Skip to content
Agentmart
Submit a tool

promotion-gate

Evaluate promotion readiness from flywheel outputs using statistical and economic gates, then produce a concise go/no-go decision note.

Skill by Open-Quant

IndexedMIT★ 52
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/open-quant-promotion-gate

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Evaluate promotion readiness from flywheel outputs using statistical and economic gates, then produce a concise go/no-go decision note.

Use cases: productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/promotion-gate

What's inside

Skill name
promotion-gate
Description
Evaluate promotion readiness from flywheel outputs using statistical and economic gates, then produce a concise go/no-go decision note.
License
MIT
Instructions
38 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Promotion Gate

Use this skill when deciding whether a strategy candidate moves from research iteration to deeper validation.

## What this skill does

1. Reads flywheel output (`summary`, `promotion`, `costs`).
2. Verifies required gates:
   - realized Sharpe
   - net Sharpe
   - alignment guard
   - event ordering guard
3. Produces a decision summary with blocking reasons.

## Core APIs

- `openquant.research.run_flywheel_iteration(...)`
- `openquant.pipeline.summarize_pipeline(...)`

## Decision contract

Required outputs:
- `promote_candidate` (bool)
- failed gate list
- key metrics (`realized_sharpe`, `net_sharpe`, `turnover`, `estimated_cost`)
- short rationale

## Artifact source

- `decision.md` and `metrics.parquet` in each experiment run folder.

## Quality checks

```bash
uv run --python .venv/bin/python pytest python/tests/test_experiment_scaffold.py -q
```

From Open-Quant/openquant, MIT.

Signals

Stars
52
Forks
6
Open issues
3
Last commit (this folder)
Mar 4, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Open-Quant

Cite this page

promotion-gate skill. Agent Mart. https://agentmart.dev/skills/open-quant-promotion-gate (last updated 2026-10-24)