DU

Maintains the reliability of durable legal workflows, providing debugging steps for stalled jobs.

Install

mkdir -p .claude/skills/durable-execution && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/19167" && unzip -o skill.zip -d .claude/skills/durable-execution && rm skill.zip

Installs to .claude/skills/durable-execution

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

The operational contract for Neon Law Navigator's Restate-backed durable execution — how to keep the running workflows alive, diagnose why one didn't fire, and not break them. Covers the submit-vs-run split (workflows lib / workflows-service bin), the service inventory, the six-hourly Heartbeat liveness canary, the three start modes, and how to investigate a stalled workflow by following the evidence — commit history, GitHub Actions runs, pod and Cloud logs, and Google Cloud (Trace, GKE, the Restate console) — then pin the fix with a guard test so it can't recur. Trigger when touching workflows-service, a *-trigger CronJob, the image Containerfiles, when re-registering with Restate, when a scheduled or manual workflow "didn't run", or when adding a workspace crate (it must enter the Containerfile COPY lists). This engine executes BINDING legal artifacts (retainer dispatch, signatures, filings, the matter-close invoice), so an outage is a diligence concern, not a backlog item. Debugging surfaces carry invocation ids and service names, NEVER client content. To *add* a new workflow use create-legal-workflow; this skill keeps the existing ones alive.
1164 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Advanced

Key capabilities

  • Keep running workflows alive
  • Diagnose why a workflow did not fire
  • Investigate stalled workflows by following evidence
  • Pin fixes with a test or manifest field
  • Add workspace crates to Containerfile COPY lists
  • Debug using identifier-and-status only

How it works

The skill provides a playbook for diagnosing and fixing issues with Restate-backed durable execution workflows, emphasizing evidence-based investigation and guarding against recurrence.

Inputs & outputs

You give it
A report of a scheduled or manual workflow that 'didn't run'
You get back
Diagnosis of the workflow issue and a plan to fix it, including guard tests

When to use durable-execution

  • Diagnose stalled workflows
  • Monitor workflow heartbeat
  • Ensure legal automation reliability

About durable-execution

Supports the operational contract for Restate-backed durable execution. Provides diagnostic paths for system outages and workflow liveness.

>

When not to use it

  • When adding a new workflow template
  • When authoring a Restate handler without breaking durability
  • When dealing with telemetry or trigger metrics

Limitations

  • Debugging must stay identifier-and-status only
  • Client content must never be used in debugging
  • Fixes must be pinned with a test or manifest field in the same PR

How it compares

This skill focuses on maintaining the liveness and reliability of existing durable workflows with a structured diagnostic approach, rather than creating new ones or general system monitoring.

Compared to similar skills

durable-execution side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
durable-execution (this skill)023dNo flagsAdvanced
home-assistant-manager98moReviewAdvanced
observability-engineer123moNo flagsAdvanced
prometheus-configuration62moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

home-assistant-manager

komal-SkyNET

Expert-level Home Assistant configuration management with efficient deployment workflows (git and rapid scp iteration), remote CLI access via SSH and hass-cli, automation verification protocols, log analysis, reload vs restart optimization, and comprehensive Lovelace dashboard management for tablet-optimized UIs. Includes template patterns, card types, debugging strategies, and real-world examples.

9110

observability-engineer

sickn33

Build production-ready monitoring, logging, and tracing systems. Implements comprehensive observability strategies, SLI/SLO management, and incident response workflows. Use PROACTIVELY for monitoring infrastructure, performance optimization, or production reliability.

1242

prometheus-configuration

wshobson

Set up Prometheus for comprehensive metric collection, storage, and monitoring of infrastructure and applications. Use when implementing metrics collection, setting up monitoring infrastructure, or configuring alerting systems.

645

mlops-engineer

sickn33

Build comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools. Implements automated training, deployment, and monitoring across cloud platforms. Use PROACTIVELY for ML infrastructure, experiment management, or pipeline automation.

333

network-info

UKGovernmentBEIS

Gather network configuration and connectivity information including interfaces, routes, and DNS

329

senior-devops

davila7

Comprehensive DevOps skill for CI/CD, infrastructure automation, containerization, and cloud platforms (AWS, GCP, Azure). Includes pipeline setup, infrastructure as code, deployment automation, and monitoring. Use when setting up pipelines, deploying applications, managing infrastructure, implementing monitoring, or optimizing deployment processes.

720

Search skills

Search the agent skills registry