| name | u0860-community-semantic-retrieval-ranker |
| description | Build and operate the "Community Semantic Retrieval Ranker" capability for Community Engagement and Feedback. Trigger when this exact capability is needed in mission execution. |
Community Semantic Retrieval Ranker
Why This Skill Exists
We need this skill because real-world feedback loops are necessary for continuous alignment. This specific skill improves recall precision for downstream decision quality.
When To Use
Use this skill when the request explicitly needs "Community Semantic Retrieval Ranker" outcomes in the Community Engagement and Feedback domain.
Step-by-Step Implementation Guide
- Define the scope and success metrics for
Community Semantic Retrieval Ranker, including at least three measurable KPIs tied to community trust loss and unaddressed concerns.
- Design and version the input/output contract for feedback channels, sentiment, urgency, and follow-ups, then add schema validation and failure-mode handling.
- Implement the core capability using semantic relevance scoring, and produce ranked retrieval results 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 community trust loss and unaddressed concerns, 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: planning-router using semantic relevance scoring to produce ranked retrieval results.
- Orchestration integration: community-engagement-and-feedback:planning-router routing, approval gates, retries, and rollback controls.
- Validation evidence: unit, integration, simulation, regression-baseline suites and rollout telemetry.
Operational Runbook
Preflight
- Confirm the Community Semantic Retrieval Ranker request scope, source evidence, and measurable success criteria before execution.
- Verify feature flag skill_0860_community-semantic-retrieval-ran, approval gates, and rollback owner before autonomous use.
Execution
- Execute semantic relevance scoring with deterministic scoring and reproducible trace capture.
- Produce ranked retrieval results 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 ranked retrieval results, 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.
