القائمة
Use when generating a cited comparison table or structured dataset from the current project's imported notebook sources.
يُحدَّد Prompt الذي يراجع المصدر أولًا بشكل افتراضي. يمكنك التبديل إلى أمر مباشر أو تنزيل نسخة محلية.
اقرأ SKILL.md وأي ملفات مرافقة يعرضها SkillsMP قبل أن تقرر التثبيت.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
يتجاوز الأمر المباشر Prompt المخصّص للمراجعة. افحص المصدر قبل تشغيله.
npx skills add https://github.com/mofa-org/mofa-skills --skill mofa-notebook-data-tableيبقى الأمر في سطر واحد. مرّر أفقيًا لمراجعته كاملًا قبل النسخ.
تفضّل نسخة محلية؟ نزّل الملفات المتاحة حاليًا لدى SkillsMP.
AI-generated greeting cards as PNG images. Triggers: greeting card, 贺卡, mofa card, mofa 贺卡, make a card, CNY card, New Year card, 新年贺卡, ink-wash card. Generates full-bleed AI artwork via Gemini in various Chinese art styles.
AI-generated comic strips and illustrations. Triggers: comic, manga, xkcd, 漫画, comic strip, 四格漫画, panel comic, illustration strip, snoopy. Generates multi-panel comics via Gemini with optional Qwen-Edit refinement, stitched into a single image.
Extract a video frame at a specific timestamp. Triggers: extract frame, 提取画面, screenshot video, capture frame, 截图, grab frame, video frame at, 视频截图.
استنادا إلى تصنيف SOC المهني
عرض SKILL.md
| name | mofa-notebook-data-table |
| description | Use when generating a cited comparison table or structured dataset from the current project's imported notebook sources. |
Call data_table_generate once. The skill handles source loading, model calls,
large-source batching, candidate merging, citation validation, and artifact
export internally.
Imported notebook sources are required. Optional arguments:
prompt: Describe the desired rows, columns, or comparison.source_ids: Limit grounding to selected imported sources.title: Set the table title and artifact filename.language: Request an output language.max_rows: Limit output to 1-500 rows.provider: Select gemini, openai, or vertex.model: Override the provider's default model.Octos injects workspace_root. Standalone callers may pass workspace.
The skill gives the model labelled notebook chunks and requires every non-empty cell to cite exact chunk IDs. It rejects missing or unknown citations, then resolves citation metadata from local source files rather than trusting model metadata.
Successful calls create JSON, Markdown, table CSV, and citation CSV files under
notebook-outputs/data-tables/. The result includes those artifact paths and
absolute files_to_send paths.
Gemini is selected when GEMINI_API_KEY is available. OpenAI-compatible chat
completions use OPENAI_API_KEY. Vertex AI Gemini uses a Google service
account JSON path or raw JSON from GOOGLE_APPLICATION_CREDENTIALS, or Octos'
profile/keychain service account JSON from VERTEX_SA_JSON; set
GOOGLE_CLOUD_PROJECT only when the JSON lacks project_id. Optional endpoint
overrides are GEMINI_BASE_URL, OPENAI_BASE_URL, and VERTEX_BASE_URL.
GOOGLE_CLOUD_LOCATION defaults to us-central1; set it to global for the
global Vertex endpoint. MOFA_NOTEBOOK_PROVIDER and
MOFA_NOTEBOOK_MODEL provide shared notebook defaults;
MOFA_DATA_TABLE_PROVIDER and MOFA_DATA_TABLE_MODEL remain accepted for
compatibility.
Run from the repository root:
printf '%s' '{"workspace":"/path/to/project","prompt":"Compare revenue"}' |
./mofa-notebook-data-table/main data_table_generate
The binary uses the same JSON stdin/stdout protocol as Octos and can be tested without Octos by pointing a provider base URL at a local HTTP fixture.