# Run AI Apps with inference.sh

AI model workflows often require separate APIs, credentials, and task tracking. This skill helps Claude, Codex, and Claude Code use inference.sh CLI workflows.

## Install

```bash
npx skillstore add inference-sh/inference-sh
```

## Metadata

- Status: approved
- Slug: inference-sh-inference-sh
- Skillstore revision: r1
- Version status: missing
- Tree hash: 69fa3a9eaa076a1e42da35937a442854940a8597c726f9ad0d9819638ce4f823
- Author: inference-sh
- GitHub username: inference-sh
- License: MIT
- Repository: https://github.com/inference-sh/skills/tree/main/skills/inference-sh/
- Ref: a25199bc7d6b82598536822d1738eb5d5f54025b
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: blocked
- Manual install advisory: allowed\_with\_warning
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: network, env\_access, filesystem, external\_commands
- Quality score: 38
- Quality tier: warning
- Public page: https://skillstore.pages.dev/skills/inference-sh-inference-sh
- Manifest: https://skillstore.pages.dev/api/skills/inference-sh-inference-sh/manifest

## Capabilities

- Guides inference.sh CLI setup, login, update, and authentication checks.
- Discovers apps by category, search term, featured status, newest listing, or page.
- Runs cloud apps with inline input or saved input files.
- Generates sample input files and inspects app schemas before execution.
- Tracks long-running tasks and retrieves or saves results.
- References image, video, LLM, search, audio, 3D, and Twitter app examples.

## Use Cases

- Generate Media Assets: Create image, video, audio, or 3D outputs from cloud AI apps without managing local GPUs.
- Prototype Model Workflows: Find models, inspect schemas, create sample inputs, and run tasks from one CLI workflow.
- Run Research Tasks: Use search and LLM apps to gather information, summarize findings, and track long-running jobs.

## Prompt Templates

### Find Apps by Category

```
Use inference.sh to list image generation apps. Show the best options and explain what each app is for.
```

### Prepare a Sample Run

```
Create a safe sample input for a FLUX image app, explain each field, and ask before running it.
```

### Track a Long Task

```
Run a video generation task without waiting, capture the task ID, and check status until the result is ready.
```

### Plan a Multi-App Workflow

```
Design a workflow that searches for references, generates a script, creates a video, and saves final outputs for review.
```

## Limitations

- Requires the external inference.sh CLI and an authenticated account.
- Runs cloud services that may use credits or provider-specific limits.
- Does not verify remote install scripts, package signatures, or model outputs.
- Some workflows can create public or private social media actions.

## Best Practices

- Review every command before execution, especially install, deploy, and social media commands.
- Use scoped API keys and store them in a secret manager.
- Pin app versions when reproducibility matters.

## Anti Patterns

- Do not pipe remote installers into a shell without verification.
- Do not post, like, follow, or send messages without explicit approval.
- Do not paste production secrets into prompt text or saved input files.

## Security Audit

- Audited at: 2026-07-05T17:25:35.957\+00:00
- Summary: Confirmed critical remote-installer findings where curl output is piped directly into sh. Most API key, shell completion, documentation URL, and Markdown backtick matches are false positives. Semantic review found broad infsh CLI permission and Twitter/X automation risks that need guardrails before publication.

## Stats

- Views: 357
- Downloads: 7
- Favorites: 0
- Popularity score: 0