Gskill

gskill

[](LICENSE) [](https://claude.ai/code)  [](https://github.com/itsmostafa/gskill/pulls)

Automatically learns repository-specific skills for coding agents using evolutionary search.

Given a GitHub repository, gskill produces a `.claude/skills/{repo}/SKILL.md` file containing optimized instructions that dramatically improve an agent's resolve rate on that repo's issues. It implements the pipeline described in the [GEPA blog post](https://gepa-ai.github.io/gepa/blog/2026/02/18/automatically-learning-skills-for-coding-agents/), which demonstrated improvements from 24% → 93% resolve rate on some repositories.

How it works

1. Loads verifiable software engineering tasks from SWE-smith for the target repository
2. Generates an initial skill via static analysis of the repo (README, config files) + gpt 5.2.
3. Uses GEPA's optimize_anything to iteratively refine the skill through evolutionary search
4. Each candidate skill is evaluated by running mini-SWE-agent on training tasks inside Docker and checking whether the FAIL_TO_PASS tests pass
5. Writes the best-scoring skill to disk

Requirements

• Python 3.13+
• uv
• Docker (for running SWE-smith task environments)
• OPENAI_API_KEY set in your environment (for initial skill generation and GEPA reflection)
• GSKILL_AGENT_MODEL (optional) — LiteLLM model string for mini-SWE-agent (default: openai/gpt-5.2)

Installation

git clone https://github.com/your-org/gskill
cd gskill
uv sync

Usage

Run the full pipeline

uv run python main.py run h