This repository is a collection of specialized 'Skills' for the Claude AI assistant, each designed to enhance Claude's capabilities for specific professional tasks. The McKinsey Consultant Skill implements McKinsey's Problem Solving methodology to guide users through structured business analysis and generate professional PowerPoint presentations. The Mimeng Writing Skill helps create viral Chinese-style articles by encoding specific writing techniques. The Find-session Skill assists in locating and resuming specific Claude Code conversations through grep-based search of conversation history. The US Government Shutdown Tracker Skill fetches and analyzes economic data from the FRED API to assess liquidity impacts of government shutdowns, generating visualizations and status assessments. The repository demonstrates thoughtful architecture, particularly in the McKinsey Consultant Skill's progressive disclosure approach to manage Claude's context limitations, and contains several reusable components for PPT styling, economic data analysis, and visualization.
AutoHarness is a CLI-driven application for automated benchmark harness optimization. It implements an iterative workflow where proposals (code/config changes) are generated via LLMs or templates, applied to a target harness, evaluated using benchmark adapters (Tau2/Bench, HAL, Harbor, etc.), and promoted based on statistical validation. The system manages workspaces, tracks, campaigns, and iterations with persistent state stored under .autoharness/. Key features include proposal generators (Codex/Claude assistants, OpenAI Responses, failure-driven), benchmark adapters with staging isolation, configuration composition, and extensible plugin architecture for search strategies and preflight checks. The tool supports both interactive and non-interactive modes with configurable autonomy levels (proposal/bounded/full) and provides comprehensive inspection/export capabilities for auditability.