{
  "schemaVersion": "1.0",
  "item": {
    "slug": "fal",
    "name": "fal",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/apekshik/fal",
    "canonicalUrl": "https://clawhub.ai/apekshik/fal",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/fal",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=fal",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "models-reference.md",
      "README.md",
      "SKILL.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "slug": "fal",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-11T23:46:02.794Z",
      "expiresAt": "2026-05-18T23:46:02.794Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=fal",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=fal",
        "contentDisposition": "attachment; filename=\"fal-1.0.1.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "fal"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/fal"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/fal",
    "agentPageUrl": "https://openagent3.xyz/skills/fal/agent",
    "manifestUrl": "https://openagent3.xyz/skills/fal/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/fal/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "fal.ai Model API Skill",
        "body": "Run 1000+ generative AI models on fal.ai."
      },
      {
        "title": "Arguments",
        "body": "Command: $0 (search | schema | run | status | result | upload)\nArg 1: $1 (model_id, search query, or file path)\nArg 2+: $2, $3, etc. (additional parameters)\nAll args: $ARGUMENTS"
      },
      {
        "title": "Session Output",
        "body": "Save generated files to session folder:\n\nmkdir -p ~/.fal/sessions/${CLAUDE_SESSION_ID}\n\nDownloaded images/videos go to: ~/.fal/sessions/${CLAUDE_SESSION_ID}/"
      },
      {
        "title": "Authentication",
        "body": "Requires FAL_KEY environment variable. If requests fail with 401, tell user:\n\nGet an API key from https://fal.ai/dashboard/keys\nThen: export FAL_KEY=\"your-key-here\""
      },
      {
        "title": "If $0 = \"search\"",
        "body": "Search for models matching $1:\n\ncurl -s \"https://api.fal.ai/v1/models?q=$1&limit=15\" \\\n  -H \"Authorization: Key $FAL_KEY\" | jq -r '.models[] | \"• \\(.endpoint_id) — \\(.metadata.display_name) [\\(.metadata.category)]\"'\n\nFor category search, use:\n\ncurl -s \"https://api.fal.ai/v1/models?category=$1&limit=15\" \\\n  -H \"Authorization: Key $FAL_KEY\" | jq -r '.models[] | \"• \\(.endpoint_id) — \\(.metadata.display_name)\"'\n\nCategories: text-to-image, image-to-video, text-to-video, image-to-3d, training, speech-to-text, text-to-speech"
      },
      {
        "title": "If $0 = \"schema\"",
        "body": "Get input schema for model $1:\n\ncurl -s \"https://api.fal.ai/v1/models?endpoint_id=$1&expand=openapi-3.0\" \\\n  -H \"Authorization: Key $FAL_KEY\" | jq '.models[0].openapi.components.schemas.Input.properties'\n\nShow required vs optional fields to help user understand what inputs are needed."
      },
      {
        "title": "If $0 = \"run\"",
        "body": "Run model $1 with parameters from remaining arguments.\n\nStep 1: Parse parameters\nExtract --key value pairs from $ARGUMENTS after the model_id to build JSON payload.\n\nExample: /fal run fal-ai/flux-2 --prompt \"a cat\" --image_size landscape_16_9\n→ Model: fal-ai/flux-2\n→ Payload: {\"prompt\": \"a cat\", \"image_size\": \"landscape_16_9\"}\n\nStep 2: Submit to queue\n\ncurl -s -X POST \"https://queue.fal.run/$1\" \\\n  -H \"Authorization: Key $FAL_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '<JSON_PAYLOAD>'\n\nStep 3: Poll until complete\n\n# Get request_id from response, then poll:\nwhile true; do\n  STATUS=$(curl -s \"https://queue.fal.run/$1/requests/$REQUEST_ID/status\" \\\n    -H \"Authorization: Key $FAL_KEY\" | jq -r '.status')\n  echo \"Status: $STATUS\"\n  if [ \"$STATUS\" = \"COMPLETED\" ]; then break; fi\n  if [ \"$STATUS\" = \"FAILED\" ]; then echo \"Job failed\"; break; fi\n  sleep 3\ndone\n\nStep 4: Get result and save\n\n# Fetch result\nRESULT=$(curl -s \"https://queue.fal.run/$1/requests/$REQUEST_ID\" \\\n  -H \"Authorization: Key $FAL_KEY\")\n\n# Create session output folder\nmkdir -p ~/.fal/sessions/${CLAUDE_SESSION_ID}\n\n# Download images/videos\n# For images: jq -r '.images[0].url' and curl to download\n# Save as: ~/.fal/sessions/${CLAUDE_SESSION_ID}/<timestamp>_<model>.png"
      },
      {
        "title": "If $0 = \"status\"",
        "body": "Check status of request $2 for model $1:\n\ncurl -s \"https://queue.fal.run/$1/requests/$2/status?logs=1\" \\\n  -H \"Authorization: Key $FAL_KEY\" | jq '{status: .status, queue_position: .queue_position, logs: .logs}'"
      },
      {
        "title": "If $0 = \"result\"",
        "body": "Get result of completed request $2 for model $1:\n\ncurl -s \"https://queue.fal.run/$1/requests/$2\" \\\n  -H \"Authorization: Key $FAL_KEY\" | jq '.'"
      },
      {
        "title": "If $0 = \"upload\"",
        "body": "Upload file $1 to fal CDN:\n\ncurl -s -X POST \"https://fal.run/fal-ai/storage/upload\" \\\n  -H \"Authorization: Key $FAL_KEY\" \\\n  -F \"file=@$1\"\n\nReturns URL to use in model requests."
      },
      {
        "title": "Quick Reference",
        "body": "Popular models:\n\nfal-ai/flux-2 — Fast text-to-image\nfal-ai/flux-2-pro — High quality text-to-image\nfal-ai/kling-video/v2/image-to-video — Image to video\nfal-ai/minimax/video-01/image-to-video — Image to video\nfal-ai/whisper — Speech to text\n\nCommon parameters for text-to-image:\n\n--prompt \"description\" — What to generate\n--image_size landscape_16_9 — Aspect ratio (square, portrait_4_3, landscape_16_9)\n--num_images 1 — Number of images\n\nExample invocations:\n\n/fal search video — Find video models\n/fal schema fal-ai/flux-2 — See input options\n/fal run fal-ai/flux-2 --prompt \"a sunset over mountains\"\n/fal status fal-ai/flux-2 abc-123\n/fal upload ./photo.png"
      }
    ],
    "body": "fal.ai Model API Skill\n\nRun 1000+ generative AI models on fal.ai.\n\nArguments\nCommand: $0 (search | schema | run | status | result | upload)\nArg 1: $1 (model_id, search query, or file path)\nArg 2+: $2, $3, etc. (additional parameters)\nAll args: $ARGUMENTS\nSession Output\n\nSave generated files to session folder:\n\nmkdir -p ~/.fal/sessions/${CLAUDE_SESSION_ID}\n\n\nDownloaded images/videos go to: ~/.fal/sessions/${CLAUDE_SESSION_ID}/\n\nAuthentication\n\nRequires FAL_KEY environment variable. If requests fail with 401, tell user:\n\nGet an API key from https://fal.ai/dashboard/keys\nThen: export FAL_KEY=\"your-key-here\"\n\nCommand: $0\nIf $0 = \"search\"\n\nSearch for models matching $1:\n\ncurl -s \"https://api.fal.ai/v1/models?q=$1&limit=15\" \\\n  -H \"Authorization: Key $FAL_KEY\" | jq -r '.models[] | \"• \\(.endpoint_id) — \\(.metadata.display_name) [\\(.metadata.category)]\"'\n\n\nFor category search, use:\n\ncurl -s \"https://api.fal.ai/v1/models?category=$1&limit=15\" \\\n  -H \"Authorization: Key $FAL_KEY\" | jq -r '.models[] | \"• \\(.endpoint_id) — \\(.metadata.display_name)\"'\n\n\nCategories: text-to-image, image-to-video, text-to-video, image-to-3d, training, speech-to-text, text-to-speech\n\nIf $0 = \"schema\"\n\nGet input schema for model $1:\n\ncurl -s \"https://api.fal.ai/v1/models?endpoint_id=$1&expand=openapi-3.0\" \\\n  -H \"Authorization: Key $FAL_KEY\" | jq '.models[0].openapi.components.schemas.Input.properties'\n\n\nShow required vs optional fields to help user understand what inputs are needed.\n\nIf $0 = \"run\"\n\nRun model $1 with parameters from remaining arguments.\n\nStep 1: Parse parameters Extract --key value pairs from $ARGUMENTS after the model_id to build JSON payload.\n\nExample: /fal run fal-ai/flux-2 --prompt \"a cat\" --image_size landscape_16_9 → Model: fal-ai/flux-2 → Payload: {\"prompt\": \"a cat\", \"image_size\": \"landscape_16_9\"}\n\nStep 2: Submit to queue\n\ncurl -s -X POST \"https://queue.fal.run/$1\" \\\n  -H \"Authorization: Key $FAL_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '<JSON_PAYLOAD>'\n\n\nStep 3: Poll until complete\n\n# Get request_id from response, then poll:\nwhile true; do\n  STATUS=$(curl -s \"https://queue.fal.run/$1/requests/$REQUEST_ID/status\" \\\n    -H \"Authorization: Key $FAL_KEY\" | jq -r '.status')\n  echo \"Status: $STATUS\"\n  if [ \"$STATUS\" = \"COMPLETED\" ]; then break; fi\n  if [ \"$STATUS\" = \"FAILED\" ]; then echo \"Job failed\"; break; fi\n  sleep 3\ndone\n\n\nStep 4: Get result and save\n\n# Fetch result\nRESULT=$(curl -s \"https://queue.fal.run/$1/requests/$REQUEST_ID\" \\\n  -H \"Authorization: Key $FAL_KEY\")\n\n# Create session output folder\nmkdir -p ~/.fal/sessions/${CLAUDE_SESSION_ID}\n\n# Download images/videos\n# For images: jq -r '.images[0].url' and curl to download\n# Save as: ~/.fal/sessions/${CLAUDE_SESSION_ID}/<timestamp>_<model>.png\n\nIf $0 = \"status\"\n\nCheck status of request $2 for model $1:\n\ncurl -s \"https://queue.fal.run/$1/requests/$2/status?logs=1\" \\\n  -H \"Authorization: Key $FAL_KEY\" | jq '{status: .status, queue_position: .queue_position, logs: .logs}'\n\nIf $0 = \"result\"\n\nGet result of completed request $2 for model $1:\n\ncurl -s \"https://queue.fal.run/$1/requests/$2\" \\\n  -H \"Authorization: Key $FAL_KEY\" | jq '.'\n\nIf $0 = \"upload\"\n\nUpload file $1 to fal CDN:\n\ncurl -s -X POST \"https://fal.run/fal-ai/storage/upload\" \\\n  -H \"Authorization: Key $FAL_KEY\" \\\n  -F \"file=@$1\"\n\n\nReturns URL to use in model requests.\n\nQuick Reference\n\nPopular models:\n\nfal-ai/flux-2 — Fast text-to-image\nfal-ai/flux-2-pro — High quality text-to-image\nfal-ai/kling-video/v2/image-to-video — Image to video\nfal-ai/minimax/video-01/image-to-video — Image to video\nfal-ai/whisper — Speech to text\n\nCommon parameters for text-to-image:\n\n--prompt \"description\" — What to generate\n--image_size landscape_16_9 — Aspect ratio (square, portrait_4_3, landscape_16_9)\n--num_images 1 — Number of images\n\nExample invocations:\n\n/fal search video — Find video models\n/fal schema fal-ai/flux-2 — See input options\n/fal run fal-ai/flux-2 --prompt \"a sunset over mountains\"\n/fal status fal-ai/flux-2 abc-123\n/fal upload ./photo.png"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/apekshik/fal",
    "publisherUrl": "https://clawhub.ai/apekshik/fal",
    "owner": "apekshik",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/fal",
    "downloadUrl": "https://openagent3.xyz/downloads/fal",
    "agentUrl": "https://openagent3.xyz/skills/fal/agent",
    "manifestUrl": "https://openagent3.xyz/skills/fal/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/fal/agent.md"
  }
}