Deploy Checklist

Community

agulli

deploy-checklist

Execute a structured deployment to staging or production. Use when asked to deploy, ship, release, push to production, or promote to staging.

Overview

Publisher	agulli
Repository	`atlas-agents`
Skill name	`deploy-checklist`
Stars	580
Forks	127
Bundled files	Instructions only
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by agulli on GitHub. Read the source before you install it.

Installation

Install the Deploy Checklist AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/agulli/atlas-agents/tree/main/ch09_agent_skills/skills/deploy-checklist
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/agulli/atlas-agents/tree/main/ch09_agent_skills/skills/deploy-checklist

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/agulli/atlas-agents.git /tmp/atlas-agents
mkdir -p .claude/skills
cp -r /tmp/atlas-agents/ch09_agent_skills/skills/deploy-checklist .claude/skills/deploy-checklist

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Deploy Checklist in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Deploy Checklist on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Deploy Checklist is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Clarification Gates

You must have unambiguous answers to these before touching anything:

Target: staging or production? (Never assume. Never infer from branch name.)
Deploying what: which service, which version/tag/commit SHA?
Rollback plan: does one exist, and do you have access to execute it?

If the user says "deploy the thing" without specifying the environment, that is not sufficient information. Ask.

Model Proposes, Code Disposes: You propose the deploy sequence. The CI/CD system or platform CLI executes it. You do not write deployment commands from memory — you use exactly the command documented in the project's deploy runbook or Makefile.

Pre-deployment

Confirm the target environment. Ask if not specified: staging or production? Never assume production.

Check the branch. Verify you are on the correct branch:

bash
git branch --show-current

Check for uncommitted changes:
```
bash
git status --porcelain
```
If there are uncommitted changes, STOP. Commit or stash them first.
Run the test suite. Execute the project's full test command. If any test fails, STOP. Do not deploy with failing tests.
Check the changelog/diff. Run git log --oneline main..HEAD to see what will be deployed. Present this to the user.

Deployment

Execute the deploy command. Use the project's existing deployment mechanism:
- Docker: docker build && docker push
- Kubernetes: kubectl apply -f
- Platform-specific: fly deploy, vercel --prod, gcloud run deploy Use exactly the command documented in the project. Do not invent deployment commands.
Wait for deployment to complete. Do not proceed until the deployment tool confirms success.

Post-deployment

Smoke test. Hit the health endpoint or run a basic functional test:

bash
curl -s https://<deployed-url>/health | jq .

Monitor for 2 minutes. Check error rates and latency. If either spikes, recommend an immediate rollback.

Rationalizations

Excuse	Rebuttal
"Tests are slow, I'll skip them"	Deploying untested code is how you get paged at 3 AM. Run the tests.
"It works on my machine"	That is not evidence. The test suite is evidence.
"I'll just deploy and fix issues as they come"	You have no rollback plan if you don't know what changed. Check the diff first.

Verification

Target environment was explicitly confirmed (not assumed)
All tests passed before deployment
Deployment tool reported success
Health check returned 200 after deployment
No error spike observed in the first 2 minutes

Frequently asked questions

What does the Deploy Checklist AI skill do?

Execute a structured deployment to staging or production. Use when asked to deploy, ship, release, push to production, or promote to staging.

Why use Deploy Checklist on TypingMind?

Because you install it once and use it with any model. Deploy Checklist is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Deploy Checklist in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/agulli/atlas-agents/tree/main/ch09_agent_skills/skills/deploy-checklist. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Deploy Checklist?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Deploy Checklist?

As many as you like. As long as a model supports skills, you can use Deploy Checklist with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Deploy Checklist AI skill free?

Yes. It is published on GitHub by agulli under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Insight Error Page

vercel

OrganizationPopular

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new `errors/<slug>.mdx` page, auditing an existing one, or checking that a page matches the framework fix…

Mcp Apps Builder

**MANDATORY for ALL MCP server work** - mcp-use framework best practices and patterns. **READ THIS FIRST** before any MCP server work, including: - Creating new MCP servers - Modifying existing MCP…

Canary

Post-deploy canary monitoring. (gstack)

Land And Deploy

Land and deploy workflow. (gstack)

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Clarification Gates

Pre-deployment

Deployment

Post-deployment

Rationalizations

Verification

Frequently asked questions

Related AI Skills

Set up your own AI workspace now