install
- Repo stars 0
- Author updated Live
- Author repo skills-registry
- Domain
- AI
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @tomevault-io · no license declared
- Token usage
- Lean
- Setup complexity
- Manual integration
- External API key
- Required · Vendor-specific
- Operating systems
- macOS · Linux · Windows
- Runtime requirements
- Node.js · Python
- Permissions
-
- Read-only
- Write / modify
- Shell exec
- Network behavior
- External requests
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: install
description: Install the aigonskills MCP server into Claude Code or other clients. Use when the user asks to…
category: ai
runtime: Node.js / Python
---
# install output preview
## PART A: Task fit
- Use case: Install the aigonskills MCP server into Claude Code or other clients. Use when the user asks to "install aigonskills", "add the skills server", "set up aigonskills MCP", or "connect to aigonskills". Use when this capability is needed..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Method 1: Claude Code CLI / Method 2: Configuration file (manual) / Method 3: Claude Desktop (mcp-remote)” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Install the aigonskills MCP server into Claude Code or other clients. Use when the user asks to "install aigonskills", "add the skills server", "set up aigonskills MCP", or "connect to aigonskills". Use when this capability is needed.”.
- **02** When the source has headings, the agent prioritizes “Method 1: Claude Code CLI / Method 2: Configuration file (manual) / Method 3: Claude Desktop (mcp-remote)” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, run shell commands; may access external network resources; requires Vendor-specific API keys.
## Running Rules
- read files, write/modify files, run shell commands; may access external network resources; requires Vendor-specific API keys.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. The source mentions slash commands such as `/mcp`, `/asexplore`, `/asadd`, `/asremove`, `/asrun`; use them first when your agent supports command triggers.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files, run shell commands.
Start with a small task and check whether the result follows “Method 1: Claude Code CLI / Method 2: Configuration file (manual) / Method 3: Claude Desktop (mcp-remote)”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: install
description: Install the aigonskills MCP server into Claude Code or other clients. Use when the user asks to…
category: ai
source: tomevault-io/skills-registry
---
# install
## When to use
- Install the aigonskills MCP server into Claude Code or other clients. Use when the user asks to "install aigonskills"…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Method 1: Claude Code CLI / Method 2: Configuration file (manual) / Method 3: Claude Desktop (mcp-remote)” and keep inference separate from source facts.
- read files, write/modify files, run shell commands; may access external network resources; requires Vendor-specific API keys.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "install" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Method 1: Claude Code CLI / Method 2: Configuration file (manual) / Method 3: Claude Desktop (mcp-remote)
rules -> SKILL.md triggers / order / output contract
runtime -> Node.js / Python | read files, write/modify files, run shell commands | may access external network resources
guardrails -> requires Vendor-specific API keys + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
} Install aigonskills MCP Server
Register the aigonskills MCP server so skill discovery tools become available. No API key required.
Server endpoint: https://aigonskills.aigon.ai/sse (SSE transport)
Method 1: Claude Code CLI
Check if the server is already configured:
claude mcp listIf
aigonskillsalready appears, tell the user it's already installed and stop.Install the server:
claude mcp add --transport sse aigonskills https://aigonskills.aigon.ai/sseVerify with
claude mcp listor the/mcpcommand inside Claude Code.Restart Claude Code (or start a new session) for the MCP tools to become available.
To remove: claude mcp remove aigonskills
Method 2: Configuration file (manual)
Claude Code stores MCP server config in .claude/settings.local.json (project-level) or ~/.claude/settings.json (global). Add the server entry manually if preferred:
{
"mcpServers": {
"aigonskills": {
"type": "sse",
"url": "https://aigonskills.aigon.ai/sse"
}
}
}
Method 3: Claude Desktop (mcp-remote)
Claude Desktop does not support SSE transport natively. Use mcp-remote to bridge the connection.
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"aigonskills": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://aigonskills.aigon.ai/sse"]
}
}
}
This spawns a local process via npx mcp-remote that proxies the remote SSE server as a local stdio MCP server that Claude Desktop can talk to. Requires Node.js/npm installed.
Method 4: Cursor
Go to Cursor settings → MCP → Add new server. Set type to sse and URL to https://aigonskills.aigon.ai/sse.
Method 5: Programmatic (Python)
from mcp import ClientSession
from mcp.client.sse import sse_client
async with sse_client("https://aigonskills.aigon.ai/sse") as (read, write):
async with ClientSession(read, write) as session:
await session.initialize()
result = await session.call_tool("call", {
"namespace": "aigonskills",
"function": "stats",
})
print(result.content[0].text)
Verify it works
After restarting Claude Code, run /mcp and confirm aigonskills shows as connected. If it does, the MCP tools are available and ready to use.
Once installed, see the asexplore skill to search and discover skills, and the use skill to read and access them.
Install the as* management skills
For optimal use of the aigonskills server, install the as* skill set as local slash commands. These are available in the aigonskills index — search for source skloesch/aigonskills:
call(namespace="aigonskills", function="list", kwargs={"query": "as", "source": "skloesch/aigonskills"})
Then install each one via asinstall (or manually download and place in ~/.claude/skills/):
/asexplore— search and discover skills/asadd— add a skill reference to CLAUDE.md/AGENT.md/asremove— remove a skill reference/asrun— run a referenced skill from remote/asinstall— install a skill locally as a slash command/asuninstall— remove a locally installed skill
These give you a complete workflow: explore → add/install → run → remove/uninstall.
Source: aigonai/aigonskills — distributed by TomeVault.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review