agentsclimarketplace

Deploy plan

Skill EntityProcess/agentv/evals/agentic-engineering/workspace-template/plugins/deploy-auto/skills/deploy-plan

Light-weight AI agent evaluation and optimization framework

Install
npx -y skills add EntityProcess/agentv --skill deploy-plan

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 14 stars14 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

This skill should be used when asked to "plan a deployment", "create a deploy plan", or "prepare release steps". Produces a deployment plan with rollback strategy.

SKILL.md

1.2 KB, as published. Nobody here has run it

Deploy Plan Skill

Purpose

Create a structured deployment plan from a release specification. Produces {output_dir}/deploy-plan.md with step-by-step instructions, dependency ordering, and rollback checkpoints.

When to Use

  • Planning a new deployment from a release spec
  • Coordinating multi-service deployments with dependency ordering
  • Generating rollback checkpoints for each deployment step

Process

  1. Read the release specification
  2. Identify affected services and their dependencies
  3. Order deployments by dependency graph (databases first, then backends, then frontends)
  4. For each service, define: pre-deploy checks, deploy command, health check, rollback command
  5. Write {output_dir}/deploy-plan.md

Phase Handoff

After completing the plan, tell the user:

"Next step — run: /deploy-execute {output_dir} Or let the orchestrator continue automatically."

Skill Resources

  • references/deployment-patterns.md — Common deployment patterns and anti-patterns

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.