Enables command-line control for modifying Prefect resources.

Install

mkdir -p .claude/skills/prefect-cli && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12625" && unzip -o skill.zip -d .claude/skills/prefect-cli && rm skill.zip

Installs to .claude/skills/prefect-cli

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Prefect CLI commands for mutations. The MCP server is read-only - use this skill when you need to trigger deployments, cancel flow runs, create automations, or modify Prefect resources.
185 chars✓ has a “when” trigger
Intermediate

Key capabilities

  • Trigger Prefect deployments
  • Cancel Prefect flow runs
  • Delete Prefect flow runs
  • Delete Prefect deployments
  • Create Prefect automations from JSON or file
  • Access Prefect API directly with `prefect api`

How it works

The skill provides Prefect CLI commands for mutation operations, ensuring agent-friendly usage by disabling prompts and providing methods for raw JSON output and full UUID retrieval.

Inputs & outputs

You give it
Prefect resource UUIDs, names, or automation JSON/file
You get back
Modified Prefect resources (e.g., triggered deployment, cancelled flow run, created automation)

When to use prefect-cli

  • Triggering deployments
  • Cancelling flow runs
  • Deleting old deployments

About this skill

Prefect CLI

The MCP server is read-only. For mutations, use the CLI.

Critical: Agent-Friendly Usage

The CLI is designed for interactive terminal use. For non-interactive (agent) use:

# ALWAYS use --no-prompt as a TOP-LEVEL flag to disable confirmations
prefect --no-prompt flow-run delete <uuid>
prefect --no-prompt deployment delete <name>

Avoiding Truncated Output

Rich table output truncates IDs and names, making them useless. Solutions:

# Use `prefect api` for raw JSON (preferred for agents)
prefect api POST /flow_runs/filter --data '{"limit": 5}'

# Use inspect with -o json for single resources
prefect flow-run inspect <uuid> -o json
prefect deployment inspect <name> -o json

IDs Must Be Complete UUIDs

Partial IDs don't work. Always get full UUIDs from JSON output:

# Get full flow run ID
prefect api POST /flow_runs/filter --data '{"limit": 1}' | jq -r '.[0].id'

Common Mutations

TaskCommand
Trigger deploymentprefect deployment run 'flow-name/deployment-name'
Trigger by IDprefect deployment run --id <deployment-uuid>
Cancel flow runprefect --no-prompt flow-run cancel <uuid>
Delete flow runprefect --no-prompt flow-run delete <uuid>
Delete deploymentprefect --no-prompt deployment delete <name>

Direct API Access

prefect api gives full API access with JSON output:

# List flow runs (with filters)
prefect api POST /flow_runs/filter --data '{"limit": 10}'

# Filter by state
prefect api POST /flow_runs/filter --data '{"flow_runs": {"state": {"type": {"any_": ["FAILED"]}}}}'

# Delete a flow run
prefect api DELETE /flow_runs/<uuid>

# Cancel a flow run
prefect api POST /flow_runs/<uuid>/set_state --data '{"state": {"type": "CANCELLING"}}'

Automation Creation

Create from JSON string (inline):

prefect automation create --from-json '{
  "name": "notify-on-failure",
  "trigger": {
    "posture": "Reactive",
    "expect": ["prefect.flow-run.Failed"],
    "match": {"prefect.resource.id": "prefect.flow-run.*"}
  },
  "actions": [{"type": "send-notification", ...}]
}'

Or from file:

prefect automation create --from-file automation.yaml

Use get_automations() from the MCP server to inspect existing automation schemas.

<!-- ref: https://github.com/pydantic/pydantic-ai/pull/3780 -->

When not to use it

  • When only read-only operations are needed on the MCP server
  • When interactive terminal use is preferred over agent-friendly commands
  • When managing Prefect resources through the UI

Limitations

  • Requires `--no-prompt` for non-interactive agent use
  • Requires full UUIDs for resource identification, not partial IDs
  • Rich table output truncates IDs and names, requiring `prefect api` or `-o json` for full details

How it compares

This skill enables mutation operations on Prefect resources via the CLI, bypassing the read-only nature of the MCP server, which is not possible through standard read-only access.

Compared to similar skills

prefect-cli side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
prefect-cli (this skill)07moReviewIntermediate
mlops-engineer34moNo flagsAdvanced
senior-devops77moReviewAdvanced
teamcity-monitor17moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

mlops-engineer

sickn33

Build comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools. Implements automated training, deployment, and monitoring across cloud platforms. Use PROACTIVELY for ML infrastructure, experiment management, or pipeline automation.

333

senior-devops

davila7

Comprehensive DevOps skill for CI/CD, infrastructure automation, containerization, and cloud platforms (AWS, GCP, Azure). Includes pipeline setup, infrastructure as code, deployment automation, and monitoring. Use when setting up pipelines, deploying applications, managing infrastructure, implementing monitoring, or optimizing deployment processes.

720

teamcity-monitor

mikopbx

Мониторинг CI/CD пайплайна MikoPBX в TeamCity. Получение статусов сборок, анализ упавших тестов, доступ к логам и артефактам. Использовать после push в git или при анализе проблем сборки.

16

genkit-infra-expert

jeremylongshore

Execute use when deploying Genkit applications to production with Terraform. Trigger with phrases like "deploy genkit terraform", "provision genkit infrastructure", "firebase functions terraform", "cloud run deployment", or "genkit production infrastructure". Provisions Firebase Functions, Cloud Run services, GKE clusters, monitoring dashboards, and CI/CD for AI workflows.

15

monitor-ci

ever-co

Monitor Nx Cloud CI pipeline and handle self-healing fixes. USE WHEN user says "monitor ci", "watch ci", "ci monitor", "watch ci for this branch", "track ci", "check ci status", wants to track CI status, or needs help with self-healing CI fixes. Prefer this skill over native CI provider tools (gh, g

00

turborepo

vercel

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

61191

Search skills

Search the agent skills registry