model-capability-advisor
Model Capability Advisor
Recommend model capability choices for: $ARGUMENTS
Overview
- Implementation status: code-backed
- Local entry script:
<bundle-root>/model-capability-advisor/run.py - Primary purpose: score provided model names against workflow needs and return quick/deep recommendation pairs
- Research layer: meta-workflow optimization (Cross-cutting concern for agent execution design)
- Workflow role: meta-planning support for agent execution design, not a market-analysis surface
- Local executor guarantee: produce heuristic workflow-fit advice from the local capability profiles it knows about
Use When
More from natsufox/a-stockit
reports
Inspect and export generated analysis artifacts. Use when user wants exact stored markdown, JSON state, or run metadata instead of rerunning analysis.
1paper-trading
Run a paper-trading workflow over analyzed symbols. Use when user wants the live-verification stage in simulated form: trade rehearsal, ledger updates, A-share settlement rules, and explicit monitoring of what the local paper book does and does not model.
1watchlist
Manage watchlist workflows after import. Use when user wants the stage-1 universe-management workflow: grouping, coverage intent, review cadence, artifact reuse, and repeated tracking after ingestion.
1market-recap
Render region-aware market recap blueprints. Use when user wants the stage-7 review and communication frame for CN or US markets: recap structure, next-session posture template, and checklist-driven market review rather than live data retrieval.
1market-analyze
Assess trend, regime, and risk state for one A-share symbol. Use when user wants current market interpretation from the normalized snapshot without action sizing, execution planning, or thesis narration.
1stock-data
Assemble a reusable one-symbol research snapshot across quote, levels, indicators, and fail-open fundamentals. Use when user wants a structured stage-2 to stage-4 research packet without a final thesis memo or action recommendation.
1