workflow-telemetry

Derive operational metrics and performance trends from recorded workflow execution events.

Updated Aug 1, 2026
One-click install
npx skills add https://github.com/QuyDu/Skills-Orchestrator --skill workflow-telemetry-quydu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: workflow-telemetry
Source: https://github.com/QuyDu/Skills-Orchestrator/tree/main/.github/skills/workflow-telemetry
Command: npx skills add https://github.com/QuyDu/Skills-Orchestrator --skill workflow-telemetry-quydu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? After workflows run, teams lack a consistent way to measure throughput, failures, retries, approval waits, and skill performance from raw execution events. This Skill turns authoritative runtime event logs into reproducible telemetry reports. ## Core Features & Use Cases - Metric Derivation: Compute throughput, latency, retries, failures, approval waits, and artifact production from normalized event streams. - Trend Analysis: Compare metrics against baselines and flag statistically meaningful deviations, with explicit degraded-coverage markers when data is missing. - Use Case: After a contract migration rollout, ingest the event log from workflow-state-manager to identify retry hotspots and produce a weekly failure-rate and approval-latency report per skill. ## Quick Start Analyze the workflow event log from last week and generate the telemetry report showing failure rates and approval latency by skill.

Frequently Asked Questions about workflow-telemetry

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate workflow performance metrics from execution logs?

Ingest the event streams and snapshots from workflow-state-manager for the desired window, then the skill normalizes events by workflow, skill, step, status, and duration. It computes throughput, latency, retries, failures, and approval waits into JSON and Markdown reports.

What metrics can I derive from workflow event streams?

You can derive throughput, latency, retry counts, failure rates, approval wait times, artifact production, and resource or budget indicators where data is available. Metrics are reproducible from the same event window and definitions.

Can workflow telemetry be used for live monitoring or alerting?

No. This skill analyzes recorded workflow events after execution and is explicitly not a live monitoring or alerting system. It requires explicit approval before telemetry is shared outside authorized project boundaries.

What inputs does workflow telemetry analysis require?

It requires authoritative execution state and event log outputs from workflow-state-manager, plus metric definitions and reporting windows. Optional baselines enable trend comparison; without them, the skill will not claim trend confidence.

What happens when telemetry data is incomplete or ambiguous?

The skill fails closed when event provenance or time window boundaries are ambiguous. Partial telemetry is returned only with explicitly excluded dimensions, and missing dimensions are marked as degraded coverage.