Skip to content
anyai.fyi

durable-agent-workflows

Skill from milad-ahmd/agent-skills

Development No risky patterns found contains scripts pythonlibrarydeploypipelineauditemail

Install

npx skills add milad-ahmd/agent-skills --skill durable-agent-workflows

Runs the open skills CLI and installs the skill for your agent (Claude Code, Codex, Cursor …). Alternatively copy the skill folder into .claude/skills/ or upload it in Claude.ai under Settings → Skills.

As a Claude Code plugin

/plugin marketplace add milad-ahmd/agent-skills /plugin install all-skills@milad-agent-skills

This skill is part of the plugin “all-skills”. In Claude Code the plugin installs it together with the plugin’s other skills, commands and hooks.

What does the durable-agent-workflows skill do?

Makes long-running, multi-step Python AI agent jobs crash-proof and resumable with the open-source rewindable library, so a failure at step 37 resumes there instead of re-running and re-paying for steps 1 to 36. Wraps each model call, tool call and side effect in a journaled step (ctx.step, ctx.llm), moves time, randomness and network reads behind ctx so replays match, puts emails, payments and deploys behind human approval, caps spend with a Budget, and proves it by killing a run and resuming it. Includes an AST audit script that flags calls breaking durable replay. Use when the user builds an LLM research pipeline, a batch job over many documents or an agent whose tools send email, pay or deploy, and wants it to survive crashes, resume after an exception without paying again, pause hours or days for a human approval, rewind a run to a step after fixing a bug, or asks for durable execution, checkpointing or human-in-the-loop for a Python agent.

Description from the SKILL.md in the source repository.

Questions about durable-agent-workflows

What does the durable-agent-workflows skill do?

Makes long-running, multi-step Python AI agent jobs crash-proof and resumable with the open-source rewindable library, so a failure at step 37 resumes there instead of re-running and re-paying for steps 1 to 36. Wraps each model call, tool call and side effect in a journaled step (ctx.step, ctx.llm), moves time, randomness and network reads behind ctx so replays match, puts emails, payments and deploys behind human approval, caps spend with a Budget, and proves it by killing a run and resuming it. Includes an AST audit script that flags calls breaking durable replay. Use when the user builds an LLM research pipeline, a batch job over many documents or an agent whose tools send email, pay or deploy, and wants it to survive crashes, resume after an exception without paying again, pause hours or days for a human approval, rewind a run to a step after fixing a bug, or asks for durable execution, checkpointing or human-in-the-loop for a Python agent.

How do I install durable-agent-workflows?

In a terminal: npx skills add milad-ahmd/agent-skills --skill durable-agent-workflows. The skills CLI asks which agents to install it for. In Claude.ai you can upload the skill folder as a ZIP under Settings → Skills.

Which agents can use durable-agent-workflows?

Skills use the open SKILL.md format, which Claude Code, Claude.ai, the Claude API, OpenAI Codex, Cursor, Gemini CLI and other agents support.

Is durable-agent-workflows safe to use?

Our automatic check found no risky patterns (piped shell scripts, hidden characters, secret access, prompt overrides). It is not a full audit – read the SKILL.md and any scripts before installing.

More skills from milad-ahmd/agent-skills

plan-griller
milad-ahmd/agent-skills

Grills the user about a planned feature or code change before any code is written. It reads the relevant code and docs first so every question is specific to the repo, asks …

Development
No risky patterns found
seo-blog-writer
milad-ahmd/agent-skills

Researches and writes SEO-optimized, genuinely helpful blog articles, covering keyword and search-intent analysis, competitor outline gaps, title and meta description, headings, FAQ, internal links, and schema, in the brand's voice and following …

Writing & Marketing
No risky patterns found
screenshot-to-component
milad-ahmd/agent-skills

Converts a screenshot, mockup, or Figma export into a production-ready UI component that reuses the project's existing design system (React/Next, Vue, Svelte, React Native, Flutter, or SwiftUI with Tailwind, CSS modules, or …

Frontend & UI
No risky patterns found
roast-my-github
milad-ahmd/agent-skills

Roasts a GitHub profile with humor, then gives genuinely useful advice. It analyzes public repos, stars, languages, missing descriptions and licenses, abandoned projects, lazy commit messages, and activity with a data script …

Development
No risky patterns found
readme-glow-up
milad-ahmd/agent-skills

Rewrites a repository's README into a polished, star-worthy page with badges, a hero tagline, demo section, quickstart, features, usage, and contributing info.

Writing & Marketing
No risky patterns found
prompt-injection-scanner
milad-ahmd/agent-skills

Scans an AI agent's instruction and tool-config files (CLAUDE.md, AGENTS.md, skills, slash commands, subagents, Cursor and Cline rules, hooks, MCP server configs) for prompt injection, hidden Unicode or HTML-comment instructions, exfiltration commands …

Agents & Workflows
Risky patterns
pr-reviewer-pro
milad-ahmd/agent-skills

Reviews a pull request or local branch diff like a senior engineer, covering correctness, security, performance, naming, and missing tests, and produces prioritized, actionable comments (optionally posted to GitHub).

Development
No risky patterns found
landing-page-roaster
milad-ahmd/agent-skills

Brutally honest but constructive critique of a landing page's copy, UX, design, and conversion. Gives a scored roast plus a prioritized fix list and rewritten headline and CTA options, working from a …

Frontend & UI
No risky patterns found

Related skills in Development

improve-codebase-architecture
mattpocock/skills

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Development 1268k installs curated
No risky patterns found
diagnosing-bugs
mattpocock/skills

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Development 933k installs curated
No risky patterns found
code-review
mattpocock/skills

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what …

Development 894k installs curated
No risky patterns found
research
mattpocock/skills

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.

Development 806k installs curated
No risky patterns found
appinsights-instrumentation
microsoft/azure-skills

Guidance for instrumenting webapps with Azure Application Insights. Provides telemetry patterns, SDK setup, and configuration references.

Development 702k installs curated
No risky patterns found
azure-resource-visualizer
microsoft/azure-skills

Analyze Azure resource groups and generate detailed Mermaid architecture diagrams showing the relationships between individual resources. WHEN: create architecture diagram, visualize Azure resources, show resource relationships, generate Mermaid diagram, analyze resource group …

Development 702k installs curated
No risky patterns found
azure-aigateway
microsoft/azure-skills

Configure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: semantic caching, token limit, content safety, load balancing, AI model governance, MCP rate limiting, jailbreak detection …

Development 701k installs curated
No risky patterns found
azure-messaging
microsoft/azure-skills

Troubleshoot and resolve issues with Azure Messaging SDKs for Event Hubs and Service Bus. Covers connection failures, authentication errors, message processing issues, and SDK configuration problems.

Development 693k installs curated
No risky patterns found