How do I install the Portainer Stack Troubleshooter skill?

Run npx skillmds@latest add knuckles-team/portainer-stack-troubleshooter in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Portainer Stack Troubleshooter safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Portainer Stack Troubleshooter?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Portainer Stack Troubleshooter free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Portainer Stack Troubleshooter?

Knuckles-Team (@knuckles-team) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Portainer Stack Troubleshooter by knuckles-team

Name: Portainer Stack Troubleshooter
Author: Knuckles-Team

File contents

Portainer Stack Troubleshooter Workflow

CONCEPT:INFRA-001

Identifies stopped or unhealthy containers inside Portainer stacks, aggregates logs, and creates a step-by-step resolution plan using portainer-agent and tunnel-manager.

Steps

Step 0: inspect-portainer-stacks [skill: portainer-agent]

Agent: discovery-agent Tools: tun_tm_system, tun_tm_hosts

Retrieve active stacks list using portainer_stack get_stacks tool, and retrieve the full list of running and stopped containers using portainer_docker docker_list_containers tool. Expected: portainer_stacks, containers_status

Step 1: User Interaction

Agent: deployer-agent Tools: pt_stack, cnt_cm_compose_operations

Scan containers_status to isolate unhealthy, degraded, or stopped instances. Construct a visual status dashboard highlighting failed stacks and down services. Expected: stack_triage_dashboard

Step 2: diagnose-portainer-stack [skill: portainer-agent]

Agent: verifier-agent Tools: pt_docker, cnt_cm_container_operations

For the identified failed containers, fetch the diagnostic logs using portainer_docker docker_get_container_logs tool. Suggest precise stack-level updates or restart commands. Expected: container_diagnostics, resolution_plan

Step 3: KG Persistence [depends_on: Step 0, Step 2]

Agent: verifier-agent Tools: graph_write

Persist workflow results as nodes and edges in the Knowledge Graph. Create appropriate typed nodes with metadata and link to existing domain entities.

Output

Portainer Stack Troubleshooter results persisted in KG
Structured report (MD/PDF)
Audit trail with timestamps and agent attributions

Execution

Run this workflow as a dependency-ordered DAG. Steps with no unmet depends_on run in parallel; dependents run after their prerequisites complete.

Run first (in parallel): Step 0 — inspect-portainer-stacks; Step 1 — User Interaction; Step 2 — diagnose-portainer-stack
After level 0: Step 3 — KG Persistence

Execution: If graph-os is reachable, offload the whole DAG via graph_orchestrate action=execute_workflow (or the kg-delegate skill) for true parallel/swarm execution. Otherwise execute the steps natively in dependency order: run steps with no unmet depends_on in parallel, then their dependents.

---name: portainer-stack-troubleshooterdescription: Identifies stopped or unhealthy containers inside Portainer stacks, aggregates logs, and creates a step-by-step resolution plan using portainer-agent and tunnel-manager.---# Portainer Stack Troubleshooter Workflow**CONCEPT:INFRA-001**Identifies stopped or unhealthy containers inside Portainer stacks, aggregates logs, and creates a step-by-step resolution plan using portainer-agent and tunnel-manager.## Steps### Step 0: inspect-portainer-stacks [skill: portainer-agent]**Agent**: `discovery-agent`**Tools**: `tun_tm_system, tun_tm_hosts`Retrieve active stacks list using portainer_stack get_stacks tool, and retrieve the full list of running and stopped containers using portainer_docker docker_list_containers tool.Expected: `portainer_stacks, containers_status`### Step 1: User Interaction**Agent**: `deployer-agent`**Tools**: `pt_stack, cnt_cm_compose_operations`Scan containers_status to isolate unhealthy, degraded, or stopped instances. Construct a visual status dashboard highlighting failed stacks and down services.Expected: `stack_triage_dashboard`### Step 2: diagnose-portainer-stack [skill: portainer-agent]**Agent**: `verifier-agent`**Tools**: `pt_docker, cnt_cm_container_operations`For the identified failed containers, fetch the diagnostic logs using portainer_docker docker_get_container_logs tool. Suggest precise stack-level updates or restart commands.Expected: `container_diagnostics, resolution_plan`### Step 3: KG Persistence [depends_on: Step 0, Step 2]**Agent**: `verifier-agent`**Tools**: `graph_write`Persist workflow results as nodes and edges in the Knowledge Graph.Create appropriate typed nodes with metadata and link to existing domain entities.## Output- Portainer Stack Troubleshooter results persisted in KG- Structured report (MD/PDF)- Audit trail with timestamps and agent attributions## ExecutionRun this workflow as a dependency-ordered DAG. Steps with no unmet `depends_on` run in parallel; dependents run after their prerequisites complete.- **Run first (in parallel):** Step 0 — inspect-portainer-stacks; Step 1 — User Interaction; Step 2 — diagnose-portainer-stack- **After level 0:** Step 3 — KG Persistence**Execution:** If graph-os is reachable, offload the whole DAG via `graph_orchestrate action=execute_workflow` (or the `kg-delegate` skill) for true parallel/swarm execution. Otherwise execute the steps natively in dependency order: run steps with no unmet `depends_on` in parallel, then their dependents.

Frequently asked questions

Portainer Stack Troubleshooter