Skip to content

staruhub/ClaudeSkills / llm-wiki

llm-wiki

Verified

Build and maintain a structured LLM-generated wiki for any codebase. Use when the user asks to analyze/understand/document a codebase, build a code wiki, create project documentation from source, or update an existing .llm-wiki. Triggers on phrases like "build wiki", "analyze this codebase", "document this project", "update wiki", "llm-wiki", or when entering an unfamiliar project that has no .llm-wiki yet.

FileKindSize
SKILL.mdskill md6.4 KB
references/article-templates.mdmarkdown3.7 KB
references/wiki-schema.mdmarkdown4.2 KB

references/wiki-schema.md

View on GitHub
# Wiki Schema Reference

## _schema.md Format

The schema file is the wiki's configuration document. It records project metadata and wiki conventions.

```markdown
---
title: Wiki Schema
updated: YYYY-MM-DD
---

# Project Metadata

| Field | Value |
|-------|-------|
| Project Name | <name> |
| Language(s) | TypeScript, Python, etc. |
| Framework(s) | Next.js, FastAPI, etc. |
| Build System | npm, cargo, gradle, etc. |
| Entry Point(s) | src/index.ts, main.py, etc. |
| Test Framework | jest, pytest, etc. |
| Package Manager | pnpm, pip, etc. |
| Monorepo | yes/no |

# Directory Overview

<annotated tree of top-level directories and their purpose>

# Wiki Conventions

## Naming
- Article filenames: kebab-case.md (e.g., `user-auth.md`, `data-flow.md`)
- Directory names: lowercase, single word when possible

## Cross-references
- Use relative markdown links: `[Module Name](../modules/module-name.md)`
- Every article must be reachable from `_index.md` within 2 clicks

## Source Citations
- Reference source files as: `src/path/file.ext:L10-L25`
- Always include the file path in article frontmatter `sources` field

## Update Protocol
- After every update, bump the `updated` field in article frontmatter
- Append a summary line to `_log.md`
```

## _index.md Format

The index is a content-oriented catalog, NOT a flat file listing.

```markdown
---
title: Wiki Index
updated: YYYY-MM-DD
---

# <Project Name> Wiki

## Architecture
- [System Overview](architecture/overview.md) — High-level architecture and component diagram
- [Data Flow](architecture/data-flow.md) — How data moves through the system
- [Directory Structure](architecture/directory-structure.md) — Annotated project tree

## Modules
- [Auth](modules/auth.md) — Authentication and authorization
- [API Gateway](modules/api-gateway.md) — Request routing and middleware
- ...

## Concepts
- [Error Handling](concepts/error-handling.md) — Error strategy and patterns
- [Configuration](concepts/configuration.md) — Config loading and env vars
- ...

## APIs
- [REST API](apis/rest.md) — HTTP endpoints
- [CLI](apis/cli.md) — Command-line interface
- ...

## Guides
- [Setup](guides/setup.md) — Dev environment setup
- [Testing](guides/testing.md) — Running and writing tests
- ...
```

## _log.md Format

Chronological, append-only log with parseable timestamps.

```markdown
---
title: Wiki Log
---

# Wiki Activity Log

## 2026-04-09

- **[INIT]** Wiki created. Scanned 245 source files across 18 directories.
- **[WRITE]** architecture/overview.md — System architecture with component diagram
- **[WRITE]** modules/auth.md — Authentication module deep dive
- **[WRITE]** modules/api.md — API layer documentation
- **[INDEX]** Updated _index.md with 12 articles
- **[LINT]** Health check passed. 0 broken links, 0 orphan pages.

## 2026-04-15

- **[UPDATE]** modules/auth.md — Added OAuth2 PKCE flow (new in commit abc123)
- **[WRITE]** concepts/rate-limiting.md — New rate limiting middleware
- **[LINT]** Fixed 2 broken links in modules/api.md
```

Log entry tags:
- `[INIT]` — First build
- `[WRITE]` — New article created
- `[UPDATE]` — Existing article modified
- `[DELETE]` — Article removed
- `[RENAME]` — Article moved/renamed
- `[INDEX]` — Index updated
- `[LINT]` — Health check run
- `[SCHEMA]` — Schema updated

## Directory Structure

```
.llm-wiki/
├── _schema.md              # Project metadata + wiki conventions
├── _index.md               # Content-oriented catalog
├── _log.md                 # Chronological activity log
├── architecture/
│   ├── overview.md         # System architecture, component diagram
│   ├── data-flow.md        # Data flow through the system
│   └── directory-structure.md  # Annotated directory tree
├── modules/
│   ├── <module-a>.md       # One per major module
│   └── <module-b>.md
├── concepts/
│   ├── <concept-a>.md      # Cross-cutting concerns
│   └── <concept-b>.md
├── apis/
│   ├── <api-group>.md      # API surface documentation
│   └── ...
└── guides/
    ├── setup.md            # Dev environment setup
    ├── testing.md          # Testing guide
    └── ...
```
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 198kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 198kUpdated Claude CodeCodexVerifiedInstall