skills.rest
Hmbown
HmbownCOMMUNITY
Explore all skills by this author →
Website𝕏@goodhuntGitHub

replay

Replay stored Autodialectics pipeline runs with an optional policy override.

1|Updated Apr 12, 2026
Search Tags:#debugging#comparison#pipeline#regression#policy#replay#autodialectics
One-click install
npx skills add https://github.com/Hmbown/plugins --skill replay-hmbown
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: replay
Source: https://github.com/Hmbown/plugins/tree/main/plugins/autodialectics/skills/replay
Command: npx skills add https://github.com/Hmbown/plugins --skill replay-hmbown

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Replay a stored Autodialectics pipeline run, optionally with a different policy, to compare outcomes and diagnose regressions.

Core Features & Use Cases

  • Replay stored runs with an optional policy override to assess impact.
  • Compare decisions, scores, and evidence across runs to identify drift.
  • Debug regressions by replaying historical runs with alternative policies.

Quick Start

Replay a previously run Autodialectics pipeline with an optional policy override.

Frequently Asked Questions about replay

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

FAQPage Schema
How do I replay a stored pipeline run to debug regressions?▼

Replaying a stored pipeline run requires calling the replay_run function with the target run_id. You can optionally include a policy_id to override the original policy and compare outcomes for regression testing.

Can I compare outcomes by replaying a historical run with a different policy?▼

Yes, you can compare outcomes by passing an optional policy_id to the replay_run function. This overrides the original policy, allowing you to assess the impact on decisions, scores, and evidence to identify drift.

Do I need autodialectics-mcp installed to replay pipeline runs?▼

Yes, you need autodialectics-mcp installed and available on your system PATH. The replay function depends on this environment to access stored pipeline runs and execute the comparison logic.

What is pipeline replay used for in regression testing?▼

Pipeline replay in regression testing is used to re-run stored historical runs with optional policy overrides. This helps developers compare decisions, scores, and evidence across runs to identify drift and diagnose regressions.

Why does my replayed run show different scores and evidence?▼

Replayed runs show different scores and evidence when you apply an optional policy override during the replay. Comparing these outcomes across runs helps identify policy impact and diagnose regressions.

Related Skills

Explore More Software Engineering Skills→
HmbownHmbown

inspect

Inspect Autodialectics pipeline runs and retrieve run manifests and artifacts.

Community
Intermediate
pkuppenspkuppens

skill-benchmark

Compare agent outputs with and without skill activation using a structured scoring framework.

Community
Intermediate
HmbownHmbown

benchmark

Benchmark policy performance and guide champion/challenger evolution.

Community
Advanced
HmbownHmbown

run

Execute the Autodialectics anti-slop pipeline with health checks and contract compilation.

Community
Advanced