inspect

Inspect Autodialectics pipeline runs and retrieve run manifests and artifacts.

1|Updated Apr 12, 2026
One-click install
npx skills add https://github.com/Hmbown/plugins --skill inspect-hmbown
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: inspect
Source: https://github.com/Hmbown/plugins/tree/main/plugins/autodialectics/skills/inspect
Command: npx skills add https://github.com/Hmbown/plugins --skill inspect-hmbown

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Examine Autodialectics run results, manifests, and stored artifacts to facilitate debugging, auditing, and decision verification.

Core Features & Use Cases

  • Retrieve run manifests including status, decisions, scores, and timing.
  • Read and inspect individual artifacts such as submission, contract, evidence, dialectic, execution, verification, and evaluation.
  • Compare verification and evaluation outcomes to identify gaps and root causes for failures.

Quick Start

Run autodialectics inspect <run_id> to fetch and summarize the specified run.

Frequently Asked Questions about inspect

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I inspect Autodialectics pipeline runs and artifacts to debug failures?

Inspect Autodialectics pipeline runs by retrieving run manifests to assess status, decisions, and quality signals. Run autodialectics inspect <run_id> to fetch and summarize the specified run for debugging and auditing.

What is the best way to audit completed pipeline runs and verify decisions?

Auditing pipeline runs involves retrieving manifests that include status, scores, and timing. You can compare verification and evaluation outcomes to identify gaps and root causes for failures across multiple artifact stages.

Can I read individual pipeline artifacts like evidence and execution logs for auditing?

Yes, you can read and inspect individual artifacts such as submission, contract, evidence, dialectic, execution, verification, and evaluation. Use read_artifact(run_id, artifact_name) to retrieve specific artifact data for auditing.

Do I need the autodialectics-mcp tool to inspect run manifests and artifacts?

Yes, the autodialectics-mcp tool must be on PATH to inspect run manifests and artifacts. The inspection functionality exposes inspect_run(run_id) and read_artifact(run_id, artifact_name) for retrieval.

Can I inspect in-progress pipeline runs or only completed runs for debugging?

You can inspect both completed and in-progress pipeline runs for debugging and auditing. The inspection applies across multiple artifact stages to enable status assessment and decision verification during execution.

Why does comparing verification and evaluation outcomes help with pipeline debugging?

Comparing verification and evaluation outcomes identifies gaps and root causes for pipeline failures. This comparison reveals discrepancies between expected and actual results across artifact stages during the inspection process.