document-chunker SKILL.md skillA
document-chunker from ellmos-ai/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ellmos-ai/skills/document-chunker@v1.1.0Pins v1.1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ellmos-ai/skills
- Path
skills/utilities/document-chunker/SKILL.md- Versions recorded
- 5
- Latest version
- v1.1.0, committed Nov 6, 2026
- First version recorded
- Jul 30, 2026
- Size
- 3,145 bytes
- Repository stars
- 9
- License
- MIT
Verwenden, wenn Text in Stücke zerlegt werden muss, die in eine Grenze passen: Dokumente für RAG, Embeddings oder einen Vektorspeicher vorbereiten, oder Text, der das Kontextfenster bzw. das Token-Limit eines Modells sprengt: 'teil das in Chunks', 'bereite die Docs für RAG auf', 'mein Embedding-Modell nimmt nur 512 Tokens', 'der Kontext läuft über', 'überlappende Stücke', 'jedes Stück braucht chunk_id und Quelle', /document-chunker. Zerlegt .txt-, .md-, .py- und .sh-Dateien oder ganze Ordner…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
<img src="banner.png" width="100%" alt="document-chunker banner">
> **Deutsch** — Offizielle Deutsch-Version / Documento Oficial en Deutsch.
# Document Chunker (Deutsch)
Splits documents into overlapping token chunks. Optimized for RAG pipelines
and LLM context windows. Zero dependencies — Python stdlib + re only.
## Usage
### As Library
```python
from document_chunker import DocumentChunker
chunker = DocumentChunker(chunk_size=400, overlap=80)
chunks = chunker.chunk_text("Long text...")
for chunk in chunks:
print(f"Chunk {chunk['chunk_id']}: {chunk['tokens']} tokens")
```
### Chunking a File
```python
chunks = chunker.chunk_document("document.md", source="My Project")
```
### Chunking an Entire Directory
```python
from document_chunker import chunk_corpus
chunks = chunk_corpus(["doc1.md", "doc2.txt"], source="Corpus")
```
### CLI
```bash
python document_chunker.py document.md # Single file
python document_chunker.py ./docs/ # Entire directory
```
## Parameters
| Parameter | Default | Description |
|-----------|---------|-------------|
| chunk_size | 400 | Max tokens per chunk |
| overlap | 80 | Overlapping tokens between chunks |
…Read the whole file at its exact version.
How to install
mdr add ellmos-ai/skills/document-chunker@sha256:be805da1e7731754The line at the top of this page pins the label v1.1.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_q2zhsaq4e7pslocn)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 30, 2026 and Nov 6, 2026, about one every 25 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.1.0 latest | 2026-11-06 | 0a1a5de | 3,145 B | A | view · diff |
| v1.0.0 | 2026-08-23 | f025c2c | 2,120 B | A | view · diff |
| v1.0.0 | 2026-07-30 | 08fbb89 | 2,101 B | A | view · diff |
| v1.0.0 | 2026-07-30 | 0a53eeb | 2,034 B | A | view · diff |
| v1.0.0 | 2026-07-30 | d690d83 | 2,100 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3145 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
ellmos-ai/skills · 9 stars · license MIT · pushed 2026-11-07 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_q2zhsaq4e7pslocn GET https://markdownregistry.com/api/v1/resolve?ref=ellmos-ai/skills/document-chunker GET https://markdownregistry.com/api/v1/blob/be805da1e773175460596eaa16033a5689e5f22b31aefa755ff21813e3402c03
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.