edge-candidate-agent

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Edge Candidate Agent

Overview

概述

Convert daily market observations into reproducible research tickets and Phase I-compatible candidate specs. Prioritize signal quality and interface compatibility over aggressive strategy proliferation. This skill can run end-to-end standalone, but in the split workflow it primarily serves the final export/validation stage.

将每日市场观测结果转化为可复现的研究工单和兼容第一阶段的候选规格文件。优先考虑信号质量和接口兼容性，而非盲目扩张策略数量。该技能可独立端到端运行，但在拆分工作流中主要负责最终的导出/验证阶段。

When to Use

适用场景

Convert market observations, anomalies, or hypotheses into structured research tickets.
Run daily auto-detection to discover new edge candidates from EOD OHLCV and optional hints.

Export validated tickets as

strategy.yaml

metadata.json

for

trade-strategy-pipeline

Phase I.

Run preflight compatibility checks for
```
edge-finder-candidate/v1
```
before pipeline execution.

将市场观测结果、异常现象或假设转化为结构化研究工单。
运行每日自动检测，从收盘OHLCV数据和可选提示中发现新的超额收益候选策略。
将验证通过的工单导出为
```
strategy.yaml
```
+
```
metadata.json
```
，用于
```
trade-strategy-pipeline
```
第一阶段。
在流水线执行前对
```
edge-finder-candidate/v1
```
进行接口兼容性预检。

Prerequisites

前置条件

Python 3.9+ with
```
PyYAML
```
installed.
Access to the target
```
trade-strategy-pipeline
```
repository for schema/stage validation.
```
uv
```
available when running pipeline-managed validation via
```
--pipeline-root
```
.

安装Python 3.9+及
```
PyYAML
```
库。
有权访问目标
```
trade-strategy-pipeline
```
仓库，用于Schema/阶段验证。
当通过
```
--pipeline-root
```
运行流水线管理的验证时，需要
```
uv
```
工具可用。

Output

输出产物

```
strategies/<candidate_id>/strategy.yaml
```
: Phase I-compatible strategy spec.
```
strategies/<candidate_id>/metadata.json
```
: provenance metadata including interface version and ticket context.
Validation status from
```
scripts/validate_candidate.py
```
(pass/fail + reasons).

Daily detection artifacts:

```
daily_report.md
```
```
market_summary.json
```
```
anomalies.json
```
```
watchlist.csv
```
```
tickets/exportable/*.yaml
```
```
tickets/research_only/*.yaml
```

```
strategies/<candidate_id>/strategy.yaml
```
：兼容第一阶段的策略规格文件。
```
strategies/<candidate_id>/metadata.json
```
：来源元数据，包含接口版本和工单上下文。
```
scripts/validate_candidate.py
```
输出的验证状态（通过/失败+原因）。

每日检测产物：

```
daily_report.md
```
```
market_summary.json
```
```
anomalies.json
```
```
watchlist.csv
```
```
tickets/exportable/*.yaml
```
```
tickets/research_only/*.yaml
```

Position in Split Workflow

在拆分工作流中的定位

Recommended split workflow:

```
skills/edge-hint-extractor
```
: observations/news ->
```
hints.yaml
```

skills/edge-concept-synthesizer

: tickets/hints ->

edge_concepts.yaml

skills/edge-strategy-designer

: concepts ->

strategy_drafts

+ exportable ticket YAML

```
skills/edge-candidate-agent
```
(this skill): export + validate for pipeline handoff

推荐拆分工作流：

```
skills/edge-hint-extractor
```
：观测结果/新闻 →
```
hints.yaml
```

skills/edge-concept-synthesizer

：工单/提示 →

edge_concepts.yaml

skills/edge-strategy-designer

：概念 →

strategy_drafts

+ 可导出的工单YAML

```
skills/edge-candidate-agent
```
（本技能）：导出+验证，移交至流水线

Workflow

工作流步骤

Run auto-detection from EOD OHLCV:
- ```
skills/edge-candidate-agent/scripts/auto_detect_candidates.py
```
- Optional:
```
--hints
```
  for human ideation input
- Optional:
```
--llm-ideas-cmd
```
  for external LLM ideation loop

Load the contract and mapping references:

skills/edge-candidate-agent/references/pipeline_if_v1.md

skills/edge-candidate-agent/references/signal_mapping.md

skills/edge-candidate-agent/references/research_ticket_schema.md

skills/edge-candidate-agent/references/ideation_loop.md

Build or update a research ticket using

skills/edge-candidate-agent/references/research_ticket_schema.md

Export candidate artifacts with

skills/edge-candidate-agent/scripts/export_candidate.py

Validate interface and Phase I constraints with

skills/edge-candidate-agent/scripts/validate_candidate.py

Hand off candidate directory to
```
trade-strategy-pipeline
```
and run dry-run first.

基于收盘OHLCV数据运行自动检测：
- 执行
```
skills/edge-candidate-agent/scripts/auto_detect_candidates.py
```
- 可选：通过
```
--hints
```
  传入人工构思的提示
- 可选：通过
```
--llm-ideas-cmd
```
  接入外部LLM构思循环

加载合约和映射参考文件：

skills/edge-candidate-agent/references/pipeline_if_v1.md

skills/edge-candidate-agent/references/signal_mapping.md

skills/edge-candidate-agent/references/research_ticket_schema.md

skills/edge-candidate-agent/references/ideation_loop.md

使用

skills/edge-candidate-agent/references/research_ticket_schema.md

创建或更新研究工单。

执行

skills/edge-candidate-agent/scripts/export_candidate.py

导出候选产物。

执行

skills/edge-candidate-agent/scripts/validate_candidate.py

验证接口和第一阶段约束。

将候选目录移交至
```
trade-strategy-pipeline
```
，并先运行试运行。

Quick Commands

快速命令

Daily auto-detection (with optional export/validation):

bash

python3 skills/edge-candidate-agent/scripts/auto_detect_candidates.py \
  --ohlcv /path/to/ohlcv.parquet \
  --output-dir reports/edge_candidate_auto \
  --top-n 10 \
  --hints path/to/hints.yaml \
  --export-strategies-dir /path/to/trade-strategy-pipeline/strategies \
  --pipeline-root /path/to/trade-strategy-pipeline

Create a candidate directory from a ticket:

bash

python3 skills/edge-candidate-agent/scripts/export_candidate.py \
  --ticket path/to/ticket.yaml \
  --strategies-dir /path/to/trade-strategy-pipeline/strategies

Validate interface contract only:

bash

python3 skills/edge-candidate-agent/scripts/validate_candidate.py \
  --strategy /path/to/trade-strategy-pipeline/strategies/my_candidate_v1/strategy.yaml

Validate both interface contract and pipeline schema/stage rules:

bash

python3 skills/edge-candidate-agent/scripts/validate_candidate.py \
  --strategy /path/to/trade-strategy-pipeline/strategies/my_candidate_v1/strategy.yaml \
  --pipeline-root /path/to/trade-strategy-pipeline \
  --stage phase1

每日自动检测（可选导出/验证）：

bash

python3 skills/edge-candidate-agent/scripts/auto_detect_candidates.py \
  --ohlcv /path/to/ohlcv.parquet \
  --output-dir reports/edge_candidate_auto \
  --top-n 10 \
  --hints path/to/hints.yaml \
  --export-strategies-dir /path/to/trade-strategy-pipeline/strategies \
  --pipeline-root /path/to/trade-strategy-pipeline

从工单创建候选目录：

bash

python3 skills/edge-candidate-agent/scripts/export_candidate.py \
  --ticket path/to/ticket.yaml \
  --strategies-dir /path/to/trade-strategy-pipeline/strategies

仅验证接口合约：

bash

python3 skills/edge-candidate-agent/scripts/validate_candidate.py \
  --strategy /path/to/trade-strategy-pipeline/strategies/my_candidate_v1/strategy.yaml

同时验证接口合约和流水线Schema/阶段规则：

bash

python3 skills/edge-candidate-agent/scripts/validate_candidate.py \
  --strategy /path/to/trade-strategy-pipeline/strategies/my_candidate_v1/strategy.yaml \
  --pipeline-root /path/to/trade-strategy-pipeline \
  --stage phase1

Export Rules

导出规则

Keep
```
validation.method: full_sample
```
.
Keep
```
validation.oos_ratio
```
omitted or
```
null
```
.

Export only supported entry families for v1:

```
pivot_breakout
```
with
```
vcp_detection
```
```
gap_up_continuation
```
with
```
gap_up_detection
```

Mark unsupported hypothesis families as research-only in ticket notes, not as export candidates.

保留
```
validation.method: full_sample
```
。
保留
```
validation.oos_ratio
```
为省略或
```
null
```
。

仅导出v1支持的入场策略类型：

带有
```
vcp_detection
```
的
```
pivot_breakout
```
带有
```
gap_up_detection
```
的
```
gap_up_continuation
```

将不支持的假设类型标记为仅研究工单，不作为导出候选。

Guardrails

防护规则

Reject candidates that violate schema bounds (risk, exits, empty conditions).
Reject candidate when folder name and
```
id
```
mismatch.

Require deterministic metadata with

interface_version: edge-finder-candidate/v1

Use
```
--dry-run
```
in pipeline before full execution.

拒绝违反Schema限制的候选策略（风险、出场条件、空条件等）。
当文件夹名称与
```
id
```
不匹配时，拒绝该候选策略。

要求元数据具有确定性，且

interface_version: edge-finder-candidate/v1

。

在流水线中使用
```
--dry-run
```
进行完整执行前的试运行。

Resources

资源说明

skills/edge-candidate-agent/scripts/export_candidate.py

skills/edge-candidate-agent/scripts/export_candidate.py

Generate

strategies/<candidate_id>/strategy.yaml

and

metadata.json

from a research ticket YAML.

从研究工单YAML文件生成

strategies/<candidate_id>/strategy.yaml

和

metadata.json

。

skills/edge-candidate-agent/scripts/validate_candidate.py

skills/edge-candidate-agent/scripts/validate_candidate.py

Run interface checks and optional

StrategySpec

validate_spec

checks against

trade-strategy-pipeline

对

trade-strategy-pipeline

执行接口检查和可选的

StrategySpec

validate_spec

检查。

skills/edge-candidate-agent/scripts/auto_detect_candidates.py

skills/edge-candidate-agent/scripts/auto_detect_candidates.py

Auto-detect edge ideas from EOD OHLCV, generate exportable/research tickets, and optionally export/validate automatically.

从收盘OHLCV数据中自动检测超额收益策略想法，生成可导出/仅研究的工单，并可选择自动导出/验证。

skills/edge-candidate-agent/references/pipeline_if_v1.md

skills/edge-candidate-agent/references/pipeline_if_v1.md

Condensed integration contract for

edge-finder-candidate/v1

edge-finder-candidate/v1

的精简集成合约。

skills/edge-candidate-agent/references/signal_mapping.md

skills/edge-candidate-agent/references/signal_mapping.md

Map hypothesis families to currently exportable signal families.

将假设类型映射至当前可导出的信号类型。

skills/edge-candidate-agent/references/research_ticket_schema.md

skills/edge-candidate-agent/references/research_ticket_schema.md

Ticket schema used by

export_candidate.py

export_candidate.py

使用的工单Schema。

skills/edge-candidate-agent/references/ideation_loop.md

skills/edge-candidate-agent/references/ideation_loop.md

Hint schema and external LLM ideation command contract.

提示Schema和外部LLM构思命令合约。

edge-candidate-agent

Original

Translation

Edge Candidate Agent

Edge Candidate Agent

Overview

概述

When to Use

适用场景

Prerequisites

前置条件

Output

输出产物

Position in Split Workflow

在拆分工作流中的定位

Workflow

工作流步骤

Quick Commands

快速命令

Export Rules

导出规则

Guardrails

防护规则

Resources

资源说明

`skills/edge-candidate-agent/scripts/export_candidate.py`

`skills/edge-candidate-agent/scripts/export_candidate.py`

`skills/edge-candidate-agent/scripts/validate_candidate.py`

`skills/edge-candidate-agent/scripts/validate_candidate.py`

`skills/edge-candidate-agent/scripts/auto_detect_candidates.py`

`skills/edge-candidate-agent/scripts/auto_detect_candidates.py`

`skills/edge-candidate-agent/references/pipeline_if_v1.md`

`skills/edge-candidate-agent/references/pipeline_if_v1.md`

`skills/edge-candidate-agent/references/signal_mapping.md`

`skills/edge-candidate-agent/references/signal_mapping.md`

`skills/edge-candidate-agent/references/research_ticket_schema.md`

`skills/edge-candidate-agent/references/research_ticket_schema.md`

`skills/edge-candidate-agent/references/ideation_loop.md`

`skills/edge-candidate-agent/references/ideation_loop.md`