run-deep-swe
97 / 100 · Low risk
Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.
Score any AI model on the DeepSWE coding-agent benchmark via the OpenRouter API. Use when the user wants an independent, reproducible coding-agent eval — "run DeepSWE", "benchmark this model on DeepSWE", "score model X on the coding benchmark", "test a model via OpenRouter on DeepSWE", or to verify vendor-reported coding scores. Covers setup, the OpenRouter wiring for mini-swe-agent, single-task / subset / full 113-task runs, and leaderboard submission.
What this skill can do
Runs commands on your computer
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'run-deep-swe' ] || [ -L ~/.agents/skills/'run-deep-swe' ]; then echo 'A skill folder named run-deep-swe already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/adriannoes/awesome-agentic-ai' "$d" && git -C "$d" checkout --quiet 'e797ed58cfe6dd6453fe7632f89d7226d203f6f6' -- 'cursor-claude-codex/skills/david-ondrej/agent-orchestration/run-deep-swe' && mkdir -p ~/.agents/skills && cp -R "$d"/'cursor-claude-codex/skills/david-ondrej/agent-orchestration/run-deep-swe' ~/.agents/skills/'run-deep-swe' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'run-deep-swe' ~/.claude/skills/'run-deep-swe' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/adriannoes/awesome-agentic-ai/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-07 | e797ed5 | 97 |