---
name: scorpio-objective-bundle
description: Assemble coherent strategic solution packages from objective parameters and scenario dimensions without scoring or selecting a winner.
---

# Objective Package Bundler

A bounded synthesis skill for the third stage of `scorpio objective`. It converts scenario dimensions into coherent end-to-end solution packages that are internally consistent, bounded, and ready for scoring in later workflow stages.

## Purpose

This skill exists to assemble packages, not to judge them.

It must:

1. combine dimension options into coherent strategic bundles
2. reject incoherent or contradictory combinations
3. preserve assumptions, risks, and MVP boundaries
4. leave ranking and critique to downstream skills

## Inputs

Read:

1. `{docs.planning}/OBJECTIVE-PARAMETERS.json`
2. `{docs.planning}/SCENARIO-DIMENSIONS.json`

Do not depend on the raw interview transcript or any downstream scorecard artifact.

## Shared Rules

1. Keep package assembly separate from evaluation.
2. Build coherent bundles, not isolated local winners.
3. Preserve evidence versus inference explicitly.
4. Keep the number of packages bounded.
5. Do not rewrite the upstream objective.

## Bundling Principles

Each package should be an internally consistent strategy with:

1. a clear audience
2. a defined primary problem
3. a value wedge
4. a distribution path
5. a retention mechanism
6. a monetization path
7. trust and safety boundaries
8. a bounded MVP

Packages should be meaningfully different from one another, not small variants of the same idea.

## Coherence Rules

Reject bundles that:

1. target mutually incompatible audiences
2. assume contradictory distribution and retention dynamics
3. require trust or compliance postures that conflict with the stated objective
4. exceed the declared MVP boundary
5. rely on unsupported assumptions without marking them as such

## Required Output

Write:

- `{docs.planning}/SOLUTION-PACKAGES.json`

If the runtime provides a request-scoped objective directory, mirror the artifact there as well, but keep the root canonical file updated in the same run.

## Canonical Output Shape

`SOLUTION-PACKAGES.json` should follow the schema contract:

```json
{
  "version": 1,
  "packages": [
    {
      "package_id": "PKG-001",
      "title": "",
      "target_segment": "",
      "problem_statement": "",
      "value_proposition": "",
      "core_product_mechanism": "",
      "distribution_strategy": "",
      "retention_loop": "",
      "monetization_strategy": "",
      "trust_safety_constraints": [],
      "mvp_scope": {
        "in_scope": [],
        "out_of_scope": []
      },
      "instrumentation_plan": [],
      "success_metrics": [],
      "key_assumptions": [],
      "key_risks": [],
      "kill_criteria": [],
      "evidence_notes": {
        "known_facts_used": [],
        "major_inferences": []
      }
    }
  ]
}
```

## Required Content

Each package should explicitly record:

1. assumptions that must hold
2. risks that could invalidate the package
3. a bounded MVP boundary
4. instrumentation needed to learn quickly
5. kill criteria for early rejection
6. evidence notes that distinguish known facts from inference

## What Not To Do

- Do not write `{docs.tasks}/**`.
- Do not score packages.
- Do not select a winning package.
- Do not write recommendation prose.
- Do not produce `SOLUTION-SCORECARDS.json`.

## Handoff

When bundling is complete, hand the coherent packages to `scorpio-objective-evaluate` and `scorpio-objective-critique` in later workflow stages.