edge-pipeline-orchestrator

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.

Best for Multi-stage edge research a…Works with GitHubLow risk

#orchestration #pipeline #edge-research #automation #workflow

⌘source

author: @tradermonty
repo: tradermonty/claude-trading-skills
language: Python

✦overview.md

Key Features

·Orchestrates full edge research pipeline from detection to export
·Supports resuming from partially completed stages
·Includes review and revision feedback loop for drafts
·Exports eligible strategy drafts with execution trace

Use Cases

→Running complete edge research workflows from raw data to final strategies
→Resuming interrupted pipeline executions from the drafts stage
→Reviewing and iteratively revising existing strategy drafts

Best for

✓Multi-stage edge research automation
✓Teams managing end-to-edge research workflows

Not ideal for

!Single-stage tasks
!Non-research pipeline orchestration

skills/edge-pipeline-orchestrator/SKILL.md

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.

Edge Pipeline Orchestrator

Coordinate all edge research stages into a single automated pipeline run.

When to Use

Run the full edge pipeline from tickets (or OHLCV) to exported strategies
Resume a partially completed pipeline from the drafts stage
Review and revise existing strategy drafts with feedback loop
Dry-run the pipeline to preview results without exporting

Workflow

Load pipeline configuration from CLI arguments
Run auto_detect stage if --from-ohlcv is provided (generates tickets from raw OHLCV data)
Run hints stage to extract edge hints from market summary and anomalies
Run concepts stage to synthesize abstract edge concepts from tickets and hints
Run drafts stage to design strategy drafts from concepts
Run review-revision feedback loop:
- Review all drafts (max 2 iterations)
- PASS verdicts accumulated; REJECT verdicts accumulated
- REVISE verdicts trigger apply_revisions and re-review
- Remaining REVISE after max iterations downgraded to research_probe
Export eligible drafts (PASS + export_ready_v1 + exportable entry_family)
Write pipeline_run_manifest.json with full execution trace

CLI Usage

...

$install

1-click copy

npx skills add tradermonty/claude-trading-skills --skill edge-pipeline-orchestrator

Safety assessment

★

Clarity score

How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.

1/ 5

poor

The SKILL.md content is hard to understand and quite ambiguous.

◎

Actionability score

How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.

1/ 5

not actionable

The SKILL.md is hard to act on; an agent would not know what to do.

~community cookbook

April 21, 2026

◧ Compare

edge-pipeline-orchestrator

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.

Best for Multi-stage edge research a…Works with GitHubLow risk

Edge Pipeline Orchestrator

Coordinate all edge research stages into a single automated pipeline run.

When to Use

Run the full edge pipeline from tickets (or OHLCV) to exported strategies

Resume a partially completed pipeline from the drafts stage

Review and revise existing strategy drafts with feedback loop

Dry-run the pipeline to preview results without exporting

Workflow

Load pipeline configuration from CLI arguments

Run auto_detect stage if --from-ohlcv is provided (generates tickets from raw OHLCV data)

Run hints stage to extract edge hints from market summary and anomalies

Run concepts stage to synthesize abstract edge concepts from tickets and hints

Run drafts stage to design strategy drafts from concepts

Run review-revision feedback loop:

Review all drafts (max 2 iterations)
PASS verdicts accumulated; REJECT verdicts accumulated
REVISE verdicts trigger apply_revisions and re-review
Remaining REVISE after max iterations downgraded to research_probe

Export eligible drafts (PASS + export_ready_v1 + exportable entry_family)

Write pipeline_run_manifest.json with full execution trace

CLI Usage

edge-pipeline-orchestrator

Key Features

Use Cases

Best for

Not ideal for

Edge Pipeline Orchestrator

When to Use

Workflow

CLI Usage

Safety assessment

Clarity score

Actionability score

~community cookbook

~you might also like

browserwing

lfg

ce-work-beta

ccw

ce-update

bmad-customize

AI Skill Finder

edge-pipeline-orchestrator

Key Features

Use Cases

Best for

Not ideal for

Edge Pipeline Orchestrator

When to Use

Workflow

CLI Usage

Safety assessment

Clarity score

Actionability score

~community cookbook

~you might also like

browserwing

lfg

ce-work-beta

ccw

ce-update

bmad-customize