Help us improve
Share bugs, ideas, or general feedback.
From liteharness
Generate or update architecture documentation for any project. Dispatches scout agents to explore the codebase, then writes structured architecture docs with an INDEX. Triggers on 'generate arch docs', 'create architecture docs', 'update arch docs', 'document this project', 'arch-gen', 'generate documentation'.
npx claudepluginhub ahostbr/liteharness-pluginHow this skill is triggered — by the user, by Claude, or both
Slash command
/liteharness:arch-genThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Generates comprehensive architecture documentation for any project by scouting the codebase and writing structured Markdown docs. This is the meta-evolution — the same process used to create LiteSuite's own architecture docs, packaged as a reusable skill.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Create and present web-based slidedecks using Slidev with Markdown, Vue components, code highlighting, animations, interactive demos, LaTeX, and Mermaid for technical presentations, conference talks, code walkthroughs, and teaching materials.
Share bugs, ideas, or general feedback.
Generates comprehensive architecture documentation for any project by scouting the codebase and writing structured Markdown docs. This is the meta-evolution — the same process used to create LiteSuite's own architecture docs, packaged as a reusable skill.
{project}/docs/architecture/
├── INDEX.md # Table of contents + section lookup
├── 00-Overview.md # Project overview, tech stack, directory layout
├── 01-{Module}.md # One doc per major module/subsystem
├── 02-{Module}.md # ...
└── NN-{Module}.md # As many as needed
Dispatch multiple parallel Haiku scout agents to explore the codebase:
For each scout, use the Agent tool with subagent_type: "Explore" and model: "haiku":
Agent({
subagent_type: "Explore",
model: "haiku",
prompt: "Explore {project_path} and report on {aspect}. Be thorough — read key files, don't just list them."
})
From scout results, identify:
For each identified subsystem, write a Markdown doc following this template:
# {Subsystem Name}
## Overview
One paragraph: what it does, where it lives, key tech.
## Architecture
Tables, code blocks, diagrams showing structure.
## Key Components
| Component | File | Purpose |
| --------- | ---- | ------- |
## API / IPC / Protocol
Routes, channels, message formats.
## Configuration
Settings, env vars, defaults.
## Key Files Reference
| File | Purpose |
| ---- | ------- |
Write INDEX.md with:
If the project uses Claude Code or LiteSuite harness, create an /arch skill pointing to the generated docs.
When updating existing docs (not generating from scratch):
INDEX.md to understand current doc structure{project}/docs/architecture-backup-{date}/