feat(reference-curator): Add Claude.ai Projects export format

Add claude-project/ folder with skill files formatted for upload to
Claude.ai Projects (web interface):

- reference-curator-complete.md: All 6 skills consolidated
- INDEX.md: Overview and workflow documentation
- Individual skill files (01-06) without YAML frontmatter

Add --claude-ai option to install.sh:
- Lists available files for upload
- Optionally copies to custom destination directory
- Provides upload instructions for Claude.ai

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
2026-01-29 00:33:06 +07:00
parent 8762f68e6e
commit 243b9d851c
10 changed files with 1987 additions and 0 deletions

View File

@@ -0,0 +1,290 @@
# Markdown Exporter
Exports approved content as structured markdown files for Claude Projects or fine-tuning.
## Export Configuration
```yaml
# ~/.config/reference-curator/export_config.yaml
output:
base_path: ~/reference-library/exports/
project_files:
structure: nested_by_topic # flat | nested_by_topic | nested_by_source
index_file: INDEX.md
include_metadata: true
fine_tuning:
format: jsonl
max_tokens_per_sample: 4096
include_system_prompt: true
quality:
min_score_for_export: 0.80
```
## Export Workflow
### Step 1: Query Approved Content
```python
def get_exportable_content(cursor, min_score=0.80, topic_filter=None):
"""Get all approved content meeting quality threshold."""
sql = """
SELECT d.doc_id, d.title, d.url,
dc.summary, dc.key_concepts, dc.code_snippets, dc.structured_content,
t.topic_slug, t.topic_name,
rl.quality_score, s.credibility_tier, s.vendor
FROM documents d
JOIN distilled_content dc ON d.doc_id = dc.doc_id
JOIN document_topics dt ON d.doc_id = dt.doc_id
JOIN topics t ON dt.topic_id = t.topic_id
JOIN review_logs rl ON dc.distill_id = rl.distill_id
JOIN sources s ON d.source_id = s.source_id
WHERE rl.decision = 'approve'
AND rl.quality_score >= %s
AND rl.review_id = (
SELECT MAX(review_id) FROM review_logs
WHERE distill_id = dc.distill_id
)
"""
params = [min_score]
if topic_filter:
sql += " AND t.topic_slug IN (%s)" % ','.join(['%s'] * len(topic_filter))
params.extend(topic_filter)
sql += " ORDER BY t.topic_slug, rl.quality_score DESC"
cursor.execute(sql, params)
return cursor.fetchall()
```
### Step 2: Organize by Structure
**Nested by Topic (recommended):**
```
exports/
├── INDEX.md
├── prompt-engineering/
│ ├── _index.md
│ ├── 01-chain-of-thought.md
│ ├── 02-few-shot-prompting.md
│ └── 03-system-prompts.md
├── claude-models/
│ ├── _index.md
│ ├── 01-model-comparison.md
│ └── 02-context-windows.md
└── agent-building/
├── _index.md
└── 01-tool-use.md
```
**Flat Structure:**
```
exports/
├── INDEX.md
├── prompt-engineering-chain-of-thought.md
├── prompt-engineering-few-shot.md
└── claude-models-comparison.md
```
### Step 3: Generate Files
**Document File Template:**
```python
def generate_document_file(doc, include_metadata=True):
content = []
if include_metadata:
content.append("---")
content.append(f"title: {doc['title']}")
content.append(f"source: {doc['url']}")
content.append(f"vendor: {doc['vendor']}")
content.append(f"tier: {doc['credibility_tier']}")
content.append(f"quality_score: {doc['quality_score']:.2f}")
content.append(f"exported: {datetime.now().isoformat()}")
content.append("---")
content.append("")
content.append(doc['structured_content'])
return "\n".join(content)
```
**Topic Index Template:**
```python
def generate_topic_index(topic_slug, topic_name, documents):
content = [
f"# {topic_name}",
"",
f"This section contains {len(documents)} reference documents.",
"",
"## Contents",
""
]
for i, doc in enumerate(documents, 1):
filename = generate_filename(doc['title'])
content.append(f"{i}. [{doc['title']}]({filename})")
return "\n".join(content)
```
**Root INDEX Template:**
```python
def generate_root_index(topics_with_counts, export_date):
content = [
"# Reference Library",
"",
f"Exported: {export_date}",
"",
"## Topics",
""
]
for topic in topics_with_counts:
content.append(f"- [{topic['name']}]({topic['slug']}/) ({topic['count']} documents)")
content.extend([
"",
"## Quality Standards",
"",
"All documents in this library have:",
"- Passed quality review (score ≥ 0.80)",
"- Been distilled for conciseness",
"- Verified source attribution"
])
return "\n".join(content)
```
### Step 4: Write Files
```python
def export_project_files(content_list, config):
base_path = Path(config['output']['base_path'])
structure = config['output']['project_files']['structure']
# Group by topic
by_topic = defaultdict(list)
for doc in content_list:
by_topic[doc['topic_slug']].append(doc)
# Create directories and files
for topic_slug, docs in by_topic.items():
if structure == 'nested_by_topic':
topic_dir = base_path / topic_slug
topic_dir.mkdir(parents=True, exist_ok=True)
# Write topic index
topic_index = generate_topic_index(topic_slug, docs[0]['topic_name'], docs)
(topic_dir / '_index.md').write_text(topic_index)
# Write document files
for i, doc in enumerate(docs, 1):
filename = f"{i:02d}-{slugify(doc['title'])}.md"
file_content = generate_document_file(doc)
(topic_dir / filename).write_text(file_content)
# Write root INDEX
topics_summary = [
{"slug": slug, "name": docs[0]['topic_name'], "count": len(docs)}
for slug, docs in by_topic.items()
]
root_index = generate_root_index(topics_summary, datetime.now().isoformat())
(base_path / 'INDEX.md').write_text(root_index)
```
### Step 5: Fine-tuning Export (Optional)
```python
def export_fine_tuning_dataset(content_list, config):
"""Export as JSONL for fine-tuning."""
output_path = Path(config['output']['base_path']) / 'fine_tuning.jsonl'
max_tokens = config['output']['fine_tuning']['max_tokens_per_sample']
with open(output_path, 'w') as f:
for doc in content_list:
sample = {
"messages": [
{
"role": "system",
"content": "You are an expert on AI and prompt engineering."
},
{
"role": "user",
"content": f"Explain {doc['title']}"
},
{
"role": "assistant",
"content": truncate_to_tokens(doc['structured_content'], max_tokens)
}
],
"metadata": {
"source": doc['url'],
"topic": doc['topic_slug'],
"quality_score": doc['quality_score']
}
}
f.write(json.dumps(sample) + '\n')
```
### Step 6: Log Export Job
```python
def log_export_job(cursor, export_name, export_type, output_path,
topic_filter, total_docs, total_tokens):
sql = """
INSERT INTO export_jobs
(export_name, export_type, output_format, topic_filter, output_path,
total_documents, total_tokens, status, started_at, completed_at)
VALUES (%s, %s, 'markdown', %s, %s, %s, %s, 'completed', NOW(), NOW())
"""
cursor.execute(sql, (
export_name, export_type,
json.dumps(topic_filter) if topic_filter else None,
str(output_path), total_docs, total_tokens
))
```
## Cross-Reference Generation
Link related documents:
```python
def add_cross_references(doc, all_docs):
"""Find and link related documents."""
related = []
doc_concepts = set(c['term'].lower() for c in doc['key_concepts'])
for other in all_docs:
if other['doc_id'] == doc['doc_id']:
continue
other_concepts = set(c['term'].lower() for c in other['key_concepts'])
overlap = len(doc_concepts & other_concepts)
if overlap >= 2:
related.append({
"title": other['title'],
"path": generate_relative_path(doc, other),
"overlap": overlap
})
return sorted(related, key=lambda x: x['overlap'], reverse=True)[:5]
```
## Output Verification
After export, verify:
- [ ] All files readable and valid markdown
- [ ] INDEX.md links resolve correctly
- [ ] No broken cross-references
- [ ] Total token count matches expectation
- [ ] No duplicate content
## Integration
| From | Input | To |
|------|-------|-----|
| quality-reviewer | Approved content IDs | markdown-exporter |
| markdown-exporter | Structured files | Project knowledge / Fine-tuning |