# AI use cases for Knowledge Base Kit (Sixian-Li/knowledge-base-kit)

Repo: [Sixian-Li/knowledge-base-kit](https://github.com/Sixian-Li/knowledge-base-kit) | Use cases: 4 | Page: https://dedupedai.com/use-cases/sixian-li-knowledge-base-kit/

Knowledge Base Kit is a Python toolkit that helps Claude Code or Codex turn documents into a local, source-backed Markdown knowledge base with full text, summaries, and a catalog.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Build a source-backed knowledge base from your documents: https://dedupedai.com/use-cases/sixian-li-knowledge-base-kit/build-source-backed-kb-with-codex/
- File documents into a knowledge base with Claude Code: https://dedupedai.com/use-cases/sixian-li-knowledge-base-kit/file-documents-with-claude-code/
- Try the offline demo with no account or model calls: https://dedupedai.com/use-cases/sixian-li-knowledge-base-kit/try-offline-demo-without-model-calls/
- Validate a knowledge base before sharing it: https://dedupedai.com/use-cases/sixian-li-knowledge-base-kit/validate-kb-before-sharing/

## How to build a source-backed knowledge base from your documents with Knowledge Base Kit

Repo: [Sixian-Li/knowledge-base-kit](https://github.com/Sixian-Li/knowledge-base-kit) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Set up a separate Markdown workspace and file documents with the Codex backend after review.

**Who it is for:** A researcher or analyst with a folder of PDFs, DOCX files, or notes who wants a searchable, source-backed knowledge base that an agent can read.

**The problem:** Raw documents are hard to reuse. Summaries get lost, and agents cannot tell what came from which source.

**The outcome:** A workspace with inbox/, catalog.md, categories, and per-document full.md, summary.md, and the original attachment, checked before filing.

### Steps

1. git clone https://github.com/Sixian-Li/knowledge-base-kit.git && cd Knowledge Base Kit (inferred, check the README)
2. `python3 -m venv .venv`
3. `source .venv/bin/activate`
4. `python -m pip install -r requirements.txt`
5. `python scripts/init_workspace.py ../my-kb --backend codex --with-example`
6. `cd ../my-kb` then `python kb.py check --backend codex`

### Prompt to paste into your agent

```text
In the knowledge-base-kit repo, initialize a Codex workspace at <workspace-path>. Then open that workspace in Codex and use the local process_docs skill with the Codex backend on <document-path>, and show the proposed category and changed files before filing. Verify that the workspace passes `python kb.py check --backend codex`.
```

### Caveat

Validators cannot prove factual accuracy or perfect coverage, so you still need to review the full text and summary the agent writes.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/sixian-li-knowledge-base-kit/build-source-backed-kb-with-codex/

## How to file documents into a knowledge base with Claude Code with Knowledge Base Kit

Repo: [Sixian-Li/knowledge-base-kit](https://github.com/Sixian-Li/knowledge-base-kit) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Initialize a workspace for Claude Code and process a document through the local skill.

**Who it is for:** A developer or writer who already uses Claude Code and wants to keep reading notes and attachments in a Markdown knowledge base.

**The problem:** Reference documents pile up in downloads folders, and agents re-read the same long files each session.

**The outcome:** A Claude Code-ready workspace where a processed document has full.md, summary.md, and its original attachment, plus a catalog agents can read first.

### Steps

1. git clone https://github.com/Sixian-Li/knowledge-base-kit.git && cd Knowledge Base Kit (inferred, check the README)
2. `python3 -m venv .venv`
3. `source .venv/bin/activate`
4. `python -m pip install -r requirements.txt`
5. `python scripts/init_workspace.py ../my-kb --backend claude` (inferred, check the README)
6. `cd ../my-kb` then `python kb.py check --backend claude` (inferred, check the README)

### Prompt to paste into your agent

```text
In the knowledge-base-kit repo, initialize a Claude backend workspace at <workspace-path>. Open it in Claude Code and use the local process_docs skill with the Claude backend on inbox/<file-name>. Show the proposed category and changed files and wait for review before filing. Verify that `python kb.py check --backend claude` passes.
```

### Caveat

Model-assisted processing requires an authenticated Claude Code CLI, and text drafting follows that provider's data handling.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/sixian-li-knowledge-base-kit/file-documents-with-claude-code/

## How to try the offline demo with no account or model calls with Knowledge Base Kit

Repo: [Sixian-Li/knowledge-base-kit](https://github.com/Sixian-Li/knowledge-base-kit) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Run the bundled demo to see extraction and validation without AI generation.

**Who it is for:** A curious reader or evaluator who wants to see the output format before connecting any AI account.

**The problem:** Before trusting a new workflow, you want to see what a filed document looks like without signing in to a model provider.

**The outcome:** A fresh demo workspace in ../kb-demo with extracted Markdown, a copied reviewed reference output, and passing validation.

### Steps

1. git clone https://github.com/Sixian-Li/knowledge-base-kit.git && cd Knowledge Base Kit (inferred, check the README)
2. `python3 -m venv .venv`
3. `source .venv/bin/activate`
4. `python -m pip install -r requirements.txt`
5. `python scripts/offline_demo.py ../kb-demo`

### Prompt to paste into your agent

```text
In the knowledge-base-kit repo, run `python scripts/offline_demo.py ../kb-demo`. Confirm that the demo workspace was created and that validation passed. Report the paths of examples/expected-output/quickstart/full.md and summary.md for comparison, and state that the demo does not simulate AI generation.
```

### Caveat

The demo copies a reviewed reference output, so it shows the format and checks, not how a live agent would write new summaries.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/sixian-li-knowledge-base-kit/try-offline-demo-without-model-calls/

## How to validate a knowledge base before sharing it with Knowledge Base Kit

Repo: [Sixian-Li/knowledge-base-kit](https://github.com/Sixian-Li/knowledge-base-kit) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README

Run the structure, link, and TeX checks on a workspace before you hand it to others.

**Who it is for:** A knowledge base maintainer who edits filed documents by hand or with an agent and needs to catch broken structure before sharing.

**The problem:** Hand edits and moved files can break links, catalog entries, or TeX blocks without any visible error.

**The outcome:** A clear pass or a list of structure, link, archive, or TeX problems to fix before the workspace is shared.

### Steps

1. `cd my-kb` (inferred, check the README)
2. `python kb.py check --backend codex`
3. Read each reported problem and fix the file it names.
4. Run `python kb.py check --backend codex` again until it passes.

### Prompt to paste into your agent

```text
In the my-kb workspace, run `python kb.py check --backend codex`. List each reported structure, link, archive folding, or TeX problem with its file path, fix only those files, and confirm the check passes again.
```

### Caveat

The checks cover structure, links, archive folding, and TeX validation only, not whether the summaries are factually correct.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/sixian-li-knowledge-base-kit/validate-kb-before-sharing/