Skip to content
Agentmart
Submit a tool

deploy

Use when the developer explicitly asks to merge, deploy, release, roll out, or promote a ready pull request or stack.

Skill by kristofferremback

IndexedMIT
Write a review

Chalk Labs

Need help deploying deploy?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/kristofferremback-deploy

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when the developer explicitly asks to merge, deploy, release, roll out, or promote a ready pull request or stack.

Use cases: devops

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/deploy

What's inside

Skill name
deploy
Description
Use when the developer explicitly asks to merge, deploy, release, roll out, or promote a ready pull request or stack.
License
MIT
Instructions
30 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Deploy

Merge and rollout are external-impact actions. Start only after explicit developer approval. A request to build, ship, or make work ready is not approval.

## Confirm the gate

1. Identify the exact PRs, contiguous stack, revisions, target environment, and rollout path covered by approval.
2. Confirm `shepherd` reached ready state at the current heads.
3. Read repository deployment guidance and runbooks. Load vendor skills such as Railway's `use-railway` when the repository requires them.
4. Verify required credentials and production signals exist. Report missing dependencies; never switch to an unapproved path.

If approval is ambiguous about any PR, environment, migration, or rollout step, ask in ordinary text and continue only unblocked inspection.

## Merge and roll out

- Treat the approved PR set or contiguous stack as the delivery unit. Preserve its reviewed order and relationships using the repository's stack or merge-queue workflow.
- At a blocked gate, diagnose against the current heads first. Before a workaround, identify checks, approvals, or proof it invalidates across the delivery unit and the downstream work it creates. Choose the supported path that advances the whole outcome with the least avoidable rework. Partial merges and rebases can change downstream heads; inspect the tooling's behavior before using them as a workaround.
- Explain a material change in delivery strategy and its downstream cost before acting. Continue within existing authorization; ask only when the change needs a decision beyond it. Routine steps in an approved merge queue or a necessary rebase follow repository guidance.
- Record every merged commit and deployed revision.
- Follow the repository's release path exactly. Do not improvise provider, environment, or migration behavior.
- Keep operations retryable and observable. Stop on unknown partial state.
- Apply activated backfills only after compatible code is live, using `migrate` and the repository runbook.

## Hand off to monitoring

Invoke `monitor` with the expected revision, environment, behavior, rollout time, and relevant risks. A green merge or deployment pipeline is not proof that production is correct.

Report direct links, revisions, rollout status, and caveats. Do not claim success until `monitor` proves it.

From kristofferremback/slopestyle, MIT.

More from kristofferremback/slopestyle

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 15, 2026 (17 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from kristofferremback

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get deploy running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying deploy?

CallGet help
Cite this page

deploy skill. Agent Mart. https://agentmart.dev/skills/kristofferremback-deploy (last updated 2026-10-24)