.
- Retain $\alpha$ 0.05 and power 0.8 wherever the predeclared statistical design requires them.
Failure and counterexamples
Stop synthesis when a required object is absent, a precondition is violated, or a counterexample invalidates the proposed conclusion; return the partial delta with the failure recorded.
Provenance map
- intermediate: portfolio-optimization [campaign]
- resolved: value-maximization
- resolved: diversity-maximization
- resolved: risk-balancing
- resolved: temporal-sequencing
- resolved: robustness-under-uncertainty
- resolved: pareto-frontier-construction
- resolved: scenario-stress-testing
- resolved: niche-coverage-analysis
Preserved source criteria ledger
| source |
criterion |
treatment |
| resolved v3 entries above |
node-specific criteria |
retained and specialized to the v4 object contract |
| experiment-execution/statistical-testing |
$\alpha$ = 0.05 |
fixed value retained where applicable |
| experiment-execution/sample-size-estimation |
power = 0.8 |
fixed value retained where applicable |
Context checkpoint / Delta notes
Return the node-specific research-state delta and preserve findings, evidence updates, uncertainties, decisions, open questions, and recommended jumps as applicable.
1---2name: portfolio-optimization3description: "Formalize objectives/constraints, construct a Pareto frontier, stress across scenarios, and select a robust portfolio."4metadata:5 source: https://skillmd.com/skills/yogsoth-ai/portfolio-optimization6---78# portfolio-optimization910## Purpose1112Formalize objectives/constraints, construct a Pareto frontier, stress across scenarios, and select a robust portfolio.1314## Input contract1516```yaml17required: [candidate_set, objective_vector, resource_constraints, scenario_set]18optional: [assumptions, prior_findings, evidence_updates]19constraints: [consume named scientific objects; preserve provenance; keep unresolved uncertainty visible]20```2122## Execution protocol2324Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.25261. You MUST load skill `define-objective` to declare outcome directions, hard constraints, stakeholder scope, horizon, and permissible tradeoffs before comparing candidates.272. You MUST load skill `optimize-pareto-frontier` to remove infeasible candidates and retain only points not dominated across the normalized objective dimensions.283. You MUST load skill `construct-scenario` to stress each surviving candidate or portfolio under a fixed scenario and expose impact, tradeoffs, and failure triggers.294. You MUST load skill `evaluate-scenario-impact` to evaluate the current portfolio inside each scenario using stable criteria, explicit missingness, and counterexamples.305. You MUST load skill `select-from-frontier` to apply the preference policy and document the chosen point, sacrificed objectives, and nearest alternatives.316. You MUST load skill `measure-portfolio-diversity` to quantify coverage and reveal concentration and niche collapse.327. You MUST load skill `map-dependencies` to map dependencies, cycles, critical paths, and independent branches before committing to an execution order.338. You MUST load skill `sequence-work` to topologically order the dependent work while surfacing fail-fast and high-risk branches.349. You MUST load skill `evaluate-optionality` to compare immediate, deferred, staged, and information-gathering actions by reversibility, delay cost, and trigger conditions.3510. You MUST load skill `evaluate-scenario-robustness` to aggregate scenario results and state which portfolio assumptions remain fragile.36 If the selected portfolio needs a strong challenge before commitment, consider `adversarial-deliberation` as the next tactic.3738Deviation: reorder only when a dependency is already satisfied or unavailable; record the reason and confidence effect.3940## Output contract4142```yaml43produces: [pareto_frontier, selected_portfolio, scenario_risk_summary]44delta_fields: [findings, decisions]45```4647## Thresholds and quality gates4849- Each output is traceable to an input object, operation, and evidence reference.50- Scope, assumptions, and unresolved alternatives remain explicit.51- Retain $\alpha$ 0.05 and power 0.8 wherever the predeclared statistical design requires them.5253## Failure and counterexamples5455Stop synthesis when a required object is absent, a precondition is violated, or a counterexample invalidates the proposed conclusion; return the partial delta with the failure recorded.5657## Provenance map5859- intermediate: portfolio-optimization [campaign]60- resolved: value-maximization61- resolved: diversity-maximization62- resolved: risk-balancing63- resolved: temporal-sequencing64- resolved: robustness-under-uncertainty65- resolved: pareto-frontier-construction66- resolved: scenario-stress-testing67- resolved: niche-coverage-analysis6869## Preserved source criteria ledger7071| source | criterion | treatment |72|---|---|---|73| resolved v3 entries above | node-specific criteria | retained and specialized to the v4 object contract |74| experiment-execution/statistical-testing | $\alpha$ = 0.05 | fixed value retained where applicable |75| experiment-execution/sample-size-estimation | power = 0.8 | fixed value retained where applicable |7677## Context checkpoint / Delta notes7879Return the node-specific research-state delta and preserve findings, evidence updates, uncertainties, decisions, open questions, and recommended jumps as applicable.