メニュー
Test the generated project inside an E2B cloud sandbox via Claude Code, apply fixes iteratively, and produce a quality report
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Search and install agent skills from ClawHub, the public skill registry.
Schedule reminders and recurring tasks.
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.
Research a hackathon using a user-supplied URL plus optional doc URLs (sitemap-driven scrape).
Two-layer memory system with grep-based recall.
| name | tester |
| description | Test the generated project inside an E2B cloud sandbox via Claude Code, apply fixes iteratively, and produce a quality report |
| metadata | {"openclaw":{"always":false}} |
Validate the generated project inside an E2B cloud sandbox: Claude Code installs dependencies, runs tests, applies fixes iteratively, and writes a structured report. The entire phase runs in an isolated Linux VM with full internet access.
After coder agents have finished implementing. Requires hackathon/project/ to exist.
Phase 6 uses E2BTestingExecutor which:
hackathon/project/ and sibling artifacts (plan.md, tasks.json, etc.).claude --dangerously-skip-permissions inside the sandbox with the
testing prompt — CC has full autonomy to install packages, run tests, fix
issues, and start servers.test_results.json from the sandbox to the local workspace.The sandbox provides full isolation from the host system with internet access, so pip/npm install and server startup work without restrictions.
hackathon/test_results.json