原始内容
name: extract description: Builds the gauntlet knowledge base from AST extraction and AI enrichment version: 1.9.8 triggers:
- initializing or refreshing codebase knowledge for challenges metadata: {"openclaw": {"homepage": "https://github.com/athola/claude-night-market/tree/master/plugins/gauntlet", "emoji": "\ud83e\udd9e"}} source: claude-night-market source_plugin: gauntlet
Night Market Skill — ported from claude-night-market/gauntlet. For the full experience with agents, hooks, and commands, install the Claude Code plugin.
Extract Codebase Knowledge
Build or rebuild the .gauntlet/knowledge.json knowledge base.
Steps
Identify target directory: use the current working directory or a user-specified path
Run AST extraction: invoke the extractor script
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/extractor.py <target-dir>AI enrichment: for each extracted entry, enhance the
detailfield with natural language explanation of business logic, data flow, architectural role, and rationaleCross-reference: link related entries across modules by matching imports, shared types, and data flow paths
Merge with annotations: preserve existing curated entries in
.gauntlet/annotations/Save: write to
.gauntlet/knowledge.jsonReport: show summary by category, coverage gaps, difficulty distribution
Category Priority
- business_logic (weight 7)
- architecture (weight 6)
- data_flow (weight 5)
- api_contract (weight 4)
- pattern (weight 3)
- dependency (weight 2)
- error_handling (weight 1)