A-EVO-Lab/a-evolve

The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".

769Stars on the repository
17Mods indexed here, across every type
10d agoLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

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

769 +4 10d ago A 34 tokens

debug-and-fix

02

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

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

769 +4 10d ago A 29 tokens

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

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

769 +4 10d ago A 24 tokens

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

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

769 +4 10d ago A 34 tokens

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

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

769 +4 10d ago A 33 tokens

self-verification

06

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

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

769 +4 10d ago A 19 tokens

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

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

769 +4 10d ago A 28 tokens

harness-optimizer

08

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

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.

769 +4 10d ago A 37 tokens

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

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

769 +4 10d ago A 24 tokens

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

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

769 +4 10d ago A 31 tokens

gui-navigation

11

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

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

769 +4 10d ago A 22 tokens

screenshot-analysis

12

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

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

769 +4 10d ago A 21 tokens

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

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

769 +4 10d ago A 28 tokens

data-formats

14

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

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

769 +4 10d ago A 34 tokens

python-packages

15

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

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

769 +4 10d ago B 27 tokens

skill-usage

16

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

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

769 +4 10d ago A 20 tokens