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.
Install
npx skills add adriannoes/awesome-agentic-ai --skill run-deep-swegit 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-swePersonal 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)Details
- Skill name
run-deep-swe- Repository
- adriannoes/awesome-agentic-ai
- 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
Browserstack
100adriannoes/awesome-agentic-ai
Run tests on BrowserStack. Use when user mentions "browserstack", "cross-browser", "cloud testing", "browser matrix", "test on safari", "test on firefox", or "browser compatibility".
Coverage
100adriannoes/awesome-agentic-ai
Analyze test coverage gaps. Use when user says "test coverage", "what's not tested", "coverage gaps", "missing tests", "coverage report", or "what needs testing".
Fix
100adriannoes/awesome-agentic-ai
Fix failing or flaky Playwright tests. Use when user says "fix test", "flaky test", "test failing", "debug test", "test broken", "test passes sometimes", or "intermittent failure".
Securing Agentic AI Tool Invocation
100adriannoes/awesome-agentic-ai
Apply least-privilege tool allowlisting, identity binding, and human-in-the-loop controls for agent tool calls.
Red Teaming Llms with Garak
100adriannoes/awesome-agentic-ai
Run NVIDIA garak probe suites against an LLM endpoint to test for jailbreaks, prompt injection, data leakage, and toxic generation, then interpret the hit-rate report for triage and reporting.
Testing for System Prompt Leakage
100adriannoes/awesome-agentic-ai
Extract and defend system prompts plus embedded secrets and routing logic.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.