重要前提
安装AI Skills的关键前提是:必须科学上网,且开启TUN模式,这一点至关重要,直接决定安装能否顺利完成,在此郑重提醒三遍:科学上网,科学上网,科学上网。查看完整安装教程 →
edge-pipeline-orchestrator by tradermonty/claude-trading-skills
npx skills add https://github.com/tradermonty/claude-trading-skills --skill edge-pipeline-orchestrator将所有边缘研究阶段协调到一个自动化的流水线运行中。
--from-ohlcv,则运行 auto_detect 阶段(从原始 OHLCV 数据生成工单)# 从工单开始的完整流水线
python3 scripts/orchestrate_edge_pipeline.py \
--tickets-dir path/to/tickets/ \
--output-dir reports/edge_pipeline/
# 从 OHLCV 开始的完整流水线
python3 scripts/orchestrate_edge_pipeline.py \
--from-ohlcv path/to/ohlcv.csv \
--output-dir reports/edge_pipeline/
# 从草稿阶段恢复
python3 scripts/orchestrate_edge_pipeline.py \
--resume-from drafts \
--drafts-dir path/to/drafts/ \
--output-dir reports/edge_pipeline/
# 仅审查模式
python3 scripts/orchestrate_edge_pipeline.py \
--review-only \
--drafts-dir path/to/drafts/ \
--output-dir reports/edge_pipeline/
# 试运行(不导出)
python3 scripts/orchestrate_edge_pipeline.py \
--tickets-dir path/to/tickets/ \
--output-dir reports/edge_pipeline/ \
--dry-run
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
所有产物都写入到 --output-dir:
output-dir/
├── pipeline_run_manifest.json
├── tickets/ (来自 auto_detect)
├── hints/hints.yaml (来自 hints)
├── concepts/edge_concepts.yaml
├── drafts/*.yaml
├── exportable_tickets/*.yaml
├── reviews_iter_0/*.yaml
├── reviews_iter_1/*.yaml (如果需要)
└── strategies/<candidate_id>/
├── strategy.yaml
└── metadata.json
完全在 Claude Code 中运行 LLM 增强的流水线:
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
4. 使用 --llm-ideas-file 和 --promote-hints 运行编排器:
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 — 转发给 hints 阶段用于日期过滤--strict-export — 任何带有警告发现的符合导出条件的草稿将获得 REVISE 而不是 PASS--max-synthetic-ratio N — 将合成工单数量限制为真实工单数量的 N 倍(下限:3)--overlap-threshold F — 概念去重的条件重叠阈值(默认值:0.75)--no-dedup — 禁用概念去重注意:--llm-ideas-file 和 --promote-hints 仅在完整流水线运行时有效。--resume-from drafts 和 --review-only 会跳过 hints/concepts 阶段,因此这些标志会被忽略。
references/pipeline_flow.md — 流水线阶段、数据契约和架构references/revision_loop_rules.md — 审查-修订反馈循环规则和启发式方法每周安装量
62
代码仓库
GitHub 星标数
412
首次出现
2026年3月1日
安全审计
安装于
cursor60
gemini-cli59
github-copilot59
amp59
cline59
codex59
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
4. Run orchestrator with --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 heuristicsWeekly Installs
62
Repository
GitHub Stars
412
First Seen
Mar 1, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
cursor60
gemini-cli59
github-copilot59
amp59
cline59
codex59
通过 LiteLLM 代理让 Claude Code 对接 GitHub Copilot 运行 | 高级变通方案指南
48,700 周安装