菜单
Orchestrate the full edge research pipeline from candidate detection through strategy design, review, revision, and export. Use when coordinating multi-stage edge research workflows end-to-end.
Convert Kanchi-style dividend investing into a repeatable US-stock operating procedure. Use when users ask for かんち式配当投資, dividend screening, dividend growth quality checks, PERxPBR adaptation for US sectors, pullback limit-order planning, or one-page stock memo creation. Covers screening, deep dive, entry planning, and post-purchase monitoring cadence.
Validate multi-skill workflows defined in CLAUDE.md by checking skill existence, inter-skill data contracts (JSON schema compatibility), file naming conventions, and handoff integrity. Use when adding new workflows, modifying skill outputs, or verifying pipeline health before release.
This skill should be used when analyzing sector rotation patterns and market cycle positioning. It fetches sector uptrend data from CSV (no API key required) and optionally accepts chart images for supplementary analysis. Use this skill when the user requests sector rotation analysis, cyclical vs defensive assessment, overbought/oversold identification, or market cycle phase estimation. All analysis and output are conducted in English.
Mine Claude Code session logs for skill idea candidates. Use when running the weekly skill generation pipeline to extract, score, and backlog new skill ideas from recent coding sessions.
Screen US stocks using William O'Neil's CANSLIM growth stock methodology. Use when user requests CANSLIM stock screening, growth stock analysis, momentum stock identification, or wants to find stocks with strong earnings and price momentum following O'Neil's investment system.
Fetch upcoming economic events and data releases using FMP API. Retrieve scheduled central bank decisions, employment reports, inflation data, GDP releases, and other market-moving economic indicators for specified date ranges (default: next 7 days). Output chronological markdown reports with impact assessment.
| name | edge-pipeline-orchestrator |
| description | Orchestrate the full edge research pipeline from candidate detection through strategy design, review, revision, and export. Use when coordinating multi-stage edge research workflows end-to-end. |
Coordinate all edge research stages into a single automated pipeline run.
# Full pipeline from tickets
python3 scripts/orchestrate_edge_pipeline.py \
--tickets-dir path/to/tickets/ \
--output-dir reports/edge_pipeline/
# Full pipeline from OHLCV
python3 scripts/orchestrate_edge_pipeline.py \
--from-ohlcv path/to/ohlcv.csv \
--output-dir reports/edge_pipeline/
# Resume from drafts stage
python3 scripts/orchestrate_edge_pipeline.py \
--resume-from drafts \
--drafts-dir path/to/drafts/ \
--output-dir reports/edge_pipeline/
# Review-only mode
python3 scripts/orchestrate_edge_pipeline.py \
--review-only \
--drafts-dir path/to/drafts/ \
--output-dir reports/edge_pipeline/
# Dry run (no export)
python3 scripts/orchestrate_edge_pipeline.py \
--tickets-dir path/to/tickets/ \
--output-dir reports/edge_pipeline/ \
--dry-run
All artifacts are written to --output-dir:
output-dir/
├── pipeline_run_manifest.json
├── tickets/ (from auto_detect)
├── hints/hints.yaml (from hints)
├── concepts/edge_concepts.yaml
├── drafts/*.yaml
├── exportable_tickets/*.yaml
├── reviews_iter_0/*.yaml
├── reviews_iter_1/*.yaml (if needed)
└── strategies/<candidate_id>/
├── strategy.yaml
└── metadata.json
Run the LLM-augmented pipeline entirely within Claude Code:
market_summary.json + anomalies.json- title: Sector rotation into industrials
observation: Tech underperforming while industrials show relative strength
symbols: [CAT, DE, GE]
regime_bias: Neutral
mechanism_tag: flow
preferred_entry_family: pivot_breakout
hypothesis_type: sector_x_stock
--llm-ideas-file and --promote-hints:python3 scripts/orchestrate_edge_pipeline.py \
--tickets-dir path/to/tickets/ \
--llm-ideas-file llm_hints.yaml \
--promote-hints \
--as-of 2026-02-28 \
--max-synthetic-ratio 1.5 \
--strict-export \
--output-dir reports/edge_pipeline/
--as-of YYYY-MM-DD — forwarded to hints stage for date filtering--strict-export — export-eligible drafts with any warn finding get REVISE instead of PASS--max-synthetic-ratio N — cap synthetic tickets to N × real ticket count (floor: 3)--overlap-threshold F — condition overlap threshold for concept deduplication (default: 0.75)--no-dedup — disable concept deduplicationNote: --llm-ideas-file and --promote-hints are effective only during full pipeline runs.
--resume-from drafts and --review-only skip hints/concepts stages, so these flags are ignored.
references/pipeline_flow.md — Pipeline stages, data contracts, and architecturereferences/revision_loop_rules.md — Review-revision feedback loop rules and heuristics