agentleFS
LinuxSuRenLinuxSuRen/my-dsh-skills/skills/patent-map/SKILL.md

patent-map

Skill2 starsChanged 39 days agoMITView on GitHub

专利地图:基于通俗解读已入库的 Obsidian 案例,点名后打开五种图。地形按 bge-small-zh 向量摊开。

  • Installs packages

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

专利地图

用途

把已经解读入库的案例摊成五种图(语义地形),给代理师找相近案子、看申请人重叠和文内引证。本包只读 vault、起本地页。空白点只表示「库里没读到」。

何时用

须用户点名(专利地图 / 案例地图 / /专利地图 / /patent-map)。解读继续只入库。

输入

已有解读入库的 vault(与解读同一份:PATENT_READER_OBSIDIAN_VAULT 或 ~/.patent-disclosure-skill/obsidian_vault.txt)。取数优先扫 Research/Patents/**/*_解读_*.md。若本机 obsidian CLI 可用且库已打开,用 obsidian vaults / base:query 核对,不替代磁盘扫描。

步骤

  1. Read prompts/guardrails.md → intake.md
  2. 确认库路径
  3. 启动:
python patent-map/tools/serve_map.py

stdout 机读前缀:MAP_URL: / MAP_PORT: / MAP_VAULT: / MAP_SOURCE: / MAP_CACHE: / MAP_MODEL:。端口由系统随机分配(127.0.0.1:0)。对话里把 URL 发给用户。

地形图按解读短文向量摊开。加载名 BAAI/bge-small-zh-v1.5,磁盘只装 Qdrant ONNX(见 prompts/guardrails.md 取数)。数据与模型默认目录:{Documents}/patent-disclosure-skill/patent-map/(与 oa 同级)。未装 fastembed 时图仍能开,地形退回 IPC 簇。

可选:

pip install -r patent-map/tools/requirements.txt
python patent-map/tools/ensure_model.py

单独拷走本包时:python tools/serve_map.py。

护栏

  • 细则 prompts/guardrails.md。地图脚本只用本包 tools/;解读笔记直接读 vault 文件。

产出物

本机页面 URL(MAP_URL)。索引与模型在 {Documents}/patent-disclosure-skill/patent-map/。本包不设「交付后请确认」。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.