magnus919_agent-skills/technical-program-management/evals/evals.json

{
  "schema_version": 1,
  "skill_name": "technical-program-management",
  "evals": [
    {"id":"program-mandate","prompt":"Four related platform projects are underway, but nobody can explain the shared outcome, authority, or why they belong together. Establish the smallest useful program mandate.","expected_output":"A program brief that defines shared outcome, authorization, sponsor, component boundaries, decision rights, and evidence gaps without inventing approval.","assertions":["States a shared outcome and coordination rationale.","Names missing sponsor/authorization as unknown rather than inventing it.","Lists components, owners, interfaces, and decision rights.","Separates proposed brief from approved program."]},
    {"id":"component-alignment","prompt":"Two component projects have different delivery methods and calendars. One wants to force the other into its sprint cadence. Advise the program manager.","expected_output":"A coordination model that preserves suitable component methods while aligning shared outcomes, milestones, interfaces, and evidence.","assertions":["Does not force one cadence without a demonstrated need.","Defines integrated milestones and interface evidence.","Preserves component decision rights.","Names a revisit trigger."]},
    {"id":"dependency-conflict","prompt":"Project A says its API is complete. Project B cannot integrate it because the schema is still changing and the test environment is unavailable. Prepare the program response.","expected_output":"A provider/receiver dependency decision with ready definition, acceptance evidence, impact, fallback, and escalation.","assertions":["Separates component completion from usable handoff.","Names provider, receiver, ready criteria, and evidence.","Shows program impact and fallback.","Escalates only the unresolved authority decision."]},
    {"id":"shared-capacity","prompt":"Three projects all need the same security architect in the next month, and each project claims its date is fixed. Give the sponsor a decision brief.","expected_output":"Options showing capacity conflict, consequences, sequencing or scope/date alternatives, and sponsor authority.","assertions":["States the shared-capacity conflict.","Does not promise capacity without a decision.","Provides at least two feasible options and consequences.","Preserves current commitments until authorized change."]},
    {"id":"benefit-drift","prompt":"All component projects delivered their outputs, but customer adoption is flat and operating costs are higher than expected. How should the program respond?","expected_output":"A benefits/disbenefits review that tests the causal chain, names owners and measures, and offers reshape, continue, or stop options.","assertions":["Does not equate output delivery with benefits realization.","Identifies adoption and cost evidence gaps.","Names benefit/disbenefit owners, measures, and review triggers.","Offers a decision beyond simply declaring success."]},
    {"id":"governance-escalation","prompt":"The program team is deadlocked over a cross-project architecture decision, and no role has authority to resolve it. What do you do?","expected_output":"An escalation record and bounded decision path, not an invented technical decision.","assertions":["Names the missing or contested authority.","Defines evidence and options for escalation.","Records impact of waiting.","Does not silently decide outside authority."]},
    {"id":"stakeholder-communication","prompt":"Write three versions of this update: one for the executive sponsor, one for component leads, and one for operations. The program is on schedule, but integration confidence is falling.","expected_output":"Audience-specific updates preserving the same evidence and decision need.","assertions":["Executive version leads with outcome confidence, impact, options, and decision date.","Component version names interfaces, actions, and authority boundaries.","Operations version names readiness, support, adoption, and residual risks.","None claims an unqualified green status."]},
    {"id":"troubled-recovery","prompt":"The program has missed two integrated milestones. Component teams want to add more work and meetings, while the sponsor wants the old date preserved. Prepare a recovery approach.","expected_output":"A bounded diagnostic and trade-off brief preserving history and identifying the limiting constraint.","assertions":["Preserves original mandate, commitments, and variance.","Diagnoses dependency, capacity, scope, quality, and authority causes.","Provides scope/date/sequence/capacity/pause/stop options.","Defines an evidence checkpoint and escalation path."]},
    {"id":"transformation-adoption","prompt":"A platform program is technically ready, but regional operations teams are not changing their processes. Build the next program decision.","expected_output":"A change/adoption response connecting affected roles, operating model, training, feedback, measures, and ownership.","assertions":["Treats adoption as part of program outcome, not a postscript.","Names affected groups and change/adoption owners.","Defines measurable signals and feedback channels.","Routes organizational structure questions to org-design when appropriate."]},
    {"id":"method-selection","prompt":"A program combines a regulated hardware migration, uncertain software integration, and a vendor transition. Select and tailor a program approach.","expected_output":"A hybrid program pattern with separate component cadences and one integrated decision/evidence view.","assertions":["Selects hybrid based on diagnosed conditions.","Separates mandatory gates from iterative learning.","Defines shared milestones/interfaces and review trigger.","Avoids claiming a method guarantees success."]},
    {"id":"project-routing","prompt":"I need to review one project's forecast, vendor handoff, and closure evidence, not coordinate a wider initiative. Which skill should I use?","expected_output":"Routes to technical-project-management and explains the program-level boundary.","assertions":["Routes single-project control to technical-project-management.","Does not answer as if a program is required.","Explains the boundary briefly and accurately."]},
    {"id":"portfolio-routing","prompt":"Which three investments should the company fund next quarter, and should we shut down the lowest-return one?","expected_output":"Routes capital allocation and portfolio choice to the appropriate portfolio/strategy skill.","assertions":["Routes to product-roadmapping-and-portfolio or strategy-frameworks based on context.","Does not invent a program mandate.","Distinguishes portfolio selection from program coordination."]}
  ]
}