Skip to content

EliasOulkadi/shokunin / .pack/skills/agent-tools

agent-tools

Flagged

Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok

inference.sh

Run 150+ AI apps in the cloud with a simple CLI. No GPU required.

Image: inference.sh

Install CLI

curl -fsSL https://cli.inference.sh | sh
infsh login

What does the installer do? The install script detects your OS and architecture, downloads the correct binary from dist.inference.sh, verifies its SHA-256 checksum, and places it in your PATH. That's it — no elevated permissions, no background processes, no telemetry. If you have cosign installed, the installer also verifies the Sigstore signature automatically.

Manual install (if you prefer not to pipe to sh):

# Download the binary and checksums
curl -LO https://dist.inference.sh/cli/checksums.txt
curl -LO $(curl -fsSL https://dist.inference.sh/cli/manifest.json | grep -o '"url":"[^"]*"' | grep $(uname -s | tr A-Z a-z)-$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/') | head -1 | cut -d'"' -f4)
# Verify checksum
sha256sum -c checksums.txt --ignore-missing
# Extract and install
tar -xzf inferencesh-cli-*.tar.gz
mv inferencesh-cli-* ~/.local/bin/inferencesh

Quick Examples

# Generate an image
infsh app run falai/flux-dev-lora --input '{"prompt": "a cat astronaut"}'

# Generate a video
infsh app run google/veo-3-1-fast --input '{"prompt": "drone over mountains"}'

# Call Claude
infsh app run openrouter/claude-sonnet-45 --input '{"prompt": "Explain quantum computing"}'

# Web search
infsh app run tavily/search-assistant --input '{"query": "latest AI news"}'

# Post to Twitter
infsh app run x/post-tweet --input '{"text": "Hello from AI!"}'

# Generate 3D model
infsh app run infsh/rodin-3d-generator --input '{"prompt": "a wooden chair"}'

Local File Uploads

The CLI automatically uploads local files when you provide a path instead of a URL:

# Upscale a local image
infsh app run falai/topaz-image-upscaler --input '{"image": "/path/to/photo.jpg", "upscale_factor": 2}'

# Image-to-video from local file
infsh app run falai/wan-2-5-i2v --input '{"image": "./my-image.png", "prompt": "make it move"}'

# Avatar with local audio and image
infsh app run bytedance/omnihuman-1-5 --input '{"audio": "/path/to/speech.mp3", "image": "/path/to/face.jpg"}'

# Post tweet with local media
infsh app run x/post-create --input '{"text": "Check this out!", "media": "./screenshot.png"}'

Commands

TaskCommand
List all appsinfsh app list
Search appsinfsh app list --search "flux"
Filter by categoryinfsh app list --category image
Get app detailsinfsh app get google/veo-3-1-fast
Generate sample inputinfsh app sample google/veo-3-1-fast --save input.json
Run appinfsh app run google/veo-3-1-fast --input input.json
Run without waitinginfsh app run <app> --input input.json --no-wait
Check task statusinfsh task get <task-id>

What's Available

CategoryExamples
ImageFLUX, Gemini 3 Pro, Grok Imagine, Seedream 4.5, Reve, Topaz Upscaler
VideoVeo 3.1, Seedance 1.5, Wan 2.5, OmniHuman, Fabric, HunyuanVideo Foley
LLMsClaude Opus/Sonnet/Haiku, Gemini 3 Pro, Kimi K2, GLM-4, any OpenRouter model
SearchTavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract
3DRodin 3D Generator
Twitter/Xpost-tweet, post-create, dm-send, user-follow, post-like, post-retweet
UtilitiesMedia merger, caption videos, image stitching, audio extraction

Related Skills

# Image generation (FLUX, Gemini, Grok, Seedream)
npx skills add inference-sh/skills@ai-image-generation

# Video generation (Veo, Seedance, Wan, OmniHuman)
npx skills add inference-sh/skills@ai-video-generation

# LLMs (Claude, Gemini, Kimi, GLM via OpenRouter)
npx skills add inference-sh/skills@llm-models

# Web search (Tavily, Exa)
npx skills add inference-sh/skills@web-search

# AI avatars & lipsync (OmniHuman, Fabric, PixVerse)
npx skills add inference-sh/skills@ai-avatar-video

# Twitter/X automation
npx skills add inference-sh/skills@twitter-automation

# Model-specific
npx skills add inference-sh/skills@flux-image
npx skills add inference-sh/skills@google-veo

# Utilities
npx skills add inference-sh/skills@image-upscaling
npx skills add inference-sh/skills@background-removal

Reference Files

Documentation

Workflow

  1. Discover — infsh app list --search "<keyword>" or infsh app list --category <image|video|llm|search|3d|x|utility> to find the right app
  2. Inspect — infsh app get <app-id> for description, pricing, input schema, and rate limits
  3. Generate sample input — infsh app sample <app-id> --save input.json to get a valid input template pre-filled with defaults
  4. Customize — edit the JSON input file: replace prompts, file paths, or configuration values
  5. Run — infsh app run <app-id> --input input.json for synchronous execution, or --no-wait for long-running tasks
  6. Check status — infsh task get <task-id> to poll progress of async tasks; infsh task logs <task-id> for streaming output
  7. Retrieve output — outputs are URLs (images, videos) or text responses; download with infsh task download <task-id>

For multi-step pipelines, chain apps: run the first app, extract its output URL, feed it as input to the next app (e.g., generate image → upscale, or generate video → add audio).

Error Handling

ErrorCauseFix
infsh: command not foundCLI not installed or not in PATHRun `curl -fsSL https://cli.inference.sh
401 UnauthorizedNot logged in or token expiredRun infsh login and re-authenticate
402 Payment RequiredAccount has no credits or payment methodCheck infsh billing; add credits via inference.sh dashboard
429 Too Many RequestsRate limit exceeded for the app or account tierWait for the Retry-After header duration; for paid tiers, request a limit increase
400 Bad Request on file uploadFile path does not exist, is a directory, or exceeds size limitsVerify the file path with ls -la; check the app's max input size in infsh app get <app-id>
Task timed out (HTTP 504 or task status failed)App execution exceeded max durationCheck infsh task get <task-id> for error details; retry with smaller input or check app status page
502 Bad Gateway or connection errorsinference.sh backend or model provider is downCheck https://status.inference.sh; retry with exponential backoff (2s, 4s, 8s)
Output URL returns 404Generated asset expired (files are ephemeral)Re-run the job; for permanent storage, download immediately with infsh task download <task-id>
JSON parse error on --inputInput file is not valid JSON or schema mismatchUse infsh app sample <app-id> --save input.json to regenerate a valid template
Image/video generation produces blank or corrupted outputModel inference failed silentlyRe-run the job; check app-specific known issues in infsh app get <app-id>; try a different model for the same task

Checklist

  • App is authenticated before running (infsh login check)
  • Model supports the requested input format (image/video/text sizes)
  • Task ID saved for async operations to retrieve results later
  • Credit cost checked before bulk operations
  • Output format confirmed (URL, file, or stdout) before passing to next step

Sources

  • inference.sh CLI documentation — installation, commands, authentication
  • inference.sh Apps Catalog — full app library with schemas and examples
  • OpenRouter API — LLM model routing and pricing
  • FLUX documentation (fal.ai, replicate.com) — image generation parameters and best practices
  • Veo API (Google DeepMind) — video generation capabilities and limitations
  • Tavily Search API (tavily.com) — web search and extraction endpoints
  • Exa API (exa.ai) — semantic search and content extraction
  • x.com Developer API — Twitter/X posting, DMs, and engagement endpoints

Anti-Patterns

Anti-patternWhy it failsFix
Not checking infsh app get before runningInput schema varies between apps; guessing fields causes 400 errorsAlways run infsh app sample first to see the exact schema
Hardcoding file paths without verifying they existThe CLI auto-uploads relative paths; missing files produce confusing errorsUse absolute paths or verify relative paths with Test-Path before running
Not using --no-wait for long-running tasksSynchronous runs block the terminal for minutes on video/3D generationUse --no-wait and poll with infsh task get <id> for tasks expected to take > 30s
Ignoring rate limits and credit costsEach app has different pricing; some cost $0.50+ per runCheck infsh app get <app-id> for cost estimate before bulk/generating runs
Using the cheapest model for everythingOpenRouter free models may have lower quality or stricter rate limitsMatch model quality to task importance; paid tiers are more reliable
Not saving task IDsAsync tasks complete after the terminal session; without the ID you can't retrieve resultsLog all task IDs: infsh task get <id> > task-<id>-result.json
Running image generation without checking supported resolutions/aspect ratiosModels silently crop or stretch to supported dimensionsCheck infsh app get for supported_sizes or aspect_ratios field
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall