lat-md-knowledge-graph
Design or audit a repo-local markdown knowledge graph with wiki links, source-code backlinks, drift checks, and searchable sections. Use when AGENTS.md/CLAUDE.md is too flat for a large codebase or when a custom harness needs durable structured project memory.
- License 许可
- MIT
- 所属仓库
- stevesolun/ctx
- 最近更新
- 2026-10-15
- Stars
- ★ 590
- Forks
- 69
01 前言 Front Matter
- name
- lat-md-knowledge-graph
- description
- Design or audit a repo-local markdown knowledge graph with wiki links, source-code backlinks, drift checks, and searchable sections. Use when AGENTS.md/CLAUDE.md is too flat for a large codebase or when a custom harness needs durable structured project memory.
03 SKILL.md 正文
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
- Create a repo-local knowledge directory such as
lat.md/ordocs/knowledge/. - Split pages by durable concepts: architecture, domain rules, workflows, interfaces, test specs, and operational constraints.
- Link concepts with
[[wiki links]]. - Link knowledge pages to source symbols or files.
- Add code backlinks such as comments or metadata where the code implements a documented rule.
- 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.
04 同仓库更多 Skills
toolbox
Pre/post dev toolbox — named bundles of skills/agents loaded before development work and councils of experts invoked after. Run /toolbox or the toolbox.py CLI to list, activate, initialize, export, import, and validate toolboxes. Invoke at the start or end of a dev session, when setting up a new repo, or when sharing toolboxes with a team.
skill-router
Alive skill router — reads the current project's stack and loads/unloads skills dynamically. Invoke at session start or when project context changes.
repo-stats-autoupdate
Keeps README badge + inline counts in sync with the real number of skills, agents, graph nodes/edges, communities, converted pipelines, and test inventory. Runs automatically on every commit via a git pre-commit hook. Use when the README drifts from reality or before publishing a release.
find-skills
Discover installable agent skills from ctx's shipped Skills.sh catalog, the Skills.sh search API, and the npx skills CLI. Use when a user asks whether a skill exists, wants to add/update a skill, or needs a repeatable procedure for finding candidate skills safely.
no-mistakes
Validate committed feature-branch changes through the no-mistakes pipeline: intent, rebase, review, test, docs, lint, push, PR, and CI. Use when the user asks to run no-mistakes, ship safely, validate before pushing, or gate a change before it reaches upstream.
zoom-out
Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.