Deployment request
The skill recognizes deploy, status, recovery, and configuration requests, then calls existing CLI, API, or Web capabilities.
AI skill
Let AI deploy projects with Appaloft.
After the Appaloft skill is installed, AI can inspect a project, call the Appaloft CLI/API/Web deployment path, and return URLs, logs, diagnostics, and recovery commands. The MCP/tool gateway connects tool calls, permissions, and audit.
Entrypoint
AI agent
State owner
CLI / API / Web
MCP
public tools + Cloud gateway
Secrets
Reference, never print
Outcome
URL + logs + diagnostics
The install command only installs the skill
Inspect source and project shape before deploy
MCP tools call existing Appaloft deployment capabilities
Return live URL, logs, diagnostics, and recovery commands
MCP tool layer
The MCP/tool gateway connects AI tool calls to Appaloft. In hosted Cloud, it also adds sign-in, permissions, policy, and audit.
Safety boundary
AI must avoid .env files, private keys, tokens, cookies, and unmasked secrets. When credentials are needed, it should reference Appaloft secrets, GitHub Secrets, or runtime environment variable names.
Result packet
A normal response includes the URL, deployment id, resource id, status, logs, diagnostics, and recovery guidance.
Deployment flow
1
Install
Install the Appaloft skill into a skill-capable AI host.
2
Ask AI
Ask the agent to deploy the current repository and return URL, logs, diagnostics, and recovery commands.
3
Verify
On failure, read structured status and recovery guidance before choosing the next step.