AgentSkillsCN

telemetry-analytics

设计遥测与分析系统,以实现可靠的KPI追踪与决策支持。在定义事件模式、指标衍生、分析管道、异常检测,或在为产品发布验证遥测覆盖范围时使用此技能。

SKILL.md
--- frontmatter
name: telemetry-analytics
description: Design telemetry and analytics systems for reliable KPI tracking and decision support. Use when defining event schemas, metric derivations, analytics pipelines, anomaly checks, or validating telemetry coverage for product releases.

Telemetry Analytics

Use this skill to define telemetry pipelines and analytics outputs with KPI trustworthiness.

Workflow

  1. Define scope and constraints.
  • Define KPI questions, event taxonomy, and data quality constraints.
  • Capture objective metrics, bounds, and release blockers.
  1. Design implementation plan.
  • Design ingestion, transformation, and aggregation flow with lineage.
  • Keep ownership and dependency boundaries explicit.
  1. Execute and iterate.
  • Implement in small, traceable increments.
  • Record run/build context for reproducibility.
  1. Validate contract integrity.
  • Validate event completeness, metric accuracy, and anomaly detection gates.
  • Treat contract breaches as blockers.
  1. Prepare handoff.
  • Deliver schema updates, dashboard mapping, and quality checks.
  • Include exact commands and acceptance criteria.

Output Contract

Return:

  1. Context: goals, assumptions, constraints.
  2. Validation: pass/fail checks and key deltas.
  3. Changes: concrete file-level updates.
  4. Commands: commands and expected outputs.
  5. Risks: unresolved issues and limits.

References

  • references/workflow.md: detailed execution flow.
  • references/checklist.md: sign-off checklist.

Execution Rules

  • Keep decisions measurable and reversible.
  • Keep validation criteria explicit before iteration.
  • Flag missing instrumentation and unverifiable KPI derivations as blockers.