OpenClaw Trading Suite
Use this skill when the user asks for end-to-end trading-agent behavior across analysis, hypothesis creation, risk management, execution, and continuous optimization.
Scope
- Strategy styles: swing-first, with optional intraday and event-driven variants.
- Assets: equities and crypto by default.
- Lifecycle: research -> hypothesis -> validate -> size risk -> execute -> review -> retrain.
- Data retention: all decisions, signals, fills, outcomes, and model versions are logged for later analysis.
Core workflow
- Ingest market, technical, and optional lightweight sentiment/event data.
- Run screeners to generate candidate tickers/coins for strategy hypotheses.
- Build trade hypotheses with explicit entry, exit, invalidation, and confidence.
- Apply strategy-specific risk profile (not global static policy).
- Gate execution based on drawdown, exposure, and confidence thresholds.
- Log every step to persistent storage (research, signals, orders, fills, P&L).
- Run periodic review: win rate, expectancy, drawdown, and regime-fit diagnostics.
- Feed outcomes into optimization/retraining loop with champion-vs-challenger testing.
Strategy catalog
Load references/strategy_profiles.md when a user asks for concrete strategies or wants to include the "4 bots competition" approaches.
Data model and retention
Load references/data_retention_schema.md when implementing storage, analytics, or RL/ML training.
Autonomy modes
Load references/autonomy_modes.md when implementing user-selected autonomy behavior and approvals.
Adapter extension contract
Load references/adapter_plugin_contract.md when adding venues, data feeds, or research tools.
Strategy builder and gates
Load references/strategy_builder_and_gates.md when user/agent-defined thresholds are needed for paper-to-live graduation.
Secrets handling
Load references/secrets_management.md when adding providers, credentials, or runtime configuration.
Orchestration
Load references/system_orchestration.md when wiring agents/tools, heartbeat cadence, and execution triggers.
Execution policy defaults
- Start in paper mode unless user explicitly requests live mode.
- Require per-hypothesis approval for first live deployment of any new strategy.
- Enforce strategy-local risk budgets and portfolio-level circuit breakers.
- Halt strategy if live or paper performance breaches configured drawdown limits.
Reuse notes for this repository
- Existing modules to reuse first:
market-data-aggregator, technical-analysis-engine, risk-position-manager, strategy-optimizer, trade-signal-processor-executor, performance-reporter-learner, profit-forecaster, and temp-rl-proto.
- Treat older module
SKILL.md files as component-level docs; this suite is the orchestrator skill.
- Nightly research entry point:
scripts/nightly_research.py.
1---2name: openclaw-trading-suite3description: Unified OpenClaw skill for autonomous algo and swing trading workflows: hypothesis generation, screening, technical/sentiment analysis, strategy-specific risk controls, execution gating, P&L and win-rate planning, and self-improvement loops backed by persistent trade data for ML/RL retraining.4---56# OpenClaw Trading Suite78Use this skill when the user asks for end-to-end trading-agent behavior across analysis, hypothesis creation, risk management, execution, and continuous optimization.910## Scope1112- Strategy styles: swing-first, with optional intraday and event-driven variants.13- Assets: equities and crypto by default.14- Lifecycle: research -> hypothesis -> validate -> size risk -> execute -> review -> retrain.15- Data retention: all decisions, signals, fills, outcomes, and model versions are logged for later analysis.1617## Core workflow18191. Ingest market, technical, and optional lightweight sentiment/event data.202. Run screeners to generate candidate tickers/coins for strategy hypotheses.213. Build trade hypotheses with explicit entry, exit, invalidation, and confidence.224. Apply strategy-specific risk profile (not global static policy).235. Gate execution based on drawdown, exposure, and confidence thresholds.246. Log every step to persistent storage (research, signals, orders, fills, P&L).257. Run periodic review: win rate, expectancy, drawdown, and regime-fit diagnostics.268. Feed outcomes into optimization/retraining loop with champion-vs-challenger testing.2728## Strategy catalog2930Load [references/strategy_profiles.md](references/strategy_profiles.md) when a user asks for concrete strategies or wants to include the "4 bots competition" approaches.3132## Data model and retention3334Load [references/data_retention_schema.md](references/data_retention_schema.md) when implementing storage, analytics, or RL/ML training.3536## Autonomy modes3738Load [references/autonomy_modes.md](references/autonomy_modes.md) when implementing user-selected autonomy behavior and approvals.3940## Adapter extension contract4142Load [references/adapter_plugin_contract.md](references/adapter_plugin_contract.md) when adding venues, data feeds, or research tools.4344## Strategy builder and gates4546Load [references/strategy_builder_and_gates.md](references/strategy_builder_and_gates.md) when user/agent-defined thresholds are needed for paper-to-live graduation.4748## Secrets handling4950Load [references/secrets_management.md](references/secrets_management.md) when adding providers, credentials, or runtime configuration.5152## Orchestration5354Load [references/system_orchestration.md](references/system_orchestration.md) when wiring agents/tools, heartbeat cadence, and execution triggers.5556## Execution policy defaults5758- Start in paper mode unless user explicitly requests live mode.59- Require per-hypothesis approval for first live deployment of any new strategy.60- Enforce strategy-local risk budgets and portfolio-level circuit breakers.61- Halt strategy if live or paper performance breaches configured drawdown limits.6263## Reuse notes for this repository6465- Existing modules to reuse first: `market-data-aggregator`, `technical-analysis-engine`, `risk-position-manager`, `strategy-optimizer`, `trade-signal-processor-executor`, `performance-reporter-learner`, `profit-forecaster`, and `temp-rl-proto`.66- Treat older module `SKILL.md` files as component-level docs; this suite is the orchestrator skill.67- Nightly research entry point: `scripts/nightly_research.py`.
dvcrn