New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Talos Helper

by shepherdjerred in shepherdjerred/monorepo

Talos Linux cluster administration using talosctl When user mentions Talos, talosctl, or Talos cluster operations

GPL-3.0Auto-check passedDevOps & Cloud

Install Talos Helper

skills CLI
$ npx skills add shepherdjerred/monorepo --skill talos-helper -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install shepherdjerred/monorepo talos-helper --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/shepherdjerred/monorepo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/dotfiles/dot_agents/skills/talos-helper .claude/skills/talos-helper && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
talos-helper
GitHub stars
112
Token cost
~3.3k tokens
SKILL.md length
538 words
Files
1
Skills in repo
63
Repo updated
First seen
Licence
GPL-3.0

At a glance

Talos Linux cluster administration using talosctl When user mentions Talos, talosctl, or Talos cluster operations

  • Works in 9 steps: Backup Secrets: Always backup… → Use Multi-Endpoint Configuration:… → Staged Upgrades: Upgrade one node at a… → …
  • Talos cluster operations
  • SKILL.md covers What's New in 2025, Overview, CLI Commands and Cluster Bootstrapping, plus 6 more sections
  • Calls kubectl and git

What it does

Talos Helper is an agent skill from shepherdjerred/monorepo. Talos Linux cluster administration using talosctl When user mentions Talos, talosctl, or Talos cluster operations

Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud, covering Container orchestration. It works with Linux and Kubernetes. The repository describes itself as: Monorepo for all of my projects. The licence is GPL-3.0.

When your agent uses it

  • Talos cluster operations
  • Tasks that involve Container orchestration

Example prompts

  • “Use the talos-helper skill to talo Linux cluster administration using talosctl When user mentions Talos, talosctl, or Talos cluster operations”
  • “/talos-helper”

Requirements

  • Docker

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

  1. Backup Secrets: Always backup secrets.yaml file
  2. Use Multi-Endpoint Configuration: Provides automatic failover
  3. Staged Upgrades: Upgrade one node at a time, start with workers
  4. Health Checks: Verify cluster health before and after changes
  5. Configuration as Code: Store Talos configs in version control (git)
  6. Use Patches: Apply configuration changes via patches, not full rewrites
  7. Test in Dev: Use QEMU for local testing before production
  8. Image Cache: Use talosctl image cache-serve for faster deployments
  9. Monitor Kernel Parameters: Check KSPP compliance regularly

What it can do on your machine

Read from SKILL.md and the folder at commit bc57ca5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • kubectl
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use kubectl and git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Talos Helper loads about 3.3k tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 538 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~32
When it runs · the whole SKILL.md, loaded when a task matches
~3.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from shepherdjerred/monorepo at commit bc57ca5, republished under its GPL-3.0 licence (© shepherdjerred). 538 words, ~3,309 tokens.

Download SKILL.mdSave it as .claude/skills/talos-helper/SKILL.md (or your agent's skills folder).
name
talos-helper
description
Talos Linux cluster administration using talosctl When user mentions Talos, talosctl, or Talos cluster operations

Talos Helper Agent

What's New in 2025

  • OCI Registry Cache: talosctl image cache-serve for local registry over HTTP/HTTPS
  • System Logs: Automatic log rotation in /var/log with structured logging
  • Kernel Parameters: talosctl get kernelparamstatus for KSPP sysctl settings
  • Multi-Endpoint: Load balancing and automatic failover across control plane endpoints
  • QEMU Support: QEMU x86 virtualization on macOS (Apple Silicon)
  • Enhanced Context Management: Similar to kubectl, manage multiple clusters easily

Overview

This agent helps you manage Talos Linux Kubernetes clusters using talosctl for node configuration, cluster bootstrapping, and system maintenance.

Key Philosophy: Talos is API-driven infrastructure:

  • No SSH Access: All operations through API
  • No Package Manager: Immutable OS
  • No Shell: Minimal attack surface
  • YAML Configuration: Single source of truth

CLI Commands

Common Operations

Check version:

bash
talosctl version

View cluster configuration:

bash
talosctl config info
talosctl config contexts

Context management (like kubectl):

bash
# List available contexts
talosctl config contexts

# Switch context
talosctl config context production-cluster

# Show current context
talosctl config info

# Add new context
talosctl config add staging \
  --ca ca.crt \
  --crt talos.crt \
  --key talos.key \
  --endpoints 10.0.1.10,10.0.1.11,10.0.1.12

# Merge contexts from another file
talosctl config merge ./staging-talosconfig

Multi-endpoint load balancing (2025):

bash
# Multiple endpoints provide automatic failover
talosctl --endpoints 10.0.0.10,10.0.0.11,10.0.0.12 \
  --nodes 10.0.0.20 get members

# Config with multiple endpoints
talosctl config add prod \
  --endpoints 10.0.0.10,10.0.0.11,10.0.0.12 \
  --nodes 10.0.0.10,10.0.0.11,10.0.0.12

# Client automatically load balances and fails over

Node status and health:

bash
talosctl --nodes <node-ip> health
talosctl --nodes <node-ip> services
talosctl --nodes <node-ip> dmesg
talosctl --nodes <node-ip> logs kubelet

Get node configuration:

bash
talosctl --nodes <node-ip> get machineconfig
talosctl --nodes <node-ip> read /etc/os-release

Cluster Bootstrapping

Initial Cluster Setup
bash
# Generate cluster configuration
talosctl gen config my-cluster https://control-plane-ip:6443

# Apply configuration to nodes
talosctl apply-config --insecure --nodes <node-ip> --file controlplane.yaml
talosctl apply-config --insecure --nodes <node-ip> --file worker.yaml

# Bootstrap the cluster (only on one control plane node)
talosctl bootstrap --nodes <control-plane-ip>

# Get kubeconfig
talosctl kubeconfig --nodes <control-plane-ip>
Configuration Generation
bash
# Generate with custom options
talosctl gen config my-cluster https://control-plane-ip:6443 \
  --with-secrets secrets.yaml \
  --config-patch @patch.yaml \
  --kubernetes-version 1.28.0

# Generate secrets separately
talosctl gen secrets -o secrets.yaml

Node Management

Upgrading Nodes
bash
# Upgrade Talos OS
talosctl --nodes <node-ip> upgrade \
  --image ghcr.io/siderolabs/installer:v1.6.0

# Upgrade with preserve option
talosctl --nodes <node-ip> upgrade \
  --image ghcr.io/siderolabs/installer:v1.6.0 \
  --preserve

# Upgrade Kubernetes
talosctl --nodes <control-plane-ip> upgrade-k8s --to 1.28.0
Homelab (torvalds) upgrade gotchas
  • Never pass repo:tag@digest to talosctl upgrade --image. containerd pulls by digest but the installer then looks up the tag@digest form in the store and fails with "not found in containerd store". Use the tag-only reference (e.g. factory.talos.dev/metal-installer-secureboot/<schematic>:vX.Y.Z).
  • Drains deadlock on unsatisfiable PDBs (minAvailable=1 on single-replica workloads on a single-node cluster). The upgrade aborts after ~5 min but leaves the node cordoned with pods Pending — a partial outage until manually uncordoned. Before any drain, check kubectl get pdb -A for ALLOWED DISRUPTIONS 0. (postgres-operator PDBs are disabled in code since PR #1126.)
  • Kernel lockdown posture: torvalds runs lockdown=integrity (set via image-schematic extraKernelArgs [-lockdown, lockdown=integrity]) so eBPF profiling works. Secure-boot installs default to lockdown=confidentiality, which breaks eBPF — if reinstalled with secure boot, this reverts. Also kernel.kptr_restrict=1 via packages/homelab/src/talos/torvalds/patches/sysctls.yaml.
  • After an upgrade that lands on a different version than the existing pin, update versions.ts (siderolabs/talos, kubernetes/kubernetes) and the README example to the now-running version.
Node Maintenance
bash
# Reboot node
talosctl --nodes <node-ip> reboot

# Shutdown node
talosctl --nodes <node-ip> shutdown

# Reset node (destructive!)
talosctl --nodes <node-ip> reset

# Reset and reboot
talosctl --nodes <node-ip> reset --graceful=false --reboot
Certificate Management
bash
# Rotate Kubernetes CA
talosctl --nodes <control-plane-ip> rotate-ca

# View certificates
talosctl --nodes <node-ip> get certs

Troubleshooting

Viewing Logs
bash
# Kubelet logs
talosctl --nodes <node-ip> logs kubelet

# Container runtime logs
talosctl --nodes <node-ip> logs cri

# Follow logs
talosctl --nodes <node-ip> logs -f kubelet

# Kernel logs
talosctl --nodes <node-ip> dmesg
talosctl --nodes <node-ip> dmesg -f
System Status
bash
# Check all services
talosctl --nodes <node-ip> services

# Check specific service
talosctl --nodes <node-ip> service kubelet status

# Restart service
talosctl --nodes <node-ip> service kubelet restart
Health Checks
bash
# Overall health
talosctl --nodes <node-ip> health

# Detailed health with verbose output
talosctl --nodes <node-ip> health --verbose

# Check cluster health from control plane
talosctl --nodes <control-plane-ip> health --run-e2e
Network Debugging
bash
# Check network interfaces
talosctl --nodes <node-ip> get addresses
talosctl --nodes <node-ip> get routes

# DNS resolution
talosctl --nodes <node-ip> read /etc/resolv.conf

# Test connectivity
talosctl --nodes <node-ip> exec -- ping -c 3 8.8.8.8
System Logs and Monitoring (2025)

Talos provides structured logging in /var/log:

bash
# View system logs (automatic rotation)
talosctl --nodes <node-ip> logs

# Read specific log files
talosctl --nodes <node-ip> read /var/log/audit/kube/audit.log
talosctl --nodes <node-ip> read /var/log/containers/

# Follow logs in real-time
talosctl --nodes <node-ip> logs -f

# Kernel parameters and security settings
talosctl --nodes <node-ip> get kernelparamstatus

# View all kernel parameters
talosctl --nodes <node-ip> read /proc/sys/

KSPP (Kernel Self-Protection Project) sysctls:

bash
# Check KSPP-compliant kernel parameters
talosctl --nodes <node-ip> get kernelparamstatus

# Example output shows hardened security settings:
# - kernel.kptr_restrict
# - kernel.dmesg_restrict
# - kernel.unprivileged_bpf_disabled
OCI Image Cache Server (2025)

Serve a local OCI registry cache over HTTP/HTTPS:

bash
# Start local registry cache server
talosctl image cache-serve --listen :5000

# Use with other nodes
# Edit machine config to use cache:
# machine:
#   registries:
#     mirrors:
#       docker.io:
#         endpoints:
#           - http://cache-server:5000

# Verify cache is working
talosctl --nodes <node-ip> read /etc/cri/conf.d/hosts/

Benefits:

  • Faster image pulls across cluster
  • Reduced external bandwidth usage
  • Works offline/air-gapped environments
  • Supports HTTPS with TLS certificates

Configuration Management

Patching Configuration
bash
# Apply configuration patch
talosctl --nodes <node-ip> patch machineconfig \
  --patch @patch.yaml

# Example patch for nameservers
cat > patch.yaml <<EOF
machine:
  network:
    nameservers:
      - 1.1.1.1
      - 8.8.8.8
EOF

talosctl --nodes <node-ip> patch machineconfig --patch @patch.yaml
Configuration Validation
bash
# Validate configuration file
talosctl validate --config controlplane.yaml --mode metal

# Generate and validate
talosctl gen config test-cluster https://localhost:6443 \
  --output-types talosconfig -o talosconfig.yaml
Show full SKILL.md (264 more words)Show less

Best Practices (2025)

  1. Backup Secrets: Always backup secrets.yaml file

    bash
    # Secrets are cryptographic keys - losing them = losing cluster access
cp secrets.yaml ~/backups/talos-secrets-$(date +%Y%m%d).yaml

  2. Use Multi-Endpoint Configuration: Provides automatic failover

    bash
    talosctl config add prod \
  --endpoints 10.0.0.10,10.0.0.11,10.0.0.12 \
  --nodes 10.0.0.10,10.0.0.11,10.0.0.12

  3. Staged Upgrades: Upgrade one node at a time, start with workers

    bash
    # Workers first, then control plane
talosctl --nodes worker-1 upgrade --image ghcr.io/siderolabs/installer:v1.8.0
# Wait and verify before continuing

  4. Health Checks: Verify cluster health before and after changes

    bash
    talosctl health --verbose

  5. Configuration as Code: Store Talos configs in version control (git)

    bash
    git add talos/
git commit -m "Update machine config: add registry mirror"

  6. Use Patches: Apply configuration changes via patches, not full rewrites

    bash
    talosctl patch machineconfig --patch @registry-mirror.yaml

  7. Test in Dev: Use QEMU for local testing before production

    bash
    # QEMU x86 support on macOS (Apple Silicon) - 2025 feature
talosctl cluster create --provisioner qemu

  8. Image Cache: Use talosctl image cache-serve for faster deployments

    bash
    # Reduces external bandwidth and speeds up scaling
talosctl image cache-serve --listen :5000

  9. Monitor Kernel Parameters: Check KSPP compliance regularly

    bash
    talosctl --nodes <node-ip> get kernelparamstatus

Common Issues and Solutions

Node Not Joining Cluster
bash
# Check node configuration
talosctl --nodes <node-ip> get machineconfig

# Check kubelet status
talosctl --nodes <node-ip> service kubelet status
talosctl --nodes <node-ip> logs kubelet

# Verify control plane is accessible
talosctl --nodes <node-ip> exec -- curl -k https://<control-plane>:6443
Certificate Issues
bash
# Check certificate expiration
talosctl --nodes <node-ip> get certs

# Regenerate certificates
talosctl --nodes <control-plane-ip> rotate-ca
Disk Issues
bash
# Check disk usage
talosctl --nodes <node-ip> exec -- df -h

# Check mount points
talosctl --nodes <node-ip> read /proc/mounts

Examples

Example 1: Complete Cluster Bootstrap
bash
#!/bin/bash
CLUSTER_NAME="production"
ENDPOINT="https://10.0.0.10:6443"
CONTROL_PLANE="10.0.0.10"
WORKER1="10.0.0.11"
WORKER2="10.0.0.12"

# Generate configuration
talosctl gen config "$CLUSTER_NAME" "$ENDPOINT" \
  --output-dir ./talos-config

# Apply to control plane
talosctl apply-config --insecure \
  --nodes "$CONTROL_PLANE" \
  --file talos-config/controlplane.yaml

# Wait for node to be ready
sleep 30

# Bootstrap cluster
talosctl bootstrap --nodes "$CONTROL_PLANE"

# Apply to workers
talosctl apply-config --insecure \
  --nodes "$WORKER1" \
  --file talos-config/worker.yaml

talosctl apply-config --insecure \
  --nodes "$WORKER2" \
  --file talos-config/worker.yaml

# Get kubeconfig
talosctl kubeconfig --nodes "$CONTROL_PLANE"

# Verify cluster
kubectl get nodes
Example 2: Safe Node Upgrade
bash
#!/bin/bash
NODE=$1
NEW_VERSION="v1.6.0"

echo "Starting upgrade of $NODE to $NEW_VERSION"

# Health check before upgrade
talosctl --nodes "$NODE" health

# Upgrade
talosctl --nodes "$NODE" upgrade \
  --image "ghcr.io/siderolabs/installer:$NEW_VERSION" \
  --preserve

# Wait for node to come back
echo "Waiting for node to restart..."
sleep 60

# Health check after upgrade
talosctl --nodes "$NODE" health

echo "Upgrade complete!"
Example 3: Cluster Health Dashboard
bash
#!/bin/bash

echo "=== Talos Version ==="
talosctl version

echo "\n=== Nodes ==="
kubectl get nodes -o wide

echo "\n=== Services Status ==="
for node in "$@"; do
  echo "\nNode: $node"
  talosctl --nodes "$node" services | grep -E '(kubelet|etcd|containerd)'
done

echo "\n=== Cluster Health ==="
talosctl health --verbose

Integration with kubectl

Talos works seamlessly with kubectl:

bash
# Get kubeconfig from Talos
talosctl kubeconfig --nodes <control-plane-ip>

# Merge with existing kubeconfig
talosctl kubeconfig --nodes <control-plane-ip> --merge

# Use kubectl normally
kubectl get nodes
kubectl get pods --all-namespaces

When to Ask for Help

Ask the user for clarification when:

  • Node IP addresses are not specified
  • Destructive operations are needed (reset, shutdown)
  • The cluster endpoint or configuration is ambiguous
  • Upgrade versions need to be confirmed
  • Multiple nodes need coordinated operations

© shepherdjerred, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in packages/dotfiles/dot_agents/skills/talos-helper of shepherdjerred/monorepo.

Open the folder on GitHubat commit bc57ca5

Compare with similar skills

Talos Helper next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Talos Helper compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Talos Helper this skillshepherdjerred/monorepo112—~3.3kAutomated safety check: PassGPL-3.0
Helm Chart ScaffoldingCybereason-Public/owLSM28013 repos~381Automated safety check: PassGPL-2.0
Kubernetes ArchitectCybereason-Public/owLSM2809 repos~2.6kAutomated safety check: PassGPL-2.0
Openbkn Deployopenbkn-ai/bkn-foundry645—~1.9kAutomated safety check: NotesCustom licence
Ama Logs Update Charts Release Notesmicrosoft/Docker-Provider174—~2.6kAutomated safety check: PassCustom licence
Alibabacloud Ecs Sec Userspacealiyun/alibabacloud-ecs-troubleshoot-skills148—~2.6kAutomated safety check: NotesApache-2.0

Similar skills

  • Helm Chart Scaffolding

    Cybereason-Public/owLSM

    Comprehensive guidance for creating, organizing, and managing Helm charts for packaging and deploying Kubernetes applications.

    280 GitHub starsUsed in 13 repos~381 tokens
    DevOps & CloudAuto-check passed

  • Kubernetes Architect

    Cybereason-Public/owLSM

    Expert Kubernetes architect specializing in cloud-native infrastructure, advanced GitOps workflows (ArgoCD/Flux), and enterprise container orchestration.

    280 GitHub starsUsed in 9 repos~2.6k tokens
    DevOps & CloudAuto-check passed

  • Openbkn Deploy

    openbkn-ai/bkn-foundry

    Deploy or upgrade OpenBKN on a customer-authorized Linux server through the repository's deploy scripts, with preflight checks, explicit confirmation, secret handling, and post-deployment…

    645 GitHub stars~1.9k tokensUpdated today
    DevOps & CloudAuto-check: notes

  • Ama Logs Update Charts Release Notes

    microsoft/Docker-Provider

    Official

    Prepare an ama-logs release PR: bump the image tag (X.Y.Z) across Helm charts, manifests, and Dockerfiles, and add a formatted ReleaseNotes.md entry.

    174 GitHub stars~2.6k tokensUpdated 2 days ago
    DevOps & CloudAuto-check passed

  • Alibabacloud Ecs Sec Userspace

    aliyun/alibabacloud-ecs-troubleshoot-skills

    Linux 用户态安全入侵检测与取证工具，专为 AI Agent 设计。自动判断服务器是否被入侵， 提供完整证据链和可执行修复建议。51 个安全分析器覆盖进程/网络/认证/持久化/Rootkit/ 恶意软件/内存取证/容器逃逸等 12 类检测维度，10 个数据采集器全面采集系统状态， 映射 103+ MITRE ATT&CK 技术，支持 standalone/docker/k8s 三种部署模式。

    148 GitHub stars~2.6k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check: notes

  • Deploy Controller

    ai-runway/airunway

    Interactively build, push or load, and deploy an airunway component (controller or any provider) to the cluster

    102 GitHub stars~927 tokensUpdated 13 days ago
    DevOps & CloudAuto-check passed

More from shepherdjerred/monorepo

All 63 skills in this repo

  • Bun Runtime Best Practices

    shepherdjerred/monorepo

    Bun runtime APIs and current operational patterns for files, processes, modules, networking, databases, tests, and deployment.

    112 GitHub stars~2k tokensUpdated today
    Auto-check passed

  • Bun Test Patterns

    shepherdjerred/monorepo

    Current Bun test runner guidance for discovery, isolation, parallelism, sharding, changed tests, mocks, timers, snapshots, coverage, DOM Testing Library, and integration teardown.

    112 GitHub stars~2k tokensUpdated today
    Auto-check passed

  • Bun Workspaces

    shepherdjerred/monorepo

    Current Bun workspace guidance for isolated and hoisted linkers, catalogs, filters, scripts, dependency classes, lockfiles, lifecycle trust, caches, publishing, TypeScript package exports, and…

    112 GitHub stars~2.2k tokensUpdated today
    Auto-check passed

  • Deep Research

    shepherdjerred/monorepo

    This skill should be used when the user asks to "deep research", "research this topic", "investigate thoroughly", "do a deep dive on", "comprehensive research on", "find everything about", "survey…

    112 GitHub stars~4.7k tokensUpdated today
    Auto-check: notes

  • Figma Use

    shepherdjerred/monorepo

    This skill should be used when the user asks to "create a Figma design", "design in Figma", "make a Figma mockup", "create an app icon", "design UI", "render JSX to Figma", "export from Figma"…

    112 GitHub stars~946 tokensUpdated today
    Auto-check passed

  • Fish Helper

    shepherdjerred/monorepo

    Current Fish shell scripting, functions, abbreviations, completions, variables, events, configuration, plugins, testing, and safety guidance.

    112 GitHub stars~2k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Talos Helper

What does Talos Helper do?

Talos Linux cluster administration using talosctl When user mentions Talos, talosctl, or Talos cluster operations. Talos Helper is an agent skill from shepherdjerred/monorepo.

When should I use Talos Helper?

Talos Helper fits situations like: talos cluster operations; tasks that involve Container orchestration.

How do I install Talos Helper in Claude Code?

Run `npx skills add shepherdjerred/monorepo --skill talos-helper -a claude-code`. Or copy the skill folder (packages/dotfiles/dot_agents/skills/talos-helper in shepherdjerred/monorepo) into .claude/skills/talos-helper in your project. Claude Code loads it when a task matches its description.

How do I install Talos Helper in Codex?

Run `npx skills add shepherdjerred/monorepo --skill talos-helper -a codex`. Or copy the skill folder (packages/dotfiles/dot_agents/skills/talos-helper in shepherdjerred/monorepo) into .agents/skills/talos-helper in your project. Codex loads it when a task matches its description.

Can I use Talos Helper in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add shepherdjerred/monorepo --skill talos-helper -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/talos-helper, .gemini/skills/talos-helper, .github/skills/talos-helper and .opencode/skills/talos-helper in your project.

What does Talos Helper need to run?

Going by SKILL.md and its folder, Talos Helper needs the command-line tools its instructions call (kubectl and git). Our summary lists: Docker.

Does Talos Helper access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Talos Helper safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Talos Helper use?

Talos Helper is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Talos Helper use?

About 3.3k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Talos Helper?

Skills that share tags, products or a category with Talos Helper: Helm Chart Scaffolding (Cybereason-Public/owLSM, 280 stars), Kubernetes Architect (Cybereason-Public/owLSM, 280 stars), Openbkn Deploy (openbkn-ai/bkn-foundry, 645 stars) and Ama Logs Update Charts Release Notes (microsoft/Docker-Provider, 174 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Talos Helper?

shepherdjerred (a GitHub user) maintains it in shepherdjerred/monorepo, which has 112 GitHub stars. The repository holds 63 skills in this directory. The repository was last updated on October 9, 2026.

Source: shepherdjerred/monorepo on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.