en un clic
run
// Compile and execute an Autodialectics anti-slop pipeline for a task. Covers health checks, runtime init, contract compilation, and full pipeline execution.
// Compile and execute an Autodialectics anti-slop pipeline for a task. Covers health checks, runtime init, contract compilation, and full pipeline execution.
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.
Re-run a stored Autodialectics pipeline run, optionally with a different policy, to compare outcomes or debug regressions.
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.
| name | run |
| description | Compile and execute an Autodialectics anti-slop pipeline for a task. Covers health checks, runtime init, contract compilation, and full pipeline execution. |
Use this skill to drive the Autodialectics anti-slop pipeline against a task.
autodialectics-mcp must be on PATH (pip install autodialectics).
health — verify the MCP server is reachable.init_runtime — ensure the database and default champion policy exist.compile_task — compile the task JSON into an immutable contract. Inspect it before proceeding.run_task — execute the full pipeline (evidence → dialectic → execution → verification → evaluation → gate).
detach: true for long-running tasks. Poll with inspect_run afterward.If the MCP server is not available:
autodialectics init
autodialectics compile <task.json>
autodialectics run <task.json>
Tasks are JSON files with at minimum:
{
"title": "Short description",
"description": "What needs to be done and why",
"domain": "code|research|writing|experiment|analysis|generic",
"workspace_root": "path/to/workspace",
"verification_commands": ["pytest -q"],
"assets": [{"kind": "file", "location": "path/to/file", "label": "name"}]
}
policy_id to run_task to test a specific policy instead of the current champion.If the user passes a task path after /autodialectics:run, treat it as the target task file and execute the compile → run workflow.