# I Built DeepRead: An Evidence-First Reading Skill for Articles, Books, and PDFs > Source: > Published: 2026-08-16 16:31:18+00:00 I recently built an open-source project called **DeepRead** to solve a problem I kept seeing with AI reading tools. Most tools can summarize a document quickly, but they often blur the line between the author's actual claims, the evidence provided by the source, and the model's own inferences. With long documents, source locations and the context around numerical claims can also disappear. DeepRead turns articles, books, PDFs, and document sets into structured reports organized around **claims, evidence, data, and relationships**. Important claims are linked to supporting evidence and source locations. If the source does not provide evidence, the report says so instead of filling the gap. `quick` `deep` `map` `feynman` `book` DeepRead can also compare 2–10 documents and identify agreements, conflicts, and complementary evidence. The portable skill has no additional runtime dependencies: ``` npx skills@latest add xiehuan123/dsh-deepread ``` Example prompt: ``` Deep-read architecture.pdf in knowledge-map mode. For every important claim, show the supporting evidence and page location. ``` The full plugin includes a reading panel, PDF extraction, background jobs, live progress, batch comparison, cost estimates, and Markdown, HTML, or XMind-compatible export. ``` dsh plugin --profile web add dsh-deepread ``` GitHub: [https://github.com/xiehuan123/dsh-deepread](https://github.com/xiehuan123/dsh-deepread) v0.5.4 Release: [https://github.com/xiehuan123/dsh-deepread/releases/tag/v0.5.4](https://github.com/xiehuan123/dsh-deepread/releases/tag/v0.5.4) The repository contains three real output examples rather than hand-written mockups. DeepRead has already been included in several DeepSeek Harness and DSH community collections. Its GitHub Awesome Copilot submission has also passed the automated specification, lint, installation, and version checks and is waiting for maintainer review. The project is MIT licensed. I would especially like feedback on one question: Is explicit claim-to-evidence tracing useful in your reading workflow, or does it make the report too heavy? Issues and pull requests are welcome. Suggested DEV tags: `showdev` , `opensource` , `ai` , `productivity` Suggested Show HN title: `Show HN: DeepRead – Evidence-first reading for books, articles, and PDFs`