Walk Forward Leakage Auditor

Audits time-based machine learning backtests, walk-forward validation, rolling retraining, forecasting evaluations, and temporal train/test pipelines for data leakage, faulty split logic, invalid feature timing, target leakage, calibration/tuning leakage, and misleading experiment comparisons. Use when agent needs to review or change walk-forward code, time-series ML experiments, trading backtests, forecasting notebooks, rolling CV logic, or any model evaluation where past-to-future chronology matters.

6 starsAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add mospira/walkforward-audit --skill walk-forward-leakage-auditor

Manual install

git clone --depth 1 https://github.com/mospira/walkforward-audit.git /tmp/walkforward-audit
mkdir -p ~/.claude/skills
cp -r /tmp/walkforward-audit/. ~/.claude/skills/walk-forward-leakage-auditor

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Walk-Forward Leakage Auditor

## Core Principle

Before trusting  reported metric, state the temporal contract:

```text
For a prediction made at <decision_time>, allowed inputs are <data sources> as known no later than <cutoff_time>. The target covers <future horizon>. Training may use rows ending at <train_end>, validation/calibration may use rows <validation_window>, and final reported performance comes only from <test_window>.
```

If the project cannot state this contract, the evaluation is not yet auditable.

## Audit Workflow

1. Map the evaluation timeline.
   - Identify the prediction timestamp, label horizon, feature cutoff, train window, validation/calibration window, test/scoring window, embargo/gap, and retrain cadence.
   - Verify that every reported metric is computed only after the model, thresholds, transforms, and selection rules are frozen for that test window.

2. Trace data through the pipeline.
   - Follow raw data into features, labels, datasets, splits, fitted transforms, models, predictions, decisions, and metrics.
   - Verify that every fitted object is trained inside the fold/window where it is used.
   - Distinguish label construction from model features: label code may look forward, but label columns must be excluded from model inputs.

3. Inspect code and artifacts against the checklist below.
   - For each suspicious pattern, decide: leak, harmless by construction, or needs a test/guard.

Read the full skill on GitHub

Details

Skill name: walk-forward-leakage-auditor
Repository: mospira/walkforward-audit
License: MIT
Repo updated: 13 June 2026

FAQ

What does the Walk Forward Leakage Auditor skill do?

How do I install the Walk Forward Leakage Auditor skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add mospira/walkforward-audit --skill walk-forward-leakage-auditor. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Walk Forward Leakage Auditor popular?

It lives in mospira/walkforward-audit, which has 6 GitHub stars and 0 forks.

Related skills

Xiaoci

evoworkAI/xiaoci-skill

中文成稿的去 AI 味清理工具（消磁）。识别并清除中文文本里的模型写作痕迹：翻案腔、破折号揭晓、提示语冒号、空转句引列表、段首零回指评论、相邻句结构同款、大纲式编号小标题、理想化拟人喻体、翻译腔、宣传腔、模糊归因、助手元话语残留。当用户说「去 AI 味」「改得说人话」「太像 AI 写的」「像 ChatGPT 写的」「润色得自然点」「过一遍 AI 痕迹」「humanize 中文」「deslop」「这稿子读着假」时使用。也可在 AI 参与写作的稿件定稿发布前主动调用。 Use to remove AI writing tells from Chinese text while preserving facts, register and voice.

AI, LLMs & Agents

Token Optimizer

samibajwaisking/Token-Optimizer-Skill

Maximize Claude's output quality while minimizing input token usage. Use this skill whenever a user wants to compress prompts, reduce token consumption, extract maximum output from Claude, write high-density instructions, optimize system prompts, or improve AI communication efficiency. Trigger on phrases like "optimize my prompt", "too many tokens", "make this shorter but better", "get more from Claude", "compress this prompt", "write a better system prompt", "token efficient", or any request to improve how someone communicates with Claude or any LLM. Also trigger when building AI-powered tool

AI, LLMs & Agents

Xl AI Language

40508597/xl-ai-language

为新项目设计、已有代码纳管、功能变更、架构重构和一致性校验提供任务架构流程。显式要求使用 Xl-Ai-Language 或任务架构流程，或当前项目存在 architecture.json 或 architecture/ 时，按本次任务范围启用。纯概念问答、只读查看和一次性实验走轻量路径。

AI, LLMs & Agents

Structflow

kings0527/structflow

Evidence-first structural research for industries, companies, commodities, tradable assets, and policy systems. Use when the user requests StructFlow or needs a rigorous, source-grounded analysis of system boundaries, variables, causal drivers, feedback loops, nonlinear dynamics, regimes, market distortion, structural signals, or asset mapping. Run canonical input resolution, staged L0-L7 modeling, adversarial challenge, contradiction search, deterministic research gates, and auditable report generation. Use the host agent's model for reasoning; no separate LLM API key is required. Optional Ta

AI, LLMs & Agents

方源 PPT 单页逻辑梳理

Liuguanyi2125/ppt-copywriting-logic-skill

当用户需要把原始材料、会议纪要、论文/方案资料、领导给的散乱内容或已有 PPT 页面，梳理成 PPT 页面级结论、文案层级、逻辑关系、页面结构和 AI 视觉提示词时使用。 Trigger: "帮我梳理 PPT 文案", "这页 PPT 逻辑怎么排", "把这些内容整理成 PPT", "方源 PPT 单页逻辑梳理", "方源梳理 PPT 文案", "PPT 页面文案和逻辑

AI, LLMs & Agents

Seedance Shotlist Director

afloy011-spec/seedance-shotlist-director-en

Generate a director's shotlist as an editable HTML production board for Seedance 2.0. Use whenever the user provides a script, scene breakdown, story idea, or treatment to turn into a numbered shotlist with English Seedance prompts — trigger on "make a shotlist", "director’s shotlist", "break this script into prompts", "generate prompts for Seedance", or any request to convert narrative content into shot-by-shot prompts. Also use to revise an existing shotlist HTML — re-render the same document (read its embedded Project Bible JSON to restore context). BOUNDARY — tuned for Seedance 2.0; if the

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.