Install the "deploy-checklist" agent skill from https://github.com/agulli/atlas-agents/tree/main/ch09_agent_skills/skills/deploy-checklist into .claude/skills/deploy-checklist/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deploy-checklist", then confirm the skill loads.
Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
skills CLI
$ npx skills add agulli/atlas-agents --skill deploy-checklist -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "deploy-checklist" agent skill from https://github.com/agulli/atlas-agents/tree/main/ch09_agent_skills/skills/deploy-checklist into .agents/skills/deploy-checklist/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deploy-checklist", then confirm the skill loads.
Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add agulli/atlas-agents --skill deploy-checklist -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "deploy-checklist" agent skill from https://github.com/agulli/atlas-agents/tree/main/ch09_agent_skills/skills/deploy-checklist into .cursor/skills/deploy-checklist/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deploy-checklist", then confirm the skill loads.
Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add agulli/atlas-agents --skill deploy-checklist -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "deploy-checklist" agent skill from https://github.com/agulli/atlas-agents/tree/main/ch09_agent_skills/skills/deploy-checklist into .gemini/skills/deploy-checklist/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deploy-checklist", then confirm the skill loads.
Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
skills CLI
$ npx skills add agulli/atlas-agents --skill deploy-checklist -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "deploy-checklist" agent skill from https://github.com/agulli/atlas-agents/tree/main/ch09_agent_skills/skills/deploy-checklist into .github/skills/deploy-checklist/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deploy-checklist", then confirm the skill loads.
GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add agulli/atlas-agents --skill deploy-checklist -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "deploy-checklist" agent skill from https://github.com/agulli/atlas-agents/tree/main/ch09_agent_skills/skills/deploy-checklist into .opencode/skills/deploy-checklist/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deploy-checklist", then confirm the skill loads.
OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
Skill name
deploy-checklist
GitHub stars
578
Token cost
~756 tokens
SKILL.md length
364 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
MIT
At a glance
Execute a structured deployment to staging or production. An agent skill from agulli/atlas-agents.
Works in 5 steps: Confirm the target environment. Ask if… → Check the branch. Verify you are on the… → Check for uncommitted changes → …
Asked to deploy
SKILL.md covers Clarification Gates, Rationalizations and Verification
Calls git, docker and curl
What it does
Deploy Checklist is an agent skill from agulli/atlas-agents. Execute a structured deployment to staging or production. Use when asked to deploy, ship, release, push to production, or promote to staging.
Its SKILL.md is about 760 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Requires git and access to the deployment target
It sits in DevOps & Cloud, covering Deployment. It works with Docker. The licence is MIT.
When your agent uses it
Asked to deploy
Push to production
Promote to staging
Example prompts
“/deploy-checklist”
Requirements
Docker
Compatibility (from SKILL.md): Requires git and access to the deployment target
5 steps, taken from the first numbered list in SKILL.md.
1Confirm the target environment. Ask if not specified: staging or production? Never assume production.
2Check the branch. Verify you are on the correct branch
3Check for uncommitted changes
4Run the test suite. Execute the project's full test command. If any test fails, STOP. Do not deploy with failing tests.
5Check the changelog/diff. Run git log --oneline main..HEAD to see what will be deployed. Present this to the user.
What it can do on your machine
Read from SKILL.md and the folder at commit 2b21998. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
Bash(git:*)
Bash(docker:*)
Bash(kubectl:*)
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
git
docker
curl
jq
kubectl
fly
vercel
gcloud
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, docker, curl, kubectl, vercel and gcloud, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Compatibility
Requires git and access to the deployment target
From compatibility in the SKILL.md frontmatter.
Context cost
Deploy Checklist loads about 756 tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 364 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~40
When it runs· the whole SKILL.md, loaded when a task matches
~756
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
Download SKILL.mdSave it as .claude/skills/deploy-checklist/SKILL.md (or your agent's skills folder).
name
deploy-checklist
description
Execute a structured deployment to staging or production. Use when asked to deploy, ship, release, push to production, or promote to staging.
allowed-tools
Bash(git:*), Bash(docker:*), Bash(kubectl:*)
compatibility
Requires git and access to the deployment target
license
MIT
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.
Show full SKILL.md (129 more words)Show less
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)
Deploy Checklist next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
Packages a locally built GreptimeDB debug binary into a development-only Docker image for local-cluster testing, with an optional push to a dev registry.
Deploys and configures a LangBot instance with Docker Compose or Kubernetes, covering config.yaml, the Box sandbox runtime, the plugin runtime and the global API key.
Turn Chinese classical poems and ci into coherent vertical Chinese-art videos with poem-driven scene grouping, GPT ImageGen stills, Docker-only Gemini I2V, retained model-generated ambience, Gemini…
Execute a structured deployment to staging or production. An agent skill from agulli/atlas-agents. Deploy Checklist is an agent skill from agulli/atlas-agents. Execute a structured deployment to staging or production.
When should I use Deploy Checklist?
Deploy Checklist fits situations like: asked to deploy; push to production; promote to staging.
How do I install Deploy Checklist in Claude Code?
Run `npx skills add agulli/atlas-agents --skill deploy-checklist -a claude-code`. Or copy the skill folder (ch09_agent_skills/skills/deploy-checklist in agulli/atlas-agents) into .claude/skills/deploy-checklist in your project. Claude Code loads it when a task matches its description.
How do I install Deploy Checklist in Codex?
Run `npx skills add agulli/atlas-agents --skill deploy-checklist -a codex`. Or copy the skill folder (ch09_agent_skills/skills/deploy-checklist in agulli/atlas-agents) into .agents/skills/deploy-checklist in your project. Codex loads it when a task matches its description.
Can I use Deploy Checklist in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agulli/atlas-agents --skill deploy-checklist -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deploy-checklist, .gemini/skills/deploy-checklist, .github/skills/deploy-checklist and .opencode/skills/deploy-checklist in your project.
What does Deploy Checklist need to run?
Going by SKILL.md and its folder, Deploy Checklist needs the command-line tools its instructions call (git, docker, curl, jq, kubectl and fly). Our summary lists: Docker. Its frontmatter pre-approves these tools: Bash(git:*), Bash(docker:*), Bash(kubectl:*). Compatibility (from SKILL.md): Requires git and access to the deployment target.
Does Deploy Checklist access the network?
SKILL.md contains no URLs. Its commands use git, docker and curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Deploy Checklist safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Deploy Checklist use?
Deploy Checklist is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Deploy Checklist use?
About 756 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Deploy Checklist?
Skills that share tags, products or a category with Deploy Checklist: GreptimeDB Dev Docker Image (GreptimeTeam/greptimedb, 6.7k stars), Senior DevOps Toolkit (maslennikov-ig/claude-code-orchestrator-kit, 259 stars), LangBot Deployment Guide (langbot-app/LangBot, 18k stars) and Reflexo Release (Myriad-Dreamin/typst.ts, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Deploy Checklist?
agulli (a GitHub user) maintains it in agulli/atlas-agents, which has 578 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on July 17, 2026.
Source: agulli/atlas-agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
