Skills by inference-sh-0

High-risk skill: installs and executes a remote script via `curl -fsSL https://cli.inference.sh | sh`, runs `infsh` commands that contact `https://inference.sh`, and instructs setting the `INFSH_API_KEY` environment variable. These explicit `curl | sh` install and `infsh app run` instructions enable remote code execution and external network access.

Discover and install related skills from inference.sh skill registry. Helps find complementary skills for your AI workflow. Use for: skill discovery, workflow expansion, capability exploration. Triggers: related skills, find skills, skill discovery, complementary skills, expand workflow, more capabilities, similar skills, skill suggestions

High-risk skill: Provides web search and content extraction via the `infsh` CLI and `inference.sh` apps. Instructs running `curl -fsSL https://cli.inference.sh | sh && infsh login` (remote install + login) and calling `infsh app run tavily/search-assistant`, enabling remote code execution and networked access.

Dangerous skill: downloads and executes a remote installer via `curl -fsSL https://cli.inference.sh | sh` and runs user-supplied Python that can make external requests such as `https://example.com` and `https://api.github.com/users/octocat`. Intended to execute Python in a sandbox and return files from `outputs/`.

This skill documents the inference.sh JavaScript/TypeScript SDK with examples for clients, agents, proxies, file uploads, and tools. It demonstrates external network calls (e.g., `https://hooks.slack.com/...`, `https://api.github.com/repos/org/repo/issues`), uses env secrets like `process.env.INFERENCE_API_KEY`, and enables `.codeExecution(true)`.

This skill documents the `inferencesh` Python SDK for running AI apps, agents, file uploads, sessions, and tool-building. It includes examples that access `INFERENCE_API_KEY` and secrets (`GITHUB_TOKEN`, `SLACK_SECRET`), call `https://hooks.slack.com/...` and execute code via `eval(call.args["expression"])`.