// Re-run a stored Autodialectics pipeline run, optionally with a different policy, to compare outcomes or debug regressions.
| name | replay |
| description | Re-run a stored Autodialectics pipeline run, optionally with a different policy, to compare outcomes or debug regressions. |
Use this skill to replay a previous pipeline run with an optional policy override.
autodialectics-mcp must be on PATH (pip install autodialectics).
replay_run(run_id, policy_id?) — re-execute a stored run manifest. If policy_id is provided, the replay uses that policy instead of the original.autodialectics replay <run_id>
autodialectics replay <run_id> --policy <policy_id>
inspect_run the original before replaying — understand what happened first.If the user passes a run ID after /autodialectics:replay, replay that run and summarize the comparison with the original.
Run benchmark suites and manage policy evolution — create challengers, compare against champions, promote or rollback policies.
Examine Autodialectics run results, manifests, and stored artifacts. Use after a pipeline run completes or to review past runs.
Compile and execute an Autodialectics anti-slop pipeline for a task. Covers health checks, runtime init, contract compilation, and full pipeline execution.
Use the local Autodialectics MCP server and CLI to compile tasks, execute anti-slop runs, inspect artifacts, replay runs, benchmark policies, and evolve champions in this repository.