skillporter_add
Install AI agent skills from a workspace path, archive, or GitHub repository into target harnesses, with controls for overwriting conflicts and accepting security findings.
Instructions
[WRITE] Install skills from a workspace directory, archive, or repository into target harnesses (requires SKILLPORTER_MCP_ALLOW_WRITES=1).
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"source": "<source>",
"harnesses": "<harnesses>"
},
"name": "skillporter_add"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | Workspace-relative root path (default: '.') | |
| force | No | Overwrite conflicting existing installations (never bypasses security findings) | |
| source | Yes | Workspace-relative path or GitHub owner/repo specifier | |
| strategy | No | copy | |
| harnesses | Yes | Target harness IDs (e.g. ['claude-code', 'codex', 'cursor']) | |
| accept_risk | No | Explicitly accept non-structural security findings after inspection |