Skip to main content
skill Claude Code CX Codex Cursor GitHub Copilot

wiki-ingest — Claude Code skill: wiki ingestion and setup

Builds a linked wiki knowledge base from articles, documents, and notes. Use it when project material needs to become separate, cross-referenced knowledge pages.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add sanyuan0704/sanyuan-skills --skill wiki-ingest -a claude-code
Open on GitHub

What wiki-ingest does

The skill accepts pasted text, file paths, and directories for batch processing. It extracts concepts, products, engineering patterns, and comparisons, then gives each knowledge entity its own Markdown page. One entity gets one page.

By default, the wiki lives in wiki/, with index.md, log.md, and directories for concepts, products, patterns, and comparisons. The skill checks the existing index, extends pages rather than replacing them, and maintains links such as [[concepts/agent-loop]].

Every ingest updates the index and operation log. In batch mode, it extracts entities from the full set before changing pages and references. That matters if wiki/ already contains material, because existing pages and cross-references are updated.

What it helps with

  • turn notes into structured wiki pages
  • split knowledge entities into separate files
  • link related concepts and tools
  • update a wiki table of contents
  • record wiki changes in a log

Example prompts for the agent

  • `/wiki-ingest add this text to the project wiki`
  • `/wiki-ingest process the files in docs/ and update wiki/`
  • `/wiki-ingest build a knowledge base from notes.md`

How to install wiki-ingest

1Skills CLI (Vercel)

npx skills add sanyuan0704/sanyuan-skills --skill wiki-ingest -a claude-code

2Manually: put the files in place

~/.claude/skills/wiki-ingest/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/wiki-ingest/

From the same set6

The whole set →

Similar

prd-development deanpeters Guides you through writing a structured PRD from discovery notes and user research for engineering handoff. Best for major product initiatives. Claude Code CX Codex Cursor +1 4,700installs pptx-quality-gates kimtth Checks and repairs editable PPTX decks for geometry, accessibility, native objects, source lineage, and OOXML package integrity before delivery. Claude Code CX Codex Cursor 2,500installs architect jsmastery-pro Structures architectural discovery and writes build specifications into docs/specs/. It helps choose tech stacks and design features before writing any code. Claude Code CX Codex Cursor +1 6,800installs visual-explainer nicobailon Generates self-contained HTML visual explanations with SVG diagrams, architectures, and animated flows. Useful for code reviews, system designs, and technical concepts. Claude Code CX Codex Cursor +1 748installs feishu-doc m1heng Reads, creates, and edits Feishu documents using Markdown, and handles document comments directly from your AI agent. Claude Code CX Codex Cursor +1 1,900installs review-docs tldraw Evaluates and iterates on tldraw SDK documentation against style guides and actual code. Useful for auditing articles and catching inaccurate API references. Claude Code CX Codex Cursor +1 390installs grill-with-docs Matt Pocock This skill interviews you about a plan or design and creates ADRs and a glossary along the way. Use it when decisions need sharper definition. Claude Code 1,219,756installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs

Questions about wiki-ingest

How do I install wiki-ingest in Claude Code?

Run npx skills add sanyuan0704/sanyuan-skills --skill wiki-ingest -a claude-code, then run npx skills add sanyuan0704/sanyuan-skills --skill wiki-ingest -a claude-code again. The skill file is at ~/.claude/skills/wiki-ingest/SKILL.md.

What does wiki-ingest do?

It turns text, documents, and notes into a structured wiki. It creates or updates entity pages, links between them, an index, and an operation log.

How does wiki-ingest avoid duplicate pages?

It reads wiki/index.md before processing content and checks the existing wiki. When a page exists, it appends new material instead of overwriting it.

Source text

SKILL.md · MIT
---
name: wiki-ingest
description: "Compile articles, documents, or notes into a structured wiki knowledge base. Use when user says 'ingest to wiki', 'compile to knowledge base', 'update wiki', 'wiki ingest', 'add this to wiki', or invokes /wiki-ingest. Supports single or batch ingest. Triggers: wiki, ingest, knowledge base, compile, digest, index, catalog."
---

# Wiki Ingest — Knowledge Base Compiler

Compile any text content (articles, documents, notes) into structured wiki pages with cross-references, building a searchable, interconnected knowledge network.

IRON LAW: One wiki page = one knowledge entity. Never cram multiple concepts into one page.

## Wiki Directory Structure

Wiki defaults to `wiki/` under the current project root. User may specify a different path.

```
wiki/
├── index.md              # Full table of contents
├── log.md                # Append-only operation log
├── concepts/             # Core concept pages
├── products/             # Product/tool entity pages
├── patterns/             # Engineering patterns & design decisions
└── comparisons/          # Cross-topic comparison pages
```

## Workflow

### 1. Confirm Input

Accept user-specified content source:
- Pasted text directly
- File path(s) (md, txt, pdf, etc.)
- Directory path (batch processing)

If user doesn't specify a wiki path, use `wiki/`. Create the directory if it doesn't exist.

### 2. Check Existing Wiki

Read `wiki/index.md` (if exists) to understand existing pages and avoid duplicates.

### 3. Extract Knowledge Entities

Extract from content:
- **Concepts** (`concepts/`): Abstract ideas, terminology, theories
- **Products** (`products/`): Specific products, tools, services
- **Patterns** (`patterns/`): Engineering patterns, design decisions, methodologies
- **Comparisons** (`comparisons/`): Cross-product or cross-approach analysis

Extraction threshold: An entity deserves its own page only if it would be referenced by other pages.

### 4. Create or Update Pages

Each entity maps to one wiki page.

→ Load [references/page-templates.md](references/page-templates.md) for page templates.

Rules:
- If page already exists → **update** it, append new information, don't overwrite existing content
- Keep the one-line definition stable unless the new content provides a clearly better one
- Prioritize updating "Sources" and "Related Pages" sections

### 5. Update Cross-References

Check all existing wiki pages. If new content involves concepts referenced in other pages:
- Update their Related Pages list
- Update their Sources list
- Supplement new information in their detail sections

### 6. Update index.md

Add new page entries to `wiki/index.md`, organized by category.

### 7. Append to log.md

Append to `wiki/log.md`:

```markdown
## YYYY-MM-DD: Ingest <source title>

**Source**: <file path or "user input">
**New pages**: list newly created pages
**Updated pages**: list modified pages
**New cross-references**: list newly established links
```

### 8. Report Results

Tell user: what pages were created, what pages were updated, what new cross-references were established.

## File Naming

- All lowercase, hyphen-separated: `agent-loop.md`, `kv-cache.md`
- Name by entity, not by number

## Cross-Reference Format

- Use `[[category/page-name]]` double-link format (Obsidian-compatible), e.g. `[[concepts/agent-loop]]`, `[[products/claude-code]]`
- Always include the category prefix to avoid ambiguity across directories
- List all related pages at the bottom of each page

## Guidelines

- Never create duplicate pages — always check wiki/ first
- Don't extract trivial entities — if a concept appears once and won't be referenced elsewhere, skip it
- For batch processing: extract all entities first, then create pages and update references in one pass to avoid inconsistent intermediate states
- Always update index.md and log.md after every ingest

© sanyuan0704 · MIT · sanyuan0704/sanyuan-skills

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor