> For the complete documentation index, see [llms.txt](https://thecontentforge.gitbook.io/thecontentforge-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://thecontentforge.gitbook.io/thecontentforge-docs/feature-glossary/glossary/assets-and-knowledge.md). # Assets and Knowledge *Last updated: 2026-08-07.* Where your brand files and your reference material live. Everything here is designed to feed the writing tools, so drafts start from approved logos, real documents, and your actual product knowledge instead of a blank page. * **Asset Library** - A shared home for logos, templates, fonts, icons, on-camera host photos, and documents. Upload up to five files at a time, review and name each one before it saves, and pick a category so the grid stays organised as the library grows. * **Category filters** - One-click filters across the top show how many assets sit in each category, so finding the right logo or template takes seconds rather than scrolling. Web3 project accounts also get FAQ, help docs, and roadmap categories, and meme or culture-coin accounts get a wider set again covering mascots, meme templates, community screenshots, approved and banned claims, and official links. * **Preview, rename and download** - Every asset shows a preview in the grid, can be renamed inline, and downloads privately to you. Downloading a file never makes it public, so an asset stays inside the workspace until you deliberately share it. * **Public share links** - Turn one asset into a short public link for a newsletter, an email, or a public page. The product confirms with you first because it makes the file world-readable, copies the link automatically, and lets you revoke it later so it stops loading wherever it was used. * **Safe for content** - A per-asset switch that tells the writing tools they are allowed to draw on that asset's contents, with a matching tick box at upload time to mark a whole batch at once. Documents you have not switched on are not pulled into a draft, which keeps unapproved material out of published copy. This appears for Web3 project accounts. * **Document analysis** - Upload a PDF, Markdown, or text file and the product reads it, then hands back a plain-language summary, a section-by-section breakdown, the key claims, and the numbers worth quoting. Progress shows live on the card, and if your plan's page cap meant only part of a long document was read, it says so. You can re-analyse at any time to pick up a corrected file or a raised cap. * **Post ideas and thread drafts from a document** - Alongside the summary, an analysed document produces suggested post angles with a hook and an angle per platform, plus ready-to-edit thread outlines you can lift straight into a draft. * **Use as source** - One click sends a document's summary, key claims, and metrics into the writing tool as the starting context for a new post, so you never retype what the analysis already found. * **Batch image transforms** - Select several images in the library at once and run a ready-made resize, thumbnail, logo cleanup or compression pack against all of them. The packs themselves are described under Batch Image Transforms on the Image Forge page. * **Knowledge Base** - An in-app reader for the documentation you have brought into TCF. Pick a source, filter its pages by title, and read clean formatted text with links back to the original page. If a refresh is running or a refresh failed, you keep reading the last good copy rather than seeing an empty screen. * **Send to Forge** - From any documentation page, or any single section within a page, send the content straight into the writing tool as the source for a post about that feature. It arrives pre-framed as a short-form social draft so you are editing, not starting over. * **Add a knowledge source** - Point at a documentation site, a sitemap, a specific list of page URLs, or upload a PDF or Markdown file. The product reads the content and tidies it up, and it then becomes the highest-priority reference the writing tools reach for. * **Ingestion progress and parse quality** - Each source shows live progress with an estimated time remaining, then a quality score out of one hundred, how many pages and sections were taken in, the first of those sections so you can eyeball the result, and warnings. When a site does not read cleanly it tells you what to try instead, such as uploading the Markdown directly or listing specific pages. * **Daily sync and manual refresh** - Turn on automatic daily syncing per source or refresh on demand. A refresh is quick, and it brings your copy back in line with whatever has changed on the source since last time. * **Source tuning** - Per source you can set priority, switch it on or off, decide whether it is used during generation, adjust how strongly it is favoured when the writing tools look for reference material, and exclude paths such as archives, changelogs, or old versions. * **Ask your Knowledge Base** - Type a question in plain English and get an answer written only from your own documentation, with numbered citations pointing at the exact pages and headings used. If the answer is not in your docs it says so rather than inventing one. * **AI-readable exports** - Every source also produces two condensed text files, a short index and a full-text version, in the format AI assistants and crawlers look for. Download them, copy a link, regenerate them, or verify they exist. Hosting them on your own docs domain is optional and does not affect answers inside TCF. * **Load a URL as a source** - Alongside the material you have brought into the library, any article, blog post or X link can be read on the spot and turned into source material for a draft. It is a Content Forge control, described under Working in Content Forge on the Content Forge page. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://thecontentforge.gitbook.io/thecontentforge-docs/feature-glossary/glossary/assets-and-knowledge.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.