skills

In the author's own words, from each skill's SKILL.md — showing the first 30 of 61 files.

• ml4t-agent-governance

  Security and governance controls for autonomous financial agents. Use when agents can call tools, read untrusted content, or affect research or trading decisions.

  advanced-ai/agent-governance/SKILL.md on GitHub (opens in a new tab)

• ml4t-agent-state-memory

  Durable agent state, memory, and replay for autonomous research workflows. Use when an agent must resume, audit, or compare multi-step runs.

  advanced-ai/agent-state-memory/SKILL.md on GitHub (opens in a new tab)

• ml4t-agent-tool-contracts

  Typed tool contracts for autonomous research agents. Use when exposing files, search, databases, or execution tools to an LLM agent.

  advanced-ai/agent-tool-contracts/SKILL.md on GitHub (opens in a new tab)

• ml4t-multi-agent-forecasting

  Multi-agent probability forecasting with diversity, aggregation, and debate controls. Use when combining several agent forecasts or evaluating forecast ensembles.

  advanced-ai/multi-agent-forecasting/SKILL.md on GitHub (opens in a new tab)

• ml4t-research-operator

  Thin autonomous research operator pattern for ML4T experiments. Use when an agent should inspect artifacts, read skills, run scripts, and produce an auditable recommendation.

  advanced-ai/research-operator/SKILL.md on GitHub (opens in a new tab)

• ml4t-cost-model

  Commission, slippage, and market-impact cost models for realistic strategy simulation. Use when backtesting to ensure P&L accounts for transaction costs.

  backtest/cost-model/SKILL.md on GitHub (opens in a new tab)

• ml4t-rl-execution

  Reinforcement learning for trade execution and hedging. Use when optimizing execution algorithms or dynamic hedging policies.

  backtest/rl-execution/SKILL.md on GitHub (opens in a new tab)

• ml4t-run-backtest

  Event-driven backtesting with realistic order execution, position tracking, and performance measurement. Use when simulating a trading strategy on historical data.

  backtest/run-backtest/SKILL.md on GitHub (opens in a new tab)

• ml4t-sensitivity-analysis

  Test strategy robustness to parameter variation and detect overfitting cliffs. Use when validating that performance is stable across parameter perturbations.

  backtest/sensitivity-analysis/SKILL.md on GitHub (opens in a new tab)

• ml4t-tearsheet

  Generate comprehensive performance reports from backtest returns. Use when summarizing backtest results for review or comparison.

  backtest/tearsheet/SKILL.md on GitHub (opens in a new tab)

• ml4t-backtest-overfitting

  Detect and prevent overfitting to historical data via multiple testing corrections and pre-registration. Use when evaluating strategy variants to ensure performance is not a data-mining artifact.

  concepts/backtest-overfitting/SKILL.md on GitHub (opens in a new tab)

• ml4t-causal-identification

  Validate causal claims using DAG adjustment sets, bad-control detection, and refutation tests. Use when distinguishing genuine factor effects from confounded associations.

  concepts/causal-identification/SKILL.md on GitHub (opens in a new tab)

• ml4t-data-leakage

  Prevent train-test contamination, target leakage, and temporal leakage. Use when splitting data, fitting preprocessors, or engineering features for time-series ML.

  concepts/data-leakage/SKILL.md on GitHub (opens in a new tab)

• ml4t-information-coefficient

  Measure predictive signal quality with IC, Rank IC, and IC_IR. Use when evaluating whether a feature has predictive power for returns.

  concepts/information-coefficient/SKILL.md on GitHub (opens in a new tab)

• ml4t-lookahead-bias

  Detect future information leaking into features, labels, or evaluation. Use when any pipeline step might expose data not yet available at prediction time.

  concepts/lookahead-bias/SKILL.md on GitHub (opens in a new tab)

• ml4t-non-stationarity

  Handle changing statistical properties in financial time series. Use when features or model performance degrade over time.

  concepts/non-stationarity/SKILL.md on GitHub (opens in a new tab)

• ml4t-point-in-time

  Ensure data reflects what was known at each decision point, not revised or restated values. Use when joining fundamental, macro, or alternative data to price series.

  concepts/point-in-time/SKILL.md on GitHub (opens in a new tab)

• ml4t-regime-awareness

  Market regimes as conditioning features for risk scaling, not timing signals. Use when incorporating regime detection into strategy logic.

  concepts/regime-awareness/SKILL.md on GitHub (opens in a new tab)

• ml4t-survivorship-bias

  Account for delisted and removed securities in historical analysis. Use when constructing universes or computing cross-sectional features to avoid survivor-only inflation.

  concepts/survivorship-bias/SKILL.md on GitHub (opens in a new tab)

• ml4t-transaction-costs

  Estimate whether a strategy can survive spread, slippage, and market impact before full simulation. Use when screening strategy feasibility early.

  concepts/transaction-costs/SKILL.md on GitHub (opens in a new tab)

• ml4t-build-bars

  Aggregate tick data into time, volume, and dollar bars. Use when resampling raw tick data into regular or information-driven bars.

  data/build-bars/SKILL.md on GitHub (opens in a new tab)

• ml4t-calendar-ops

  Trading calendar awareness for correct date alignment and rolling windows. Use when aligning data across markets or computing holiday-aware windows.

  data/calendar-ops/SKILL.md on GitHub (opens in a new tab)

• ml4t-continuous-futures

  Build roll-adjusted continuous futures series without artificial price jumps. Use when backtesting futures strategies that span contract rollovers.

  data/continuous-futures/SKILL.md on GitHub (opens in a new tab)

• ml4t-data-export

  Export financial data in efficient columnar formats with schema enforcement. Use when persisting datasets for reproducible research or cross-pipeline sharing.

  data/data-export/SKILL.md on GitHub (opens in a new tab)

• ml4t-define-universe

  Define point-in-time tradeable universes with liquidity filters. Use when constructing the investable asset set that avoids survivorship and liquidity bias.

  data/define-universe/SKILL.md on GitHub (opens in a new tab)

• ml4t-fetch-data

  Reliable data acquisition with provider abstraction and schema validation. Use when ingesting market data from APIs, databases, or files.

  data/fetch-data/SKILL.md on GitHub (opens in a new tab)

• ml4t-validate-data

  Systematic data quality validation before modeling. Use when checking for gaps, outliers, stale prices, or schema violations in datasets.

  data/validate-data/SKILL.md on GitHub (opens in a new tab)

• ml4t-compute-features

  Systematic feature computation across multiple assets with group-aware operations. Use when computing technical or fundamental features for a panel of securities.

  features/compute-features/SKILL.md on GitHub (opens in a new tab)

• ml4t-feature-families

  Five families of financial features - momentum, mean-reversion, volatility, carry, and value. Use when designing a feature set to ensure coverage across complementary market dynamics.

  features/feature-families/SKILL.md on GitHub (opens in a new tab)

• ml4t-feature-selection

  Select informative features using IC ranking, mutual information, or RFE - always within CV folds. Use when reducing feature dimensionality before training.

  features/feature-selection/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 270k stars · 1 skill
• taste-skillby Leonxlnx Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages 97.3k stars · 13 skills
• archifyby tt-a1i Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more. 84.1k stars · 2 skills
• khazix-skillsby KKKKhazix 数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader（帮你定义目标）, neat-freak 洁癖, hv-analysis, khazix-writer & more — Claude Code, Codex & 40+ agents 21.4k stars · 6 skills
• Kamiby tw93 👩 🚒 Good content deserves good paper. Layout rules and templates that let AI agents export PDF, PNG and editable PowerPoint. 12k stars · 1 skill
• gentle-aiby Gentleman-Programming Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Or… 7.8k stars · 20 skills