docs-toc-shards-style
Skill0 starsChanged 5 months agoNo licenceView on GitHub
긴 SPEC.md / README.md / PLAN.md 같은 프로젝트 루트 문서를 한 파일에 다 쑤셔넣지 말고, 잘 짜여진 글처럼 작은 단위로 쪼개고 (각 shard 2–5KB), 루트 문서는 얇은 TOC + 1~2줄 요약 + 링크만 두는 패턴. 트리거 — 사용자가 "SPEC 너무 길다", "TOC 만들어", "잘게 쪼개서 관리해", "LLM이 빠르게 찾아갈 수 있게", "attention mechanism 처음/끝만 본다", "글을 잘 짜인 책처럼 구조화" 같은 말을 할 때, 또는 SPEC/README/PLAN/ARCHITECTURE 같은 루트 문서가 200줄/15KB 이상으로 자라고 LLM 컨텍스트에 자꾸 들어가는 게 보일 때. 핵심 — 루트는 인덱스, 살은 shard 에, shard 끼리는 [[wiki-link]] 로 상호참조, attention 머케니즘 한계 (앞/뒤만 잘 봄) 를 *반대로* 이용해 각 shard 가 그 자체로 짧고 self-contained 하도록.
In this repository21 other files it gives its agents.
- adsense-content-approval-strategySkill
- apple-buildSkill
- bulk-data-via-script-not-tokensSkill
- consulting-deck-craftSkill
- data-go-kr-api-quirksSkill
- design-policySkill
- external-content-citation-policySkill
- feature-flag-removalSkill
- geometric-folding-fabricationSkill
- geometric-foldingSkill
- git-commit-message-qualitySkill
- kakao-map-client-nav-relayoutSkill
- leaflet-marker-hitboxSkill
- macos-nativeSkill
- mit-ocw-vaultSkill
- obsidian-dailySkill
- obsidian-knowledgeSkill
- ssg-determinismSkill
- swiftuiSkill
- tier-grading-systemSkill
- writing-tone-personalSkill
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.