Andrew Yim
6d7a6d7a88
6 modular skills for curating, processing, and exporting reference docs: - reference-discovery: Search and validate authoritative sources - web-crawler-orchestrator: Multi-backend crawling (Firecrawl/Node/aiohttp/Scrapy) - content-repository: MySQL storage with version tracking - content-distiller: Summarization and key concept extraction - quality-reviewer: QA loop with approve/refactor/research routing - markdown-exporter: Structured output for Claude Projects or fine-tuning Cross-machine installation support: - Environment-based config (~/.reference-curator.env) - Commands tracked in repo, symlinked during install - install.sh with --minimal, --check, --uninstall modes - Firecrawl MCP as default (always available) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
47 lines
1.1 KiB
YAML
47 lines
1.1 KiB
YAML
# Reference Curator - Export Configuration
|
|
# Location: ~/.config/reference-curator/export_config.yaml
|
|
#
|
|
# Copy this file to ~/.config/reference-curator/export_config.yaml
|
|
|
|
output:
|
|
base_path: ~/reference-library/exports/
|
|
|
|
# Project files format (for Claude Projects)
|
|
project_files:
|
|
structure: nested_by_topic # flat | nested_by_topic | nested_by_source
|
|
index_file: INDEX.md
|
|
include_metadata: true
|
|
max_file_size_kb: 500
|
|
|
|
# Fine-tuning dataset format
|
|
fine_tuning:
|
|
format: jsonl
|
|
include_system_prompt: true
|
|
system_prompt: "You are an expert on AI and prompt engineering."
|
|
max_tokens_per_sample: 4096
|
|
|
|
# Knowledge base format
|
|
knowledge_base:
|
|
structure: flat
|
|
include_toc: true
|
|
|
|
# Quality thresholds
|
|
quality:
|
|
min_score_for_export: 0.80
|
|
require_human_review: false
|
|
auto_approve_tier1_sources: true
|
|
auto_approve_min_score: 0.80
|
|
|
|
# Cross-reference settings
|
|
cross_references:
|
|
enabled: true
|
|
min_concept_overlap: 2
|
|
max_related_docs: 5
|
|
|
|
# Verification
|
|
verification:
|
|
check_broken_links: true
|
|
validate_markdown: true
|
|
check_duplicates: true
|
|
max_allowed_duplicates: 0
|