Ship Prod logo

Ship Prod

Community
PramodDutta
ship-prod

Use when deploying qaskills.sh to production, verifying whether a deploy landed, or when a push to main did not show up on the live site, e.g. "deploy", "ship it", "push this live", "is prod updated?", "the site still shows the old version".

Overview

PublisherPramodDutta
Repositoryqaskills
Skill nameship-prod
Stars
239
Forks
31
Bundled files
Instructions only
LicenseMIT
Links
  • 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 PramodDutta on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/PramodDutta/qaskills/tree/main/.claude/skills/ship-prod
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

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/PramodDutta/qaskills.git /tmp/qaskills
mkdir -p .claude/skills
cp -r /tmp/qaskills/.claude/skills/ship-prod .claude/skills/ship-prod
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ship Prod 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 Ship Prod 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 Ship Prod 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.

Ship Prod

Deploys COMMITTED HEAD only, to the correct Vercel project, then proves the deploy landed. git push to main does not reliably auto-deploy; this skill is the deploy path.

Fixed facts

  • Project: qaskills.sh, project ID prj_rDKli4AyhHoXZXV8NHrs92Ncbf4f, org team_DGM6VSs6vhASlhktmHkSqPwn, account luckydutta96
  • A decoy project qaskills exists WITHOUT the domain. Never deploy there. Never accept interactive "link this directory?" defaults.
  • Build command lives in root vercel.json (shared build && web build); Node is pinned to 24.x via engines in packages/web/package.json (Vercel stopped building 20.x on 2026-10-01; the Neon HTTP driver is verified on 24)
  • vercel --prod uploads the WORKING TREE, not git HEAD
  • .vercel/project.json is gitignored, so fresh worktrees are unlinked: explicit env IDs required there

Preflight

bash
cd /Users/promode/qaskills
vercel whoami                              # must be luckydutta96; else STOP, user must vercel login
git status --short                         # empty => clean path; anything => worktree path
git log -1 --oneline --stat | head -15     # confirm HEAD is exactly what you intend to ship
pnpm --filter @qaskills/shared build && pnpm --filter @qaskills/web build   # never ship a red build

Deploy

Clean tree (no modified or untracked files that could ship):

bash
cd /Users/promode/qaskills && npx vercel --prod --yes

Dirty tree (default assumption; the working tree here usually carries WIP):

bash
DEPLOY_DIR=$(mktemp -d)/qaskills-deploy
git -C /Users/promode/qaskills worktree add "$DEPLOY_DIR" HEAD
cd "$DEPLOY_DIR"
VERCEL_ORG_ID=team_DGM6VSs6vhASlhktmHkSqPwn \
VERCEL_PROJECT_ID=prj_rDKli4AyhHoXZXV8NHrs92Ncbf4f \
npx vercel --prod --yes
cd /Users/promode/qaskills
git worktree remove "$DEPLOY_DIR" --force

Capture the deployment URL the CLI prints; it goes in the final summary.

Verify (required, every deploy)

bash
npx vercel ls | head -5                                         # newest deployment: Ready, Production
curl -s -o /dev/null -w '%{http_code}\n' https://qaskills.sh    # 200
# The specific change, visible live. Examples:
curl -s -o /dev/null -w '%{http_code}\n' https://qaskills.sh/blog/<new-slug>   # new article: 200
curl -s https://qaskills.sh/<changed-page> | grep -c '<expected-marker>'       # code change: >= 1

All three must pass before saying "deployed". If the domain still serves old content while the new deployment is Ready, the alias did not move: npx vercel promote <deployment-url>.

Rollback

bash
npx vercel ls                       # find the previous Ready production deployment
npx vercel promote <previous-url>   # fast path: point the domain back

For a code-level revert, git revert <sha> on main, then run this skill again.

Failure modes

SymptomCauseFix
CLI asks to link / offers project qaskillsUnlinked dir, interactive defaultsAbort; re-run with both VERCEL_* env vars set
Error: not authorized / wrong scopeLogged into another accountvercel whoami; user runs vercel login as luckydutta96
Vercel build fails, local build greenEnv-dependent code at import timeLazy-init pattern (see CLAUDE.md); no secrets required at build
Deploy Ready but site unchangedDomain alias on older deployment, or you shipped stale HEADvercel promote; confirm intended commit was in HEAD
WIP appeared on prodDeployed dirty working tree directlyRoll back via promote, then redeploy via worktree

Red flags

  • "The push probably triggered a deploy"
  • Deploying from a dirty root without the worktree
  • Answering Vercel's interactive prompts with defaults
  • Declaring success without the three verification commands' output
  • Touching Vercel project settings (Node version, env vars, domains) without user approval

Frequently asked questions

What does the Ship Prod AI skill do?

Use when deploying qaskills.sh to production, verifying whether a deploy landed, or when a push to main did not show up on the live site, e.g. "deploy", "ship it", "push this live", "is prod updated?", "the site still shows the old version".

Why use Ship Prod on TypingMind?

Because you install it once and use it with any model. Ship Prod 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 Ship Prod in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/PramodDutta/qaskills/tree/main/.claude/skills/ship-prod. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ship Prod?

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 Ship Prod?

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

Is the Ship Prod AI skill free?

Yes. It is published on GitHub by PramodDutta 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇