Files

Andrew Yim 6d7a6d7a88 feat(reference-curator): Add portable skill suite for reference documentation curation

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>

2026-01-29 00:20:27 +07:00

3.0 KiB

Raw Permalink Blame History

Quality Reviewer

QA loop for reference library content. Scores distilled materials, routes decisions, and provides actionable feedback.

Trigger Keywords

"review content", "quality check", "QA review", "assess distilled content", "check reference quality"

Decision Flow

[Distilled Content]
       │
       ▼
┌─────────────────┐
│ Score Criteria  │ → accuracy, completeness, clarity, PE quality, usability
└─────────────────┘
       │
       ├── ≥ 0.85 → APPROVE → markdown-exporter
       ├── 0.60-0.84 → REFACTOR → content-distiller
       ├── 0.40-0.59 → DEEP_RESEARCH → web-crawler
       └── < 0.40 → REJECT → archive

Scoring Criteria

Criterion	Weight	Checks
Accuracy	0.25	Factual correctness, up-to-date, attribution
Completeness	0.20	Key concepts, examples, edge cases
Clarity	0.20	Structure, concise language, logical flow
PE Quality	0.25	Techniques, before/after, explains why
Usability	0.10	Easy reference, searchable, appropriate length

Workflow

Step 1: Load Pending Reviews

python scripts/load_pending_reviews.py --output pending.json

Step 2: Score Content

python scripts/score_content.py --distill-id 123 --output assessment.json

Step 3: Calculate Final Score

python scripts/calculate_score.py --assessment assessment.json

Step 4: Route Decision

python scripts/route_decision.py --distill-id 123 --score 0.78

Outputs:

approve → Ready for export
refactor → Return to distiller with instructions
deep_research → Need more sources (queries generated)
reject → Archive with reason

Step 5: Log Review

python scripts/log_review.py --distill-id 123 --decision refactor --instructions "Add more examples"

PE Quality Checklist

When scoring prompt_engineering_quality:

Demonstrates specific techniques (CoT, few-shot, etc.)
Shows before/after examples
Explains why techniques work
Provides actionable patterns
Includes edge cases and failure modes
References authoritative sources

Auto-Approve Rules

Tier 1 sources with score ≥ 0.80 may auto-approve:

# In config
quality:
  auto_approve_tier1_sources: true
  auto_approve_min_score: 0.80

Scripts

scripts/load_pending_reviews.py - Get pending reviews
scripts/score_content.py - Multi-criteria scoring
scripts/calculate_score.py - Weighted average calculation
scripts/route_decision.py - Decision routing logic
scripts/log_review.py - Log review to database
scripts/generate_feedback.py - Generate refactor instructions

Integration

From	Action	To
content-distiller	Distilled content	→
→	APPROVE	markdown-exporter
→	REFACTOR + instructions	content-distiller
→	DEEP_RESEARCH + queries	web-crawler-orchestrator

3.0 KiB Raw Permalink Blame History