Integrated multi-source support from development branch into feature branch's C3.x auto-cloning and cache system. This merge combines TWO major features: FEATURE BRANCH (C3.x + Cache): - Automatic GitHub repository cloning for C3.x analysis - Hidden .skillseeker-cache/ directory for intermediate files - Cache reuse for faster rebuilds - Enhanced AI skill quality improvements DEVELOPMENT BRANCH (Multi-Source): - Support multiple sources of same type (multiple GitHub repos, PDFs) - List-based data storage with source indexing - New configs: claude-code.json, medusa-mercurjs.json - llms.txt downloader/parser enhancements - New tests: test_markdown_parsing.py, test_multi_source.py CONFLICT RESOLUTIONS: 1. configs/claude-code.json (COMPROMISE): - Kept file with _migration_note (preserves PR #244 work) - Feature branch had deleted it (config migration) - Development branch enhanced it (47 Claude Code doc URLs) 2. src/skill_seekers/cli/unified_scraper.py (INTEGRATED): Applied 8 changes for multi-source support: - List-based storage: {'github': [], 'documentation': [], 'pdf': []} - Source indexing with _source_counters - Unique naming: {name}_github_{idx}_{repo_id} - Unique data files: github_data_{idx}_{repo_id}.json - List append instead of dict assignment - Updated _clone_github_repo(repo_name, idx=0) signature - Applied same logic to _scrape_pdf() 3. src/skill_seekers/cli/unified_skill_builder.py (INTEGRATED): Applied 3 changes for multi-source synthesis: - _load_source_skill_mds(): Glob pattern for multiple sources - _generate_references(): Iterate through github_list - _generate_c3_analysis_references(repo_id): Per-repo C3.x references TESTING STRATEGY: Backward Compatibility: - Single source configs work exactly as before (idx=0) New Capabilities: - Multiple GitHub repos: encode/httpx + facebook/react - Multiple PDFs with unique indexing - Mixed sources: docs + multiple GitHub repos Pipeline Integrity: - Scraper: Multi-source data collection with indexing - Builder: Loads all source SKILL.md files - Synthesis: Merges multiple sources with separators - C3.x: Independent analysis per repo in unique subdirectories Result: Support MULTIPLE sources per type + C3.x analysis + cache system 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
85 lines
4.3 KiB
JSON
85 lines
4.3 KiB
JSON
{
|
|
"_migration_note": "TODO: Migrate to external skill-seekers-configs repo. Kept temporarily to preserve PR #244 work.",
|
|
"name": "claude-code",
|
|
"description": "Claude Code CLI and development environment. Use for Claude Code features, tools, workflows, MCP integration, plugins, hooks, configuration, deployment, and AI-assisted development.",
|
|
"base_url": "https://code.claude.com/docs/en/",
|
|
"start_urls": [
|
|
"https://code.claude.com/docs/en/overview",
|
|
"https://code.claude.com/docs/en/quickstart",
|
|
"https://code.claude.com/docs/en/common-workflows",
|
|
"https://code.claude.com/docs/en/claude-code-on-the-web",
|
|
"https://code.claude.com/docs/en/desktop",
|
|
"https://code.claude.com/docs/en/chrome",
|
|
"https://code.claude.com/docs/en/vs-code",
|
|
"https://code.claude.com/docs/en/jetbrains",
|
|
"https://code.claude.com/docs/en/github-actions",
|
|
"https://code.claude.com/docs/en/gitlab-ci-cd",
|
|
"https://code.claude.com/docs/en/slack",
|
|
"https://code.claude.com/docs/en/sub-agents",
|
|
"https://code.claude.com/docs/en/plugins",
|
|
"https://code.claude.com/docs/en/discover-plugins",
|
|
"https://code.claude.com/docs/en/skills",
|
|
"https://code.claude.com/docs/en/output-styles",
|
|
"https://code.claude.com/docs/en/hooks-guide",
|
|
"https://code.claude.com/docs/en/headless",
|
|
"https://code.claude.com/docs/en/mcp",
|
|
"https://code.claude.com/docs/en/third-party-integrations",
|
|
"https://code.claude.com/docs/en/amazon-bedrock",
|
|
"https://code.claude.com/docs/en/google-vertex-ai",
|
|
"https://code.claude.com/docs/en/microsoft-foundry",
|
|
"https://code.claude.com/docs/en/network-config",
|
|
"https://code.claude.com/docs/en/llm-gateway",
|
|
"https://code.claude.com/docs/en/devcontainer",
|
|
"https://code.claude.com/docs/en/sandboxing",
|
|
"https://code.claude.com/docs/en/setup",
|
|
"https://code.claude.com/docs/en/iam",
|
|
"https://code.claude.com/docs/en/security",
|
|
"https://code.claude.com/docs/en/data-usage",
|
|
"https://code.claude.com/docs/en/monitoring-usage",
|
|
"https://code.claude.com/docs/en/costs",
|
|
"https://code.claude.com/docs/en/analytics",
|
|
"https://code.claude.com/docs/en/plugin-marketplaces",
|
|
"https://code.claude.com/docs/en/settings",
|
|
"https://code.claude.com/docs/en/terminal-config",
|
|
"https://code.claude.com/docs/en/model-config",
|
|
"https://code.claude.com/docs/en/memory",
|
|
"https://code.claude.com/docs/en/statusline",
|
|
"https://code.claude.com/docs/en/cli-reference",
|
|
"https://code.claude.com/docs/en/interactive-mode",
|
|
"https://code.claude.com/docs/en/slash-commands",
|
|
"https://code.claude.com/docs/en/checkpointing",
|
|
"https://code.claude.com/docs/en/hooks",
|
|
"https://code.claude.com/docs/en/plugins-reference",
|
|
"https://code.claude.com/docs/en/troubleshooting",
|
|
"https://code.claude.com/docs/en/legal-and-compliance"
|
|
],
|
|
"selectors": {
|
|
"main_content": "#content-area, #content-container, article, main",
|
|
"title": "h1",
|
|
"code_blocks": "pre code"
|
|
},
|
|
"url_patterns": {
|
|
"include": ["/docs/en/"],
|
|
"exclude": [
|
|
"/docs/fr/", "/docs/de/", "/docs/it/", "/docs/ja/", "/docs/es/",
|
|
"/docs/ko/", "/docs/zh-CN/", "/docs/zh-TW/", "/docs/ru/",
|
|
"/docs/id/", "/docs/pt/", "/changelog", "github.com"
|
|
]
|
|
},
|
|
"categories": {
|
|
"getting_started": ["overview", "quickstart", "common-workflows"],
|
|
"ide_integrations": ["vs-code", "jetbrains", "desktop", "chrome", "claude-code-on-the-web", "slack"],
|
|
"ci_cd": ["github-actions", "gitlab-ci-cd"],
|
|
"building": ["sub-agents", "subagent", "plugins", "discover-plugins", "skills", "output-styles", "hooks-guide", "headless", "programmatic"],
|
|
"mcp": ["mcp", "model-context-protocol"],
|
|
"deployment": ["third-party-integrations", "amazon-bedrock", "google-vertex-ai", "microsoft-foundry", "network-config", "llm-gateway", "devcontainer", "sandboxing"],
|
|
"administration": ["setup", "iam", "security", "data-usage", "monitoring-usage", "costs", "analytics", "plugin-marketplaces"],
|
|
"configuration": ["settings", "terminal-config", "model-config", "memory", "statusline"],
|
|
"reference": ["cli-reference", "interactive-mode", "slash-commands", "checkpointing", "hooks", "plugins-reference"],
|
|
"troubleshooting": ["troubleshooting"],
|
|
"legal": ["legal-and-compliance"]
|
|
},
|
|
"rate_limit": 0.5,
|
|
"max_pages": 250
|
|
}
|