Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Deploy

ASecurity

Plans and executes a deployment — verifies release readiness, build/tag, migration order, delegates the stack mutation to an installed deployment skill (container platform / Kubernetes / cloud) or produces manual runbook steps, runs post-deploy smoke checks, documents rollback. Every production mutation needs confirmation.

3 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsbashkubernetesgitdevops

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add gonimar/claude-web-studio --skill deploy --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Deploy?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Deploy
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/gonimar-deploy/badge)](https://www.skillsdirectory.com/skills/gonimar-deploy)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: deploy
description: "Plans and executes a deployment — verifies release readiness, build/tag, migration order, delegates the stack mutation to an installed deployment skill (container platform / Kubernetes / cloud) or produces manual runbook steps, runs post-deploy smoke checks, documents rollback. Every production mutation needs confirmation."
argument-hint: "[version | --env staging|prod] [--plan-only]"
user-invocable: true
allowed-tools: Read, Glob, Grep, Bash, Write, Task, AskUserQuestion
model: sonnet
agent: devops-lead
---

# Deploy

Prerequisites & secrets per `docs/deploy-target-contract.md`: verify registry access, exact image names and the stack method before the first mutation; secrets never through the chat — offer the env/file channel yourself; a refused path stays refused.


Reply in the project conversation language (CLAUDE.md → Language); code, identifiers, paths and commit messages stay in English.

File writes and any mutation (git, deploy) happen only after an explicit "May I write?" / "Proceed?" — each one `AskUserQuestion` (proceed (Recommended) · show the draft/diff first · not now) → "yes"; delegated agents follow the same protocol. After the "write" answer: `touch .claude/.write-consent` (rule 7 — the consent-guard hook checks the marker).

## Phase 1: Readiness
`production/releases/vX.Y.Z.md` (missing → `/release-checklist`); the tag exists; CI green on the tag (`gh run`); the image is built/available; runbook `docs/ops/deploy.md`; the deploy target and delegate from `technical-preferences.md` (Infrastructure) and `docs/deploy/<target>.md` — contract: `docs/deploy-target-contract.md`.

## Phase 2: Plan
Steps: DB backup → migrations (migrate service/command) → stack redeploy → smoke (healthz, key journey, GraphQL `{ __typename }`/REST ping) → 30 min monitoring; rollback: previous tag + migration reversibility. `--plan-only` — stop.

## Phase 3: Execute
By the declared delegate (`docs/deploy-target-contract.md`): `agent <name>` → `Task` to that agent with the prompt `deploy <tag> --confirmed` (after the user's "Proceed?" → "yes" here — the delegate never asks itself); `script <path>` → `Bash` `<path> deploy <tag> --confirmed`; `none`/`manual` → the runbook steps for the user/`devops-engineer`. A delegate declared but not found (no agent file, no script) → `BLOCKED (delegate <name> not found — fix technical-preferences or run /setup-stack)`, never a guess. A companion slash command alone (`/<kit> deploy`) is not a delegate: skills cannot call skills. Read the verdict line (`DEPLOYED <tag>` | `FAILED (…)`) and the evidence; then run the runbook smoke checks yourself (`/healthz`, key journey) — the delegate's verdict is necessary, not sufficient. A failed smoke check or an unhealthy container → one `AskUserQuestion`: `rollback` to the previous tag via the delegate (Recommended) · investigate first (`logs`) · keep — never leave a red deploy without that question. **Every production mutation after an explicit "yes".** Verify by containers and smoke requests, not by response codes.

## Phase 4: Record
Update `production/releases/vX.Y.Z.md` (time, result, who); `docs/ops/deploy.md` when the procedure changed.

Verdict: `DEPLOYED` | `ROLLED BACK` | `PLAN` | `BLOCKED (delegate …)`. Next step — one `AskUserQuestion`: monitor the release (`/incident` on problems) (Recommended) · `/deploy rollback` · `/sprint-plan` for the next cycle.

Attribution

gonimargonimar
View sourceMore from gonimar →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →