Skill486 repo starsupdated yesterday
lat-md-knowledge-graph
The lat-md-knowledge-graph skill organizes project-specific documentation into a linked markdown knowledge base that AI agents can search and reference, preventing repeated rediscovery of architecture decisions and domain rules. Use it when a single instruction file becomes unwieldy, when agents need persistent memory of business logic, or when test specifications require explicit links to implementation code.
Install in Claude Code
Copygit clone --depth 1 https://github.com/stevesolun/ctx /tmp/lat-md-knowledge-graph && cp -r /tmp/lat-md-knowledge-graph/imported-skills/lat-md/skills/lat-md-knowledge-graph ~/.claude/skills/lat-md-knowledge-graphThen start a new Claude Code session; the skill loads automatically.
Definition
SKILL.md
# lat.md Knowledge Graph ## Purpose Turn durable project knowledge into linked markdown files that agents can search, cite, and keep synchronized with code. ## When to Use - One root instruction file is too large or hides domain decisions. - Agents repeatedly rediscover the same architecture or business rules. - Test intent needs explicit specs linked to test code. - A custom harness needs persistent memory outside conversation history. ## Design Pattern 1. Create a repo-local knowledge directory such as `lat.md/` or `docs/knowledge/`. 2. Split pages by durable concepts: architecture, domain rules, workflows, interfaces, test specs, and operational constraints. 3. Link concepts with `[[wiki links]]`. 4. Link knowledge pages to source symbols or files. 5. Add code backlinks such as comments or metadata where the code implements a documented rule. 6. Add a check that fails on broken links, missing backlinks, stale indexes, or test specs without code mentions. ## ctx Fit Use this alongside ctx's LLM-wiki when a project needs its own local memory graph. ctx recommends skills/MCPs/agents from its catalog; the repo-local graph stores project-specific facts that should not live in the global catalog. ## Quality Bar - Page titles and section anchors are stable. - Links resolve both ways where needed. - Code backlinks are narrow and reviewable. - Checks run in CI before merge. - Sensitive facts stay out unless the repo already allows them. - The graph explains current behavior, not a speculative roadmap.
More from this repository
skill-routerSkill
Alive skill router — reads the current project's stack and loads/unloads skills dynamically. Invoke at session start or when project context changes.
agents-md-protocolSkill
>
cavecrewSkill
>
caveman-commitSkill
>
caveman-compressSkill
>
caveman-helpSkill
>
caveman-reviewSkill
>
caveman-statsSkill
>