Provides command-line control over applications managed by the Armorer runtime.

Install

mkdir -p .claude/skills/armorer && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/9545" && unzip -o skill.zip -d .claude/skills/armorer && rm skill.zip

Installs to .claude/skills/armorer

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.

Act as the Armorer agent for end-to-end app setup and operations. Use Armorer commands first and verify before reporting success.
129 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Install managed agents
  • Stop agents
  • Uninstall agents
  • Verify agent status

How it works

Uses the Armorer CLI to manage the lifecycle of managed agents.

Inputs & outputs

You give it
Agent alias
You get back
Agent state

When to use armorer

  • Installing managed apps
  • Resetting Armorer state
  • Checking agent job status
  • Managing agent lifecycle

About this skill

Be The Armorer Agent

Use this skill when the task involves installing, configuring, running, repairing, or inspecting Armorer-managed apps.

Operator Surface Priority

Use these in order:

  1. Armorer TypeScript CLI
  2. Armorer-owned config and registry
  3. Raw shell only when Armorer has no clean equivalent

Prefer commands like:

pnpm armorer -- list
pnpm armorer -- install <agent> --yes --skip-scan
pnpm armorer -- run <agent>
pnpm armorer -- stop <agent>
pnpm armorer -- uninstall <agent> --force
pnpm armorer -- jobs list
pnpm armorer -- core status

Verification

Never report success from intent alone. Verify with concrete checks:

  • CLI output
  • job status in ~/.armorer/jobs/*.json
  • config state under ~/.armorer
  • service/container health
  • health endpoint where available

Clean Reset / Fresh Test State

When the user asks to clean up, reset, factory reset, or test Armorer from scratch, remove all active Armorer runtime leftovers, not only queue/job files.

Use Armorer-owned commands first where available:

pnpm armorer -- list
pnpm armorer -- stop <alias>
pnpm armorer -- uninstall <alias> --force
pnpm armorer -- core clear-queue
pnpm armorer -- core clear-jobs

If the pnpm armorer wrapper cannot resolve the CLI bin, use the built CLI entrypoint from the repository checkout:

node packages/cli/dist/index.js <command>

For a full local reset, stop the self-hosted UI/core process first, then delete the active ~/.armorer folder itself. Preserve ~/.armorer/training_data/ outside the folder first unless the user explicitly asks to delete training traces too. Recreate an empty ~/.armorer after deletion so the UI can bootstrap cleanly.

If deleting individual leftovers instead of the whole folder, remove these active state locations:

  • ~/.armorer/registry.json
  • ~/.armorer/jobs/
  • ~/.armorer/chats/
  • ~/.armorer/chats.backup-*
  • ~/.armorer/host_processes/
  • ~/.armorer/armorer.db
  • ~/.armorer/vault.json
  • ~/.armorer/armorer-vault.json
  • ~/.armorer/armorer-vault.key
  • ~/.armorer/.env
  • ~/.armorer/ui-api-token
  • ~/.armorer/ui-api.fingerprint
  • ~/.armorer/first_run_setup_completed.json
  • ~/.armorer/guard_settings.json
  • repo-local installed app checkouts such as installed/ and web/armorer-ui-selfhost/installed/

Do not casually delete ~/.armorer/training_data/; preserve or archive it unless the user explicitly asks to delete training traces.

After cleanup, restart the UI/core and verify:

  • node packages/cli/dist/index.js list shows zero agents for a fresh reset.
  • /api/status reports zero installed agents and zero jobs.
  • /api/chat/history?surface=manager returns an empty sessions array.
  • find ~/.armorer/chats -type f is empty, except for intentionally recreated default command-thread seed files if agents are still installed.

Implementation References

  • packages/core/src/
  • packages/agent-flue/src/
  • packages/cli/src/
  • catalog/playbooks/
  • web/armorer-ui-selfhost/src/app/api/

Armorer-Guard is external; call it through the configured external boundary.

When not to use it

  • Deleting training data without permission

Prerequisites

Armorer CLI

Limitations

  • Requires Armorer-owned commands
  • Must verify status after operations

How it compares

Provides a verified, managed lifecycle for agents rather than manual process management.

Compared to similar skills

armorer side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
armorer (this skill)02moReviewIntermediate
pnpm06moReviewIntermediate
turborepo612moReviewIntermediate
playwright-browser-automation297moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

pnpm

valibali

Use when managing Node.js dependencies with pnpm - provides workspace setup, catalogs, CLI commands, overrides, and CI configuration

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

playwright-browser-automation

lackeyjb

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

29146

codex-skill

feiskyer

Use when user asks to leverage codex, gpt-5, or gpt-5.1 to implement something (usually implement a plan or feature designed by Claude). Provides non-interactive automation mode for hands-off task execution without approval prompts.

12110

bullmq-specialist

davila7

BullMQ expert for Redis-backed job queues, background processing, and reliable async execution in Node.js/TypeScript applications. Use when: bullmq, bull queue, redis queue, background job, job queue.

2595

nuxthub-migration

onmax

Use when migrating NuxtHub projects or when user mentions NuxtHub Admin sunset, GitHub Actions deployment removal, self-hosting NuxtHub, or upgrading to v1/nightly. Covers v0.9.X self-hosting (stable) and v1/nightly multi-cloud (experimental, database/blob not ready).

589

Search skills

Search the agent skills registry