Oversight Plan Quality Evaluator
Why This Skill Exists
We need this skill because human teams need fast, legible control when stakes are high. This specific skill quantifies whether plans are complete, safe, and feasible.
When To Use
Use this skill when the request explicitly needs "Oversight Plan Quality Evaluator" outcomes in the Human Oversight and Operator UX domain.
Step-by-Step Implementation Guide
- Define the scope and success metrics for
Oversight Plan Quality Evaluator, including at least three measurable KPIs tied to slow interventions and approval bottlenecks.
- Design and version the input/output contract for approval queues, operator workload, and intervention history, then add schema validation and failure-mode handling.
- Implement the core capability using multi-criteria plan scoring, and produce plan quality scorecards with deterministic scoring.
- Integrate the skill into swarm orchestration: task routing, approval gates, retry strategy, and rollback controls.
- Add unit, integration, and simulation tests that explicitly cover slow interventions and approval bottlenecks, then run regression baselines.
- Deploy behind a feature flag, monitor telemetry/alerts for two release cycles, and iterate thresholds based on observed outcomes.
Required Deliverables
- Capability contract: input schema, deterministic scoring, output schema, and failure modes.
- Runtime profile: general-capability using multi-criteria plan scoring to produce plan quality scorecards.
- Orchestration integration: human-oversight-and-operator-ux:general-capability routing, approval gates, retries, and rollback controls.
- Validation evidence: unit, integration, simulation, regression-baseline suites and rollout telemetry.
Operational Runbook
Preflight
- Confirm the Oversight Plan Quality Evaluator request scope, source evidence, and measurable success criteria before execution.
- Verify feature flag skill_0221_oversight-plan-quality-evaluator, approval gates, and rollback owner before autonomous use.
Execution
- Execute multi-criteria plan scoring with deterministic scoring and reproducible trace capture.
- Produce plan quality scorecards plus scorecard, assumptions, and unresolved-risk notes.
Recovery
- Fail closed when required signals, evidence, or approval gates are missing.
- Rollback to the last stable baseline when posture is critical or validation fails.
Handoff
- Publish plan quality scorecards, validation evidence, and telemetry links to downstream owners.
- Queue follow-up tasks for unresolved risks, threshold tuning, or approval review.
Guardrails
- [quality] Require deterministic scoring and validation evidence before promotion.
- [reliability] Preserve retries, rollback controls, and failure-mode evidence for every run.
- [safety] Route critical posture or missing approval gates to human review before autonomous action.
1---2name: u0221-oversight-plan-quality-evaluator3description: Build and operate the "Oversight Plan Quality Evaluator" capability for Human Oversight and Operator UX. Trigger when this exact capability is needed in mission execution.4---56# Oversight Plan Quality Evaluator78## Why This Skill Exists9We need this skill because human teams need fast, legible control when stakes are high. This specific skill quantifies whether plans are complete, safe, and feasible.1011## When To Use12Use this skill when the request explicitly needs "Oversight Plan Quality Evaluator" outcomes in the Human Oversight and Operator UX domain.1314## Step-by-Step Implementation Guide151. Define the scope and success metrics for `Oversight Plan Quality Evaluator`, including at least three measurable KPIs tied to slow interventions and approval bottlenecks.162. Design and version the input/output contract for approval queues, operator workload, and intervention history, then add schema validation and failure-mode handling.173. Implement the core capability using multi-criteria plan scoring, and produce plan quality scorecards with deterministic scoring.184. Integrate the skill into swarm orchestration: task routing, approval gates, retry strategy, and rollback controls.195. Add unit, integration, and simulation tests that explicitly cover slow interventions and approval bottlenecks, then run regression baselines.206. Deploy behind a feature flag, monitor telemetry/alerts for two release cycles, and iterate thresholds based on observed outcomes.2122## Required Deliverables23- Capability contract: input schema, deterministic scoring, output schema, and failure modes.24- Runtime profile: general-capability using multi-criteria plan scoring to produce plan quality scorecards.25- Orchestration integration: human-oversight-and-operator-ux:general-capability routing, approval gates, retries, and rollback controls.26- Validation evidence: unit, integration, simulation, regression-baseline suites and rollout telemetry.2728## Operational Runbook29### Preflight30- Confirm the Oversight Plan Quality Evaluator request scope, source evidence, and measurable success criteria before execution.31- Verify feature flag skill_0221_oversight-plan-quality-evaluator, approval gates, and rollback owner before autonomous use.3233### Execution34- Execute multi-criteria plan scoring with deterministic scoring and reproducible trace capture.35- Produce plan quality scorecards plus scorecard, assumptions, and unresolved-risk notes.3637### Recovery38- Fail closed when required signals, evidence, or approval gates are missing.39- Rollback to the last stable baseline when posture is critical or validation fails.4041### Handoff42- Publish plan quality scorecards, validation evidence, and telemetry links to downstream owners.43- Queue follow-up tasks for unresolved risks, threshold tuning, or approval review.4445## Guardrails46- [quality] Require deterministic scoring and validation evidence before promotion.47- [reliability] Preserve retries, rollback controls, and failure-mode evidence for every run.48- [safety] Route critical posture or missing approval gates to human review before autonomous action.
zwright8