Quicksilver
Project / 项目 · In the catalogue / 在目录中查看
What Jev decides here · Jev 在这里做什么决定
Document triage (文档分拣), Context compaction (上下文压缩)
noul: read in the code by a model, not yet by a person 由模型在代码里读到，尚无人复核
a model read the call site; no person yet 模型读过调用点，尚无人复核 · · Cited file / 引用的文件: skills/quicksilver/scripts/qs.mjs
Summary · 摘要
Claude Code skill that hands relevance calls to Jev: one noul per file, log line or ticket ('which of these files handle auth?'), asked in parallel and sorted by probability, so Claude gets a shortlist with confidences instead of reading everything.written by a model
一个 Claude Code 技能，把“是否相关”的判断交给 Jev：对每个文件、每行日志或每张工单问一个 noul（例如“这些文件里哪些处理鉴权？”），并行询问并按概率排序，于是 Claude 拿到的是带置信度的候选清单，而不必通读全部内容。模型撰写机翻
Notes · 备注
Row drafted from the discovery queue (issue #14) by an AI assistant that read the README and the cited file on 2026-10-24; a maintainer has not yet read the call site.
本条目由 AI 助手根据发现队列（issue #14）起草，于 2026-10-24 阅读了 README 和所引文件；维护者尚未亲自阅读调用点。
Launches · 发布记录
Not launched yet. 还没有发布过。 Launch it / 发布它 ↗ · How a product launches / 怎样发布一个产品
Makers · Maker
Made this? Confirm or correct its entry / 这是你做的？确认或更正条目 ↗
The same form takes the product's one line and a demo link, in its maker's own words. 同一个表单也可以补上产品的一句话和演示链接，用 Maker 自己的话。
Badge for its README · README 徽章
[](https://kydlikebtc.github.io/awesome-jev/products/quicksilver.html)One line for the product's README, linked to this page. The picture says that it is listed; while it is on the launch board, that it is launching; after a week in the top three, its place. It is rebuilt with the site, so the line never needs changing. 放进产品 README 的一行，链接到本页。图片显示已收录；在发布榜上时显示正在发布；进过某周前三后显示名次。它随网站一起重建，这一行不用再改。
Also under this pattern · 同一模式的其他产品
docjev
Classifies and splits PDF, DOCX and PPTX files: LiteParse extracts page text locally, then Jev picks a document's category with a choice over your rules, or for a packet answers per page a category choice and a noul on whether a new document starts there. Its report covers 40 real PDFs.
tax-doc-classifier
Classifies tax document pages: one request per page asks Jev two choices, page kind (7 options) and IRS form (230 plus none), and a follow-up choice for five forms' schedules; criteria come from IRS PDFs and code gates at 0.95. Its author measured no strict error on 314 filled pages.
formanator
Submits Forma benefit claims from the command line or an MCP client. With --category-provider jev, Jev picks the benefit and category with a choice over the pairs Forma allows plus no_match, seeing only merchant and description; under 0.5 confidence or no match it falls back to the configured LLM.
doc-router
Rust library that decides page by page whether a PDF needs OCR: Jev, or by default a bundled heuristic, answers one noul per page from text-layer evidence; text pages are extracted locally and only the rest go to an OCR model through LiteLLM. In the author's run, 87 of 155 pages were billed.
jevmory
Local memory for coding agents: hooks store what sessions actually said as verbatim quotes, and jevmory audit asks Jev, for each line of a MEMORY.md, whether stored evidence supports or contradicts it, marking it keep, stale, wrong or unsupported. Python standard library, SQLite; grading is opt-in.