A-EVO-Lab/a-evolve

application-shortcuts

Keyboard shortcuts for common desktop applications — LibreOffice, GIMP, Chrome, Thunderbird, VS Code.

原文の言語: 英語

gui-click-over-keyboard

When to prefer GUI mouse clicks over keyboard shortcuts — especially for formatting, multi-step visual tasks, and cross-application workflows.

原文の言語: 英語

gui-navigation

General GUI navigation patterns for desktop environments — finding elements, interacting with menus, and handling dialogs.

原文の言語: 英語

screenshot-analysis

How to interpret accessibility tree elements and correlate them with screenshot regions for accurate GUI interaction.

原文の言語: 英語

self-verification

Verification patterns to confirm task completion before submitting. Read this before calling submit().

原文の言語: 英語

web-access-strategies

Workarounds for bot detection, CAPTCHA, 403 errors, and Cloudflare challenges when browsing the web.

原文の言語: 英語

build-compiled-extensions

How to build C/C++/Cython/Fortran extensions and frameworks like Caffe, OpenCV, protobuf-dependent projects from source.

原文の言語: 英語

debug-and-fix

Strategies for debugging build failures, runtime errors, writing complete output files (ICS/JSON/config), and constraint satisfaction tasks.

原文の言語: 英語

environment-discovery

Strategies for quickly discovering what tools, languages, and files are available in a Terminal-Bench container.

原文の言語: 英語

python-data-analysis

Best practices for multi-step Python tasks including data analysis, HuggingFace datasets, token counting, and any task requiring state across multiple python() calls.

原文の言語: 英語

scientific-computing

Strategies for scientific computing, numerical methods, bioinformatics/DNA tasks, logic circuit design, algorithmic challenges, and ML training tasks.

原文の言語: 英語

self-verification

Verification patterns to confirm task completion before submitting. Read this before calling submit().

原文の言語: 英語

systematic-exploration

Strategies for avoiding dead ends and premature conclusions. Read this when stuck or when an approach seems to not work.

原文の言語: 英語

harness-optimizer

Optimize an AI agent's harness for MCP-Atlas benchmark. Use when analyzing execution traces, diagnosing failures, and proposing improved prompts, skills, or harness code.

原文の言語: 英語

data-formats

Reading, writing, and converting common data formats (CSV, Excel, JSON, YAML) with correct handling of encoding, types, and edge cases.

原文の言語: 英語

environment-discovery

Strategies for quickly discovering what tools, languages, data files, and skills are available in a SkillBench container.

原文の言語: 英語

python-packages

Installing and using common Python packages in SkillBench containers. Covers scientific computing, data analysis, and file format libraries.

原文の言語: 英語

skill-usage

How to discover, load, and effectively use skills to solve SkillBench tasks.

原文の言語: 英語