메뉴
OOMOL Fusion API (oomol.com). Use this skill for ANY OOMOL Fusion API request — reading, creating, updating, and deleting data. Whenever a task involves OOMOL Fusion API, use this skill instead of calling the API directly.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/oomol-lab/skills --skill oo-fusion-api명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SKILL.md 표시 중
| name | oo-fusion-api |
| description | OOMOL Fusion API (oomol.com). Use this skill for ANY OOMOL Fusion API request — reading, creating, updating, and deleting data. Whenever a task involves OOMOL Fusion API, use this skill instead of calling the API directly. |
| allowed-tools | ["Bash(oo *)"] |
| metadata | {"title":"OOMOL Fusion API","author":"OOMOL","version":"1.0.4","services":["fusion-api"],"icon":"https://static.oomol.com/logo/logo.png"} |
Operate OOMOL Fusion API through your OOMOL-connected account. This skill calls the fusion-api connector with the oo CLI; OOMOL injects credentials server-side, so you never handle raw tokens.
OOMOL Fusion API needs no account connection. Assume the oo CLI is installed and signed in. Do not run oo auth login proactively — just run the action. Fall back to First-time setup only when a command actually fails.
1. Inspect the contract to get the authoritative input/output schema before building a payload:
oo connector schema "fusion-api" --action "<action_name>"
2. Run the action with a JSON payload that matches the input schema:
oo connector run "fusion-api" --action "<action_name>" --data '<json>' --json
--data takes a JSON object string or @path/to/file.json; omit it to send {}.{ "data": ..., "meta": { "executionId": "..." } }; the execution id lives under meta.executionId.Each action is listed below with a one-line description; actions that change state carry a [write] or [destructive] tag. Before constructing --data, fetch the action's live schema with oo connector schema to get its authoritative input fields.
cosyvoice_tts_generate — Generate speech audio with CosyVoice TTS.cphone_nano_banana_result — Get cphone-nano-banana task resultcphone_nano_banana_state — Get cphone-nano-banana task statecphone_nano_banana_submit — Edit images with Nano Banana [write]deepseek_ocr_recognize — Recognize text from a single image.doubao_stt_result — Get doubao-stt task resultdoubao_stt_state — Get doubao-stt task statedoubao_stt_submit — Convert speech to text with Doubao [write]doubao_text_to_image_seedream_generate — Generate images from text with Doubao Seedreamdoubao_tts_result — Get doubao-tts task resultdoubao_tts_state — Get doubao-tts task statedoubao_tts_submit — Convert text to speech with Doubao [write]fal_aura_sr_result — Get fal-aura-sr task resultfal_aura_sr_state — Get fal-aura-sr task statefal_aura_sr_submit — Image super-resolution upscaling [write]fal_nano_banana_2_result — Get fal-nano-banana-2 task resultfal_nano_banana_2_state — Get fal-nano-banana-2 task statefal_nano_banana_2_submit — Generate or edit images with Nano Banana 2 [write]fal_nano_banana_pro_result — Get fal-nano-banana-pro task resultfal_nano_banana_pro_state — Get fal-nano-banana-pro task statefal_nano_banana_pro_submit — Edit images with Nano Banana Pro [write]fal_nano_banana_result — Get fal-nano-banana task resultfal_nano_banana_state — Get fal-nano-banana task statefal_nano_banana_submit — Edit images with Nano Banana [write]fal_qwen_image_layered_result — Get the Qwen Image Layered task resultfal_qwen_image_layered_state — Get the Qwen Image Layered task statefal_qwen_image_layered_submit — Split an image into multiple layers with Qwen Image Layered [write][write] change OOMOL Fusion API state — confirm the exact payload and effect with the user before running.[destructive] remove or overwrite data — always confirm the target and get explicit approval first.These are one-time steps — do not repeat them on every call. Run a step only when a command fails for the matching reason.
oo: command not found — install the oo CLI (other platforms: https://cli.oomol.com/install-guide.md):
curl -fsSL https://cli.oomol.com/install.sh | bash # macOS / Linux
irm https://cli.oomol.com/install.ps1 | iex # Windows PowerShell
Not signed in / authentication error — sign in to your OOMOL account once:
oo auth login
HTTP 402 / OOMOL_INSUFFICIENT_CREDIT — billing stop. Recharge at https://console.oomol.com/billing/token-recharge before retrying.
fal_remove_background_resultfal_remove_background_state — Get fal-remove-background task state [destructive]fal_remove_background_submit — Remove image backgrounds with the Fal.ai BRIA model [destructive]file_upload_abort_multipart_upload — Abort multipart upload [write]file_upload_complete_multipart_upload — Complete multipart upload [write]file_upload_create_multipart_upload — Initialize multipart upload [write]file_upload_generate_presigned_url — Generate a presigned URL for file upload [write]file_upload_generate_presigned_urls — Generate a presigned URL for multipart upload parts [write]jina_reader_read — Read and extract URL contentjina_reader_search — Search web contentoomol_tts_ng_generate — Generate speech audiooomol_tts_result — Get oomol-tts task resultoomol_tts_state — Get oomol-tts task stateoomol_tts_submit — Convert text to audio [write]openai_image_async_result — Get asynchronous OpenAI image generation resultopenai_image_async_submit — Submit asynchronous OpenAI image generation requests, including gpt-image-2 image creation. [write]openai_image_edit_async_result — Get asynchronous OpenAI image edit result [write]openai_image_edit_async_submit — Submit asynchronous OpenAI image edit requests, including gpt-image-2 image editing. [write]pdf_transform_epub_result — Get pdf-transform-epub task resultpdf_transform_epub_state — Get pdf-transform-epub task statepdf_transform_epub_submit — Convert a PDF to EPUB format [write]pdf_transform_markdown_result — Get pdf-transform-markdown task resultpdf_transform_markdown_state — Get pdf-transform-markdown task statepdf_transform_markdown_submit — Convert a PDF to Markdown format [write]qwen_asr_filetrans_result — Get Qwen ASR file transcription task resultqwen_asr_filetrans_state — Get Qwen ASR file transcription task stateqwen_asr_filetrans_submit — Submit a long-audio speech recognition task with Qwen ASR file transcription [write]qwen_doc_turbo_analyze — Analyze documents with Tongyi Qianwenqwen_image_edit_plus_edit — Edit images with Tongyi Wanxiang [write]qwen_image_generate — Generate images with Tongyi Qianwenqwen_mt_image_result — Get qwen-mt-image task resultqwen_mt_image_state — Get qwen-mt-image task stateqwen_mt_image_submit — Image machine translation [write]qwen_tts_generate — Generate speech audioqwen_voice_cloning_create — Create a Qwen voice cloning voice and return a preview audio URL. [write]qwen_voice_design_create — Create a Qwen voice design voice and return preview audio. [write]qwen_voice_design_delete — Delete a Qwen voice design voice. [destructive]qwen_voice_design_generate — Generate speech audio using a Qwen voice design voice.qwen_voice_design_list — List Qwen voice design voices.qwen_voice_design_query — Get details for a Qwen voice design voice.seedance_video_result — Query a Seedance video generation task resultseedance_video_state — Get a Seedance video generation task stateseedance_video_submit — Generate videos with Doubao Seedance [write]text_to_epub_illustrate_generate — Generate illustrations for EPUB contenttinify_png_shrink_compress — Compress PNG images with the Tinify APIwanx_i2v_video_result — Query first-frame-to-video task resultwanx_i2v_video_state — Get wanx-i2v-video task statewanx_i2v_video_submit — Generate videos from the first frame with Tongyi Wanxiang [write]wanx_image_result — Get wanx-image task resultwanx_image_state — Get wanx-image task statewanx_image_submit — Generate and edit images with Tongyi Wanxiang AI [write]wanx_kf2v_video_result — Get wanx-kf2v-video task resultwanx_kf2v_video_state — Get wanx-kf2v-video task statewanx_kf2v_video_submit — Generate videos from keyframes with Tongyi Wanxiang [write]wanx_r2v_video_result — Query reference-to-video task resultwanx_r2v_video_state — Get wanx-r2v-video task statewanx_r2v_video_submit — Generate videos from reference assets with Tongyi Wanxiang [write]wanx_t2v_video_result — Query text-to-video task resultwanx_t2v_video_state — Get wanx-t2v-video task statewanx_t2v_video_submit — Generate text-to-video videos with Tongyi Wanxiang [write]17TRACK (17track.net). Use this skill for ANY 17TRACK request — reading, creating, and updating data. Whenever a task involves 17TRACK, use this skill instead of calling the API directly.
Xweather (xweather.com). Use this skill for ANY Xweather request — searching and reading data. Whenever a task involves Xweather, use this skill instead of calling the API directly.
Alt Text Generator AI (alttextgeneratorai.com). Use this skill for ANY Alt Text Generator AI request — searching and reading data. Whenever a task involves Alt Text Generator AI, use this skill instead of calling the API directly.
SOC 직업 분류 기준
