zwright8 Evolution Plan Quality Evaluator
Why This Skill Exists
We need this skill because agents stagnate without structured reflection and continuous improvement loops. This specific skill quantifies whether plans are complete, safe, and feasible.
When To Use
Use this skill when the request explicitly needs "Evolution Plan Quality Evaluator" outcomes in the Autonomous Learning and Evolution domain.
Step-by-Step Implementation Guide
- Define the scope and success metrics for
Evolution Plan Quality Evaluator, including at least three measurable KPIs tied to capability stagnation and repeated blind spots. - Design and version the input/output contract for outcomes, error taxonomies, and adaptation decisions, 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 capability stagnation and repeated blind spots, 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: autonomous-learning-and-evolution: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 Evolution Plan Quality Evaluator request scope, source evidence, and measurable success criteria before execution.
- Verify feature flag skill_0981_evolution-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.