--- name: DocVQA slug: docvqa category: AI Engineering description: DocVQA guides an agent to extract exact, evidence-backed answers from document images, tables, forms, and handwriting. Use it when answering visual document questions where precision and exact text spans matter. github: "https://github.com/microsoft/SkillOpt/tree/main/ckpt/docvqa/gpt5.5_skill.md" language: Python stars: 16007 forks: 1489 install: "npx degit https://github.com/microsoft/SkillOpt/tree/main/ckpt/docvqa ~/.claude/skills/docvqa" installs_to: ~/.claude/skills/docvqa source_path: ckpt/docvqa/gpt5.5_skill.md collection_size: 12 category_size: 2451 collection_url: "https://dirskills.com/collections/microsoft/SkillOpt" added: 2026-08-14T07:12:42.961Z last_synced: 2026-08-14T07:12:42.961Z canonical_url: "https://dirskills.com/skills/docvqa" --- # DocVQA DocVQA guides an agent to extract exact, evidence-backed answers from document images, tables, forms, and handwriting. Use it when answering visual document questions where precision and exact text spans matter. **Install:** ```bash npx degit https://github.com/microsoft/SkillOpt/tree/main/ckpt/docvqa ~/.claude/skills/docvqa ``` ## README # DocVQA Skill ## Visual Evidence Discipline - Read the document carefully before answering. - Prefer the smallest exact text span that answers the question. - For questions asking for a value, count, page number, date, or graph reading, return only the requested value span; omit nearby labels, category names, units, or explanatory words unless the question explicitly asks for them. - When several nearby strings look similar, choose the one whose surrounding labels or layout best match the question. ## Exact Answer Discipline - Copy names, numbers, and dates exactly from the document whenever possible. - Preserve the document's exact spelling and punctuation for names and quoted phrases; do not substitute similar letters or change straight/curly quotes, spacing, or parentheses when the visible text provides them. - Prefer direct extraction over paraphrase. - Before finalizing, compare the answer against nearby alternatives and keep the best-supported exact span. ## Structured Layout Lookup - For tables, first find the row or entry named in the question, then read the value under the requested column, header, date, or category; answer with that cell only. - For forms, receipts, or labeled fields, locate the exact role, party, or field label mentioned in the question, then copy the filled-in value from the same line, box, block, or immediately adjacent field. - For table-of-contents, indexed, numbered, or bulleted lists, match the requested title, entry, or point number, then follow the same line or list item to the associated value; do not take a nearby value from another item. ## Anchored Handwriting / Nearby Text - For handwritten or list/table questions with an anchor term, first locate the anchor, then inspect the immediately adjacent text in the same row, column, or nearby margin. If legible, provide the best-supported nearby span rather than leaving the answer blank.