Skip to main content
ClaudeWave
EN, English
Skill5.1k repo starsupdated 2mo ago

env-manager

The env-manager skill provides persistent storage and retrieval of environment variables across sessions by executing Python commands to set, list, and unset configuration values. Use this when users need to save API keys, authentication tokens, database credentials, or other sensitive configuration data that should persist between separate interactions without requiring re-entry.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/dtyq/magic /tmp/env-manager && cp -r /tmp/env-manager/backend/super-magic/agents/skills/env-manager ~/.claude/skills/env-manager
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# Environment Variable Manager

Use this skill by calling `set_env`, `get_env`, `unset_env`, and `list_env` through `sdk.tool.call(...)` inside `run_sdk_snippet`.

By default, save and delete personal environment variables stored in `~/.magic/super-magic.env` for reuse across workspaces.
Pass `"scope": "workspace"` only when the user explicitly asks to save or delete values for the current workspace/project.

The runtime effective environment merges workspace env and personal env. Personal env has the highest priority and overrides workspace values with the same key.
Tool display and results never echo plaintext values.

## Get One Env

When you only need to check whether one key is configured, prefer `get_env`. `get_env` queries the final effective env by default (`scope=all`). Do not call `list_env` just to inspect one key, because that exposes unrelated environment variable names and masked values to the model context.

```python
run_sdk_snippet(python_code="""
from sdk.tool import tool

result = tool.call("get_env", {
    "key": "KEY_NAME",
})
if not result.ok:
    raise SystemExit(result.content)
print(result.content)
""")
```

Only pass `"scope": "personal"` or `"scope": "workspace"` when you need to check whether a key exists in a specific storage scope.

```python
run_sdk_snippet(python_code="""
from sdk.tool import tool

result = tool.call("get_env", {
    "key": "KEY_NAME",
    "scope": "workspace",
})
if not result.ok:
    raise SystemExit(result.content)
print(result.content)
""")
```

## Set Personal Env

```python
run_sdk_snippet(python_code="""
from sdk.tool import tool

result = tool.call("set_env", {
    "key": "KEY_NAME",
    "value": "value",
})
if not result.ok:
    raise SystemExit(result.content)
print(result.content)
""")
```

## Set Workspace Env

```python
run_sdk_snippet(python_code="""
from sdk.tool import tool

result = tool.call("set_env", {
    "key": "KEY_NAME",
    "value": "value",
    "scope": "workspace",
})
if not result.ok:
    raise SystemExit(result.content)
print(result.content)
""")
```

## List Personal Env

```python
run_sdk_snippet(python_code="""
from sdk.tool import tool

result = tool.call("list_env", {})
if not result.ok:
    raise SystemExit(result.content)
print(result.content)
""")
```

## List Workspace Env

```python
run_sdk_snippet(python_code="""
from sdk.tool import tool

result = tool.call("list_env", {
    "scope": "workspace",
})
if not result.ok:
    raise SystemExit(result.content)
print(result.content)
""")
```

## List Effective Env

`"scope": "all"` means the final effective merge of workspace and personal env. Personal env overrides workspace env with the same key.

```python
run_sdk_snippet(python_code="""
from sdk.tool import tool

result = tool.call("list_env", {
    "scope": "all",
})
if not result.ok:
    raise SystemExit(result.content)
print(result.content)
""")
```

## Unset Personal Env

```python
run_sdk_snippet(python_code="""
from sdk.tool import tool

result = tool.call("unset_env", {
    "key": "KEY_NAME",
})
if not result.ok:
    raise SystemExit(result.content)
print(result.content)
""")
```

## Unset Workspace Env

```python
run_sdk_snippet(python_code="""
from sdk.tool import tool

result = tool.call("unset_env", {
    "key": "KEY_NAME",
    "scope": "workspace",
})
if not result.ok:
    raise SystemExit(result.content)
print(result.content)
""")
```
agent-infoSkill

Query the list of all agents (employees) available to the current user. Use when generating code that requires a real agentId, or when the user asks "which agents/employees do I have".

ai-card-generatorSkill

|

antd-style-to-tailwindSkill

Migrate existing antd-style CSS-in-JS (createStyles) components to Tailwind CSS utility classes with full dark mode support, following the project's style system transition strategy. Use when the user asks to migrate, convert, or rewrite antd-style components to Tailwind, or when working on new components in files that already use antd-style.

browserSkill

Open and operate webpages in a real browser: navigate, read rendered content, inspect interactive elements, click, type, submit forms, press keys, select options, check boxes, hover, scroll, upload files, wait for page changes, manage pages, take and save screenshots, analyze visual layout, and inspect page errors and network activity.

canvas-designerSkill

Core canvas design skill covering project management, multimedia principles, AI image generation, web image search, and design marker processing. Load for any canvas design task. CRITICAL - When user message contains [@design_canvas_project:...] or [@design_marker:...] mentions, or when the user wants to generate video/animation/clip on a canvas project, you MUST load this skill first before any operations.

chat-historySkill

Use when details may have been lost after context compaction, or when the Agent needs to inspect earlier compacted messages or previously created sub-agents.

cli-managerSkill

Manage persistence for user-installed third-party CLI tools in the Super Magic sandbox. Use when the user wants to install, configure, adopt, restore, inspect, or remove a CLI, or when an external skill, webpage, or installer asks to run CLI install commands such as curl|sh, npm install -g, pipx install, uv tool install, go install, cargo install, or brew install. Do not persist runtime-provided CLIs.

code-review-expertSkill

Expert code review of current git changes with a senior engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements.