restate

0
C

Restate durable execution for fault-tolerant services and workflows. Triggers on restate, durable, ctx.run, ctx.sleep, awakeable.

CommandsAgentsMarketplace
#restate#durable#restate description#fault-tolerant services#mcp#Build durable#Restate server#Restate durable

Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security

Installation for Agentic Skill

View all platforms →
skilz install settlemint/agent-marketplace/restate
skilz install settlemint/agent-marketplace/restate --agent opencode
skilz install settlemint/agent-marketplace/restate --agent codex
skilz install settlemint/agent-marketplace/restate --agent gemini

First time? Install Skilz: pip install skilz

Works with 14 AI coding assistants

Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...

View All Agents
Download Agent Skill ZIP

Extract and copy to ~/.claude/skills/ then restart Claude Desktop

1. Clone the repository:
git clone https://github.com/settlemint/agent-marketplace
2. Copy the agent skill directory:
cp -r agent-marketplace/devtools/skills/restate ~/.claude/skills/

Need detailed installation help? Check our platform-specific guides:

Related Agentic Skills

Agentic Skill Details

Type
Other
Meta-Domain
Primary Domain
Market Score
0

Agent Skill Grade

C
Score: 76/100 Click to see breakdown

Score Breakdown

Spec Compliance
13/15
PDA Architecture
19/30
Ease of Use
22/25
Writing Style
8/10
Utility
16/20
Modifiers: -2

Areas to Improve

  • Missing references architecture
  • Missing TOC for 257-line file
  • Verbose research section

Recommendations

  • Address 1 high-severity issues first
  • Add trigger phrases to description for discoverability
  • Add table of contents for files over 100 lines

Graded: 2026-01-19

Developer Feedback

I took a look at your restate skill and wanted to share some thoughts.

Links:

The TL;DR

You're at 76/100, solidly in C territory (70-79). This is based on Anthropic's best practices for skill architecture.

The good news: Your metadata and ease of use are solid (22/25 on EoU). Strong trigger coverage and clean terminology around ctx, durable, and handler.

The rough patch: Progressive Disclosure Architecture is dragging you down (19/30). You've got 257 lines crammed into a single file with no reference architecture, and that's eating your score.

What's Working Well

  • Frontmatter is chef's kiss — Valid YAML, specific name, and a comprehensive trigger list that actually captures intent patterns (durable execution, distributed workflows, Virtual Objects)
  • Consistent terminology — Using ctx, durable, and handler throughout makes it predictable for developers
  • Real-world patterns — Code examples showing services, workflows, and Virtual Objects demonstrate genuine value for distributed systems problems
  • Success criteria checklist — Actually helpful for validation

The Big One: Monolithic File Architecture

Severity: High | Impact: +6 points possible

Your 257-line skill violates the layered structure principle. Everything — extended patterns, research examples, detailed code — is inline, which inflates token load for simple queries.

The fix: Extract into a references directory:

  • Move patterns section → references/patterns.md
  • Move research section (lines 203-224) → references/research.md
  • Keep SKILL.md under 150 lines for quick navigation

This is the single biggest lever for improvement. You'd jump from 19/30 to 25/30 on PDA alone.

Other Things Worth...

AI-Detected Topics

Extracted using NLP analysis

restate durable restate description fault-tolerant services mcp Build durable Restate server Restate durable services Service

Report Security Issue

Found a security vulnerability in this agent skill?