knowledge-base-builder
Build searchable knowledge bases from document collections (PDFs, Word, text files). Use for creating technical libraries, standards repositories, research databases, or any large document collection requiring full-text search.
Best use case
knowledge-base-builder is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Build searchable knowledge bases from document collections (PDFs, Word, text files). Use for creating technical libraries, standards repositories, research databases, or any large document collection requiring full-text search.
Teams using knowledge-base-builder should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/knowledge-base-builder/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How knowledge-base-builder Compares
| Feature / Agent | knowledge-base-builder | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Build searchable knowledge bases from document collections (PDFs, Word, text files). Use for creating technical libraries, standards repositories, research databases, or any large document collection requiring full-text search.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Knowledge Base Builder
## Overview
This skill creates searchable knowledge bases from document collections using SQLite FTS5 full-text search indexing. It handles PDF extraction, text chunking, metadata cataloging, and search interface creation.
## Quick Start
```python
import sqlite3
conn = sqlite3.connect("knowledge.db", timeout=30)
cursor = conn.cursor()
# Create FTS5 search table
cursor.execute('''
CREATE VIRTUAL TABLE IF NOT EXISTS search_index
USING fts5(content, filename)
''')
# Add content
cursor.execute('INSERT INTO search_index VALUES (?, ?)',
("Sample document text...", "doc.pdf"))
# Search
cursor.execute("SELECT * FROM search_index WHERE search_index MATCH 'sample'")
print(cursor.fetchall())
```
## When to Use
- Building searchable technical standards libraries
- Creating research paper databases
- Indexing corporate document repositories
- Setting up knowledge management systems
- Converting file-based document collections to queryable databases
## Architecture
```
Document Collection
|
v
+------------------+
| 1. Inventory | Scan files, extract metadata
+--------+---------+
v
+------------------+
| 2. Extract | PDF -> text, chunk by pages
+--------+---------+
v
+------------------+
| 3. Index | SQLite FTS5 full-text search
+--------+---------+
v
+------------------+
| 4. Search CLI | Query interface with filtering
+------------------+
```
## Implementation Steps
See [references/implementation.md](references/implementation.md) for detailed code for each step (schema creation, document inventory, PDF extraction, search interface, CLI template, and usage examples).
## Related Skills
- `semantic-search-setup` - Add vector embeddings for AI search
- `rag-system-builder` - Build AI Q&A on top of knowledge base
- `pdf/text-extractor` - Detailed PDF extraction options
## Version History
- **1.1.0** (2026-01-02): Added Quick Start, Execution Checklist, Error Handling, Metrics sections; updated frontmatter with version, category, related_skills
- **1.0.0** (2024-10-15): Initial release with SQLite FTS5 full-text search, PDF extraction, CLI
## Sub-Skills
- [Execution Checklist](execution-checklist/SKILL.md)
- [Error Handling](error-handling/SKILL.md)
- [Metrics](metrics/SKILL.md)
- [Best Practices](best-practices/SKILL.md)
- [Dependencies](dependencies/SKILL.md)Related Skills
domain-knowledge-sweep
Systematic multi-source research of an engineering domain. Spawns parent issue → 6 research subissues (Standards, Academic, Industry, LinkedIn-marketing, Code-audit, Synthesis) → gap implementation subissues. Replaces LinkedIn-only extraction with defensible comprehensive sourcing.
public-knowledge-graph-governance
Maintain public-safe knowledge graph artifacts for llm-wiki and similar markdown knowledge bases. Use when changing graph generators, validators, schema docs, weekly freshness checks, or public/private source-scope boundaries.
improve-codebase-architecture
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
workspace-knowledge-doc-contracts
Class-level workspace knowledge, LLM-wiki, repo mission contracts, stale doc references, semantic taxonomy, and knowledge-source reconnaissance.
wave-based-parallel-plan-execution
Orchestrate phase execution by discovering dependencies, grouping into waves, spawning subagents, and collecting results with optional wave filtering
portable-config-baseline-pattern
Extract machine-agnostic settings into portable template files while keeping machine-specific hooks and plugins separate
portable-baseline-pattern-implementation
Implement portable configuration baselines by separating machine-agnostic settings from machine-specific hooks and plugins
portable-baseline-pattern-extraction
Extract and separate portable baseline config from machine-specific overrides in multi-environment projects
portable-baseline-configuration-pattern
Separate portable/universal config from machine-specific settings to enable safe template reuse across environments
portable-baseline-config-pattern
Separate machine-portable baseline config from environment-specific hooks and plugins
batch-syntax-fix-with-regex-line-based-fallback
Fix repeated syntax errors across many files using regex, then fall back to line-based parsing when regex fails
interactive-Codex-to-file-based-fallback
Switch from tmux/interactive Codex to file-based Codex -p execution when interactive runs fail with upstream errors or analysis-only stalls, then verify landing from git/GitHub state.