# Send falimagegen to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - 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. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text 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. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "falimagegen", "name": "falimagegen", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/xxmzdxxxm/falimagegen", "canonicalUrl": "https://clawhub.ai/xxmzdxxxm/falimagegen", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/falimagegen", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=falimagegen", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "agents/openai.yaml", "references/fal-model-examples.md", "references/fal-model-api-checklist.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "falimagegen", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-11T23:48:11.859Z", "expiresAt": "2026-05-18T23:48:11.859Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=falimagegen", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=falimagegen", "contentDisposition": "attachment; filename=\"falimagegen-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "falimagegen" }, "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/falimagegen" }, "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." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/falimagegen", "downloadUrl": "https://openagent3.xyz/downloads/falimagegen", "agentUrl": "https://openagent3.xyz/skills/falimagegen/agent", "manifestUrl": "https://openagent3.xyz/skills/falimagegen/agent.json", "briefUrl": "https://openagent3.xyz/skills/falimagegen/agent.md" } } ``` ## Documentation ### Overview Use this skill to implement text-to-image or image-to-image calls against fal model APIs. Prioritize correctness by checking the current docs for the selected model’s required inputs/outputs and authentication requirements. ### Quick Start Identify the target model ID from the fal model API docs. Collect inputs from the user. Text-to-image: prompt, optional negative_prompt, size/aspect, steps, seed, safety options. Image-to-image: source image URL, strength/denoise, plus prompt/options above. Pick the calling method. If the user prefers SDKs: provide Python and/or JavaScript examples. If the user prefers REST: provide a curl/HTTP example. Execute the request and return image URL(s) from the response. ### Workflow: Text-to-Image Resolve the model ID and schema. Open the fal model API docs and confirm the exact input fields and output format. Validate inputs. Ensure prompt is non-empty and size/aspect settings are supported by the model. Build the request. SDK: call the SDK’s run/submit method with an input object. REST: call the model endpoint with a JSON body that matches the schema. Execute and parse output. Extract image URL(s) from the response fields defined by the model. Return URLs. Provide a clean list of URLs and note any metadata the user asked for (seed, size, etc.). ### Workflow: Image-to-Image Resolve the model ID and schema. Validate inputs. Ensure the source image is reachable by URL (or converted to the required format). Confirm any strength/denoise range constraints from docs. Build the request. Include source image + prompt + other options as required by the model. Execute and parse output. Extract image URL(s) from the response fields defined by the model. Return URLs. ### SDK vs REST Guidance Prefer SDKs for simpler auth and retries. Prefer REST when the user needs raw HTTP examples, or when running in environments without SDK support. Never hardcode API keys. Follow the docs for the required environment variable or header name. ### Minimal Examples (Fill From Docs) Use these as templates only. Replace placeholders after checking the docs. ### Python (SDK) # Pseudocode: replace with the exact fal SDK import + call pattern from docs import os # from fal import client # or the current SDK import MODEL_ID = "" input_data = { "prompt": "a cinematic photo of a red fox", # "image_url": "https://..." # for image-to-image # "negative_prompt": "...", # "width": 1024, # "height": 1024, } # result = client.run(MODEL_ID, input=input_data) # urls = extract_urls(result) ### JavaScript (SDK) // Pseudocode: replace with the exact fal SDK import + call pattern from docs // import { client } from "@fal-ai/client"; const MODEL_ID = ""; const input = { prompt: "a cinematic photo of a red fox", // image_url: "https://..." // for image-to-image }; // const result = await client.run(MODEL_ID, { input }); // const urls = extractUrls(result); ### REST (curl) # Pseudocode: replace endpoint, headers, and payload schema from docs curl -X POST "https:///" \\ -H "Authorization: Bearer " \\ -H "Content-Type: application/json" \\ -d '{ "prompt": "a cinematic photo of a red fox" }' ### Resources references/fal-model-api-checklist.md: Checklist for gathering inputs and validating responses. references/fal-model-examples.md: Example templates for text-to-image, image-to-image, and REST usage. ## Trust - Source: tencent - Verification: Indexed source record - Publisher: xxmzdxxxm - Version: 1.0.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-11T23:48:11.859Z - Expires at: 2026-05-18T23:48:11.859Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/falimagegen) - [Send to Agent page](https://openagent3.xyz/skills/falimagegen/agent) - [JSON manifest](https://openagent3.xyz/skills/falimagegen/agent.json) - [Markdown brief](https://openagent3.xyz/skills/falimagegen/agent.md) - [Download page](https://openagent3.xyz/downloads/falimagegen)