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
Chalk Labs
Need help deploying promotion-gate?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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.
About
Use cases: productivity
Reviews
Write a reviewNo 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.
More from Open-Quant/openquant
- 0.506score
flywheel-runner
Open-Quant
Run OpenQuant notebook-to-experiment flywheel iterations (single run and grid run), capture artifacts, and summarize ranked outcomes for promotion decisions.
SkillDFreshness: D★ 52Claude Code +9 - 0.506score
notebook-executor
Open-Quant
Execute OpenQuant notebook code cells non-interactively, persist outputs to artifact paths, and fail fast on runtime errors.
SkillDFreshness: D★ 52Claude Code +9 - 0.506score
parity-check
Open-Quant
Verify parity between notebook-like pipeline execution and scripted experiment workflows so research findings are reproducible.
SkillDFreshness: D★ 52Claude Code +9 - 0.506score
feature-discovery
Open-Quant
Build candidate features, run feature screening and diagnostics, and prepare accepted feature sets for downstream flywheel experiments.
SkillDFreshness: D★ 52Claude Code +9 - 0.506score
artifact-auditor
Open-Quant
Audit experiment artifact folders for completeness, schema consistency, and promotion traceability across single and grid runs.
SkillDFreshness: D★ 52Claude Code +9
Signals
- Stars
- 52
- Forks
- 6
- Open issues
- 3
- Last commit (this folder)
- Mar 4, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Open-Quant/openquant
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Open-Quant
- 0.506score
flywheel-runner
Open-Quant
Run OpenQuant notebook-to-experiment flywheel iterations (single run and grid run), capture artifacts, and summarize ranked outcomes for promotion decisions.
SkillDFreshness: D★ 52Claude Code +9 - 0.506score
notebook-executor
Open-Quant
Execute OpenQuant notebook code cells non-interactively, persist outputs to artifact paths, and fail fast on runtime errors.
SkillDFreshness: D★ 52Claude Code +9 - 0.506score
parity-check
Open-Quant
Verify parity between notebook-like pipeline execution and scripted experiment workflows so research findings are reproducible.
SkillDFreshness: D★ 52Claude Code +9 - 0.506score
feature-discovery
Open-Quant
Build candidate features, run feature screening and diagnostics, and prepare accepted feature sets for downstream flywheel experiments.
SkillDFreshness: D★ 52Claude Code +9 - 0.506score
artifact-auditor
Open-Quant
Audit experiment artifact folders for completeness, schema consistency, and promotion traceability across single and grid runs.
SkillDFreshness: D★ 52Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get promotion-gate running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
promotion-gate skill. Agent Mart. https://agentmart.dev/skills/open-quant-promotion-gate (last updated 2026-10-24)