SKILL: newapi

newapi (new-api) is an open-source unified AI gateway platform.
It aggregates multiple model providers behind OpenAI / Claude / Gemini compatible interfaces, and provides model, token, group, and balance management.

Security Guidelines

This skill follows these security guidelines to protect API keys:

1. 1. Do not expose any sk- key value in chat, files, code, logs, or command arguments. To use keys securely, tell the user to run copy-token (clipboard), apply-token (config file), or exec-token (CLI command).
2. All New API calls should go through the provided scripts (api.js, copy-key.js, inject-key.js, exec-token.js) rather than using curl, wget, fetch, or other HTTP clients to call New API endpoints directly.
3. Do not read .env files, environment variables containing credentials, or clipboard contents after copy-key.js.
4. When working with config files that may contain API keys, use inject-key.js --scan to get a sanitized view rather than reading them directly. Note: scan-config is best-effort and not guaranteed to redact every secret in every format.
5. After create-token, do not make any follow-up call to retrieve or list the key. Report success and tell the user they can use copy-token <id>, apply-token <id> <file>, or exec-token <id> <command> to securely use the key.
6. Do not modify the security scripts to disable masking or redirect output.

How to Execute

1. 1. First invocation only — read ${CLAUDE_SKILL_DIR}/docs/setup.md for configuration, auth headers, and runtime detection.
2. Match the action from the table below.
3. Read the corresponding doc file for detailed steps.
4. If no arguments or unrecognized action, show the help table below.
5. If the user asks about newapi (what it is, how to use a command, or any API usage question like calling a specific model format) — read ${CLAUDE_SKILL_DIR}/docs/help.md and follow the instructions there.

Actions

help (or no arguments) — Show available actions