Run Deep Swe

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.

100 stars 27 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add adriannoes/awesome-agentic-ai --skill run-deep-swe
Manual install
git clone --depth 1 https://github.com/adriannoes/awesome-agentic-ai.git /tmp/awesome-agentic-ai
mkdir -p ~/.claude/skills
cp -r /tmp/awesome-agentic-ai/cursor-claude-codex/skills/david-ondrej/agent-orchestration/run-deep-swe ~/.claude/skills/run-deep-swe

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Run DeepSWE via OpenRouter

DeepSWE (deepswe.datacurve.ai) is a 113-task Harbor-compatible coding-agent benchmark. It runs via **Pier** (Harbor fork) driving **mini-swe-agent** (model-agnostic). Any model reachable through OpenRouter can be scored.

## Prerequisites — state-check first

```bash
which uv git docker || echo "MISSING: install uv, git, docker"
docker info >/dev/null 2>&1 || echo "MISSING: Docker daemon not running (Pier's default sandbox)"
echo "OPENROUTER_API_KEY set? ${OPENROUTER_API_KEY:+YES}"
```

**Docker must be running** — Pier sandboxes each task in Docker by default (`--env modal` for cloud instead).

David has a dedicated OpenRouter key for this benchmark exported globally in `~/.zshrc` (weekly hard spend limit set as a safeguard). A fresh shell already has `OPENROUTER_API_KEY` available. If it's somehow not set, re-source the shell:

```bash
source ~/.zshrc && echo "key loaded? ${OPENROUTER_API_KEY:+YES}"
```

If still unset, ask David — never invent a key.

## Setup

```bash
git clone https://github.com/datacurve-ai/deep-swe && cd deep-swe
uv tool install datacurve-pier            # PyPI (preferred)
# or: uv tool install git+https://github.com/datacurve-ai/pier
# pier bundles mini-swe-agent as the --agent driver
```

Run all `pier` commands from inside `deep-swe/`, using relative `-p tasks/...`.

## OpenRouter wiring (the part the docs don't spell out)
Read the full skill on GitHub

Details

Skill name
run-deep-swe
Path
cursor-claude-codex/skills/david-ondrej/agent-orchestration/run-deep-swe/SKILL.md
License
MIT
Repo updated
2 November 2026

FAQ

What does the Run Deep Swe skill do?

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.

How do I install the Run Deep Swe skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add adriannoes/awesome-agentic-ai --skill run-deep-swe. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Run Deep Swe popular?

It lives in adriannoes/awesome-agentic-ai, which has 100 GitHub stars and 27 forks, and is included in 2 curated skill lists.

Related skills

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.