claude-code-install

A three-part Claude Code setup skill with subskills for installation, skip-login configuration, and custom API-key launcher setup. Use when the user wants Claude Code installed or configured on the current host, with instructions adapted to the actual operating system and runtime environment.

7 stars

Best use case

claude-code-install is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

A three-part Claude Code setup skill with subskills for installation, skip-login configuration, and custom API-key launcher setup. Use when the user wants Claude Code installed or configured on the current host, with instructions adapted to the actual operating system and runtime environment.

Teams using claude-code-install should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/claude-code-install/SKILL.md --create-dirs "https://raw.githubusercontent.com/igamenovoer/magic-context/main/skills/cli-agents/claude-code-install/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/claude-code-install/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How claude-code-install Compares

Feature / Agentclaude-code-installStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

A three-part Claude Code setup skill with subskills for installation, skip-login configuration, and custom API-key launcher setup. Use when the user wants Claude Code installed or configured on the current host, with instructions adapted to the actual operating system and runtime environment.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Claude Code Install

## Manual invocation

Invoke this skill explicitly by name (`$claude-code-install`) because it modifies the local host environment.

## Core operating rules

- Detect the host OS first and choose commands accordingly.
- On Windows, prefer the PowerShell helpers in `scripts/*.ps1`; if the user needs a double-clickable entrypoint, use the matching `scripts/*.bat` wrapper.
- On Linux or macOS, prefer the POSIX shell helpers in `scripts/*.sh`.
- Do not mix command styles across OS families.

- If the OS is unclear from context, check it before acting.
- Treat the scripts in `scripts/` as optional accelerators and reference implementations, not the only path.
- Before running a helper script, inspect the actual environment: available shell, available package managers, PATH layout, permission constraints, and existing Claude configuration.
- If a helper script works in the current environment, use it.
- If a helper script fails, do not stop at the script failure. Read the relevant subskill guide under `references/`, infer the required actions, and execute an environment-appropriate plan manually.

## Subskills

This skill has exactly three subskills.

1. `installation`
   Install the Claude Code CLI in the current environment.
   Primary guide: `references/installation.md`
   Optional helpers: `scripts/install-comp.sh`, `scripts/install-comp.ps1`, `scripts/install-comp.bat`

2. `skip-login-config`
   Configure the host so Claude Code skips first-run onboarding/login locally.
   Primary guide: `references/skip-login-config.md`
   Optional helpers: `scripts/config-skip-login.sh`, `scripts/config-skip-login.ps1`, `scripts/config-skip-login.bat`

3. `add-custom-api-key`
   Create a custom launcher or shell/profile function that injects an Anthropic-compatible API key and optional base URL/model overrides.
   Primary guide: `references/add-custom-api-key.md`
   Optional helpers: `scripts/config-custom-api-key.sh`, `scripts/config-custom-api-key.ps1`, `scripts/config-custom-api-key.bat`
   Known provider registry: `references/known-providers.json`

## Subskill selection

- If the user wants Claude Code installed, use `installation`.
- If Claude is already installed but the user wants to bypass onboarding or login prompts on this host, use `skip-login-config`.
- If the user wants a wrapper such as `claude-kimi`, a custom base URL, a known provider name such as `yunwu-global`, or a custom API key, use `add-custom-api-key`.
- If the user wants a complete setup, run the subskills in this order: `installation`, then `skip-login-config`, then `add-custom-api-key`.

## How to execute each subskill

For each subskill:

1. Read the corresponding file in `references/` first.
2. Detect the OS and shell family.
3. Check which runtime tools are actually available.
4. Prefer the documented manual steps from the reference guide.
5. Use a helper script from `scripts/` only if it matches the environment and clearly reduces work.
6. If the helper script fails, continue by applying the guide manually instead of retrying blindly.
7. Verify the result with the verification section from the corresponding reference guide.

## Example prompts

- "Use the Claude Code install skill to install Claude Code on this machine."
- "Use the skip-login subskill so Claude no longer shows onboarding on this host."
- "Use the custom API key subskill to make a `claude-yunwu` launcher that reads the key from an environment variable and targets `yunwu-global`."
- "Set up Claude Code fully, and adapt the steps if the bundled scripts do not work in this environment."

## Resources

- Installation guide: `references/installation.md`
- Skip-login guide: `references/skip-login-config.md`
- Custom API-key guide: `references/add-custom-api-key.md`
- Known provider registry: `references/known-providers.json`
- Helper scripts: `scripts/`

Related Skills

pixi-install-nvidia

7
from igamenovoer/magic-context

Use when the user says "use pixi to install <some nvidia tool>" (or similar) and wants NVIDIA/CUDA/GPU packages installed via Pixi (no sudo/apt), e.g., CUDA toolkit pieces, cuDNN/NCCL, PyTorch CUDA builds, RAPIDS.

codex-cli-install

7
from igamenovoer/magic-context

A three-part Codex CLI setup skill with subskills for installation, skip-login configuration, and custom API-key launcher setup. Use when the user wants Codex CLI installed or configured on the current host, with instructions adapted to the actual operating system and runtime environment.

claude-code-invoke-persist

7
from igamenovoer/magic-context

Create and resume Claude Code CLI sessions with a persistent session-name-to-session_id mapping (plus last-used model and reasoning effort) stored in a workspace-scoped JSON file under system temp. Use when the user wants deterministic, session-persistent Claude Code automation across turns and processes.

claude-code-invoke-once

7
from igamenovoer/magic-context

Programmatically invoke Claude Code via the `claude` CLI (headless `-p`, `--output-format json|stream-json`, `--resume`/`--continue`) to automate tasks like producing code review reports for specific files/dirs, investigating an issue, or drafting an implementation plan. Use when you need scriptable, machine-readable output and/or session-persistent multi-turn workflows with Claude Code.

vscode-make-offline-installer

7
from igamenovoer/magic-context

Build a VS Code air-gapped "offline kit" for Remote-SSH: desktop VS Code installers/archives for Windows/macOS/Linux, matching VS Code Server+CLI tarballs for headless Linux (commit-aligned), and pinned extension .vsix bundles for both local (client) and remote (server) sides. Use when you need a reproducible offline deployment, or when you want to mirror the VS Code release+extensions currently installed on a host.

pixi-make-offline-channel

7
from igamenovoer/magic-context

Use when the user wants to create a self-hosted, offline-installable Conda channel (mirror) containing a specific subset of packages using Pixi.

pixi-make-cu-build-env

7
from igamenovoer/magic-context

Guides the agent to setup a new or existing Pixi environment for compiling C++ and CUDA code. It ensures the correct compilers, toolkits, and CMake configurations are in place for a robust user-space build.

pei-docker-usage

7
from igamenovoer/magic-context

Helper for PeiDocker (`pei-docker-cli`). Trigger ONLY when the user explicitly requests PeiDocker usage OR when working within a PeiDocker-generated project (indicated by `user_config.yml`).

conan-basic-usage

7
from igamenovoer/magic-context

Basic operations for the Conan C++ package manager. Use when the user explicitly asks to 'use conan' for tasks like creating projects, installing dependencies, or building packages, or asks for 'how to' guidance on Conan setup.

explore-dnn-model

7
from igamenovoer/magic-context

Manual invocation only; use only when the user explicitly requests `explore-dnn-model` by name. Explore how to run a given DNN model checkpoint in the current Python environment by locating weights + upstream source code, resolving dependencies with user confirmation, running reproducible experiments under `tmp/`, and producing reports about I/O contracts, timing, and profiling.

openspec-ext-revise-by-decision

7
from igamenovoer/magic-context

Manual invocation only; use only when the user explicitly requests `openspec-ext-revise-by-decision` by exact name. Revise OpenSpec change artifacts from a review or decision document that contains questions plus `DECISION` blocks, applying chosen decisions from a review file such as `openspec/changes/<change>/review/review-*.md` back into proposal, design, specs, and tasks.

openspec-ext-review-plan

7
from igamenovoer/magic-context

Review an OpenSpec change (or a single OpenSpec change artifact file) for completeness, coherence, and alignment with existing system design; capture actionable feedback plus open questions; write a review report under the change directory (review/review-YYYYMMDD-HHMMSS.md).