corpus-search
Skill0 starsChanged 3 months agoNo licenceView on GitHub
ค้นเอกสารกองใหญ่ในเครื่อง (เล่มมาตรฐาน, คลังความรู้, wiki/Obsidian vault, ไฟล์ .txt/.md) แล้วคืนเฉพาะ excerpt สั้น ๆ พร้อมชื่อไฟล์+เลขบรรทัดสำหรับอ้างอิง — แทนการอ่านทั้งเล่ม เข้า context ซึ่งเปลือง token มหาศาล Use this skill BEFORE answering any question whose answer should come from local documents: standards books (มสพร./มรด./TGIX), a knowledge base, a wiki, a corpus folder, or any collection of .txt/.md files — especially when the user asks "เล่มเราเขียนว่าอย่างไร", "มีนิยามคำนี้ไหม", "อ้างอิงจากเล่มไหน", or asks you to cite sources. Also use it before drafting or reviewing a document that must be consistent with existing standards, and whenever you are tempted to read a large file into context to find one fact. Do NOT use for searching code (use Grep/Glob) or for questions the local documents cannot answer.
In this repository6 other files it gives its agents.
- flow-simSkill
- meeting-summarySkill
- meeting-transcribeSkill
- safe-coding-workflowSkill
- sak-saiSkill
- thai-pdf-extractSkill
The file
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
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.