Loading...
Loading...
A-share Market Daily Review System. Actively invoked when users mention needs such as market review, market analysis, or tomorrow's market prediction. Covers: Market Environment, Sentiment Cycle, Main Line Identification, Capital Monitoring, Post-Market Variables, Tomorrow's Combat Map. For research reference only, does not constitute securities investment consulting business or investment advice.
npx skill4agent add aurix-labs/thesis-builder market-review/market-review [--force] [--module <module-name>]--module--force| Module | Main Name | TTL |
|---|---|---|
| Market Environment Diagnosis | | 1 day |
| Sentiment Cycle Positioning | | 1 day |
| Main and Branch Line Identification | | 1 day |
| Capital Behavior Monitoring | | 1 day |
| Post-Market Variables Summary | | 1 day |
| Tomorrow's Combat Map | | 1 day |
| User Says | Translation |
|---|---|
| Start today's review | |
| How's the market today | |
| Review today's market | |
| Can we trade tomorrow | |
| What stage is today's sentiment cycle in | |
| Re-run today's review | |
| ID | Constraint | Why |
|---|---|---|
| R1 | Same-day data is valid on the day, | Post-market data for the same trading day won't change; repeated pulling wastes API quotas |
| R2 | | Prevent the Agent from arbitrarily re-running all modules just to "do a complete job" |
| R3 | report.md files between modules do not reference each other (do not write "see conclusion in Module 1"), only reference raw data in data.json | Core guarantee for module decoupling |
| R4 | When synthesizing review.md, each module independently applies R1/R2 | Module 6 is rewritten every time (depends on the latest output of the first five modules) |
| R5 | A single module never outputs "Tomorrow's Combat Map" or position suggestions; position suggestions are only produced by Module 6 | Positioning requires comprehensive information from all modules |
| R6 | Each module's report.md must start with the | Verify module integrity and date alignment during synthesis |
| R7 | Market review never mentions individual stocks | Core boundary rule |
| R8 | Python scripts only handle fetching and verification, do not generate report.md | Agent is the sole producer of report.md |
| R9 | verify_facts checks data.json ↔ report.md for a single module; verify_consistency only runs after synthesis | Cross-module consistency is only meaningful after merging |
/market-review1. Run python scripts/run_review.py --date <today> [--force]
2. Parse stdout output (JSONL):
- status=reuse → Directly read <module>/<ymd>/report.md for the user
- status=data_ready → Read data.json + references/modules/<m>.md
Write <module>/<today>/report.md
Run python scripts/verify_facts.py --module <m> --ymd <today>
3. Loop step 2 for each module where needs_report_md=true
4. Agent reads 6 report.md files and synthesizes output/<today>/review.md
5. Run python scripts/verify_consistency.py --ymd <today>
6. Run python scripts/record_eval.py --ymd <today>
7. Feed the content of review.md back to the user/market-review --module sentiment1. Run python scripts/run_review.py --date <today> --module sentiment [--force]
2. Parse stdout:
- status=reuse → Directly read report.md
- status=data_ready → Agent writes report.md → verify_facts
3. Feed the content of report.md back to the useroutput/
└── <YYYY-MM-DD>/
├── index/{data.json, report.md}
├── sentiment/{data.json, report.md}
├── mainline/{data.json, report.md}
├── capital/{data.json, report.md}
├── variables/{data.json, report.md}
├── combatmap/{data.json, market_data.json, report.md}
├── review.md
└── eval.json| When to Read | File |
|---|---|
| When writing a module's report.md | references/modules/<m>.md |
| When writing data.json | references/data-schema.md |
| When modifying configurations | config.yaml |