メニュー
Run the full Explorer end-to-end wheel test against a real LLM provider and Memgraph. Use to verify the Explorer produces valid wheels after changes to the exploration pipeline, transformations, or synthesis.
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
| name | df-wheel-test |
| description | Run the full Explorer end-to-end wheel test against a real LLM provider and Memgraph. Use to verify the Explorer produces valid wheels after changes to the exploration pipeline, transformations, or synthesis. |
| disable-model-invocation | true |
| allowed-tools | Bash(poetry run pytest *) |
Usage: /df-wheel-test
Runs the Explorer wheel end-to-end test with a real LLM provider. Requires Memgraph running (docker compose -f docker-compose.test.yml up -d) and provider credentials in .env.
poetry run pytest "tests/test_agents_e2e.py::TestExplorerEndToEnd::test_explorer_produces_wheels" --real-llm -v -s --tb=short
Review the layered prompt system that assembles the framework's dialectical reasoning — across apps, agents, concerns, and shared theory. Reviews at three altitudes — the isolated prompt, the assembled context it lands in, and the whole reasoning chain it steers. Use proactively when writing or modifying LLM prompts in agents/, concerns/, or orchestrator/tools/.
Sync the theory→implementation wiki (docs/theory/) with the Structured Dialectics theory PDFs and the codebase. Ingests/validates theory changes, updates the wiki's claim→code mapping and statuses, promotes essentials to CLAUDE.md, and reports theory↔implementation gaps. Use after theory PDFs change, after implementing/changing theory-encoding code, or to audit drift.
Manage the test Memgraph container (start/stop/restart/status/logs/clear/wipe) via docker-compose.test.yml. Use when graph tests need the DB up, data cleared, a stuck lock cleared, or the volume fully wiped.