improvement-agent

Analyze delivery traces to generate and orchestrate improvement proposals.

1|Updated Mar 12, 2026

Search Tags:#automation #improvement #proposal-generation #trace-analysis #challenger #delivery-governance

Ready to run

npx skills add https://github.com/heymishy/skills-repo --skill improvement-agent

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: improvement-agent
Source: https://github.com/heymishy/skills-repo/tree/main/.github/skills/improvement-agent
Command: npx skills add https://github.com/heymishy/skills-repo --skill improvement-agent

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The improvement agent automates the self-improvement loop for the delivery governance platform, reading traces, detecting failure and staleness signals, proposing SKILL.md changes, and managing the challenger pre-check and review workflow end-to-end.

Core Features & Use Cases

Read and filter delivery traces to identify failure signals and stale activity.
Generate improvement proposals and orchestrate the challenger pre-check, review, and state updates.
Apply approved SKILL.md changes to the target skill via a controlled, auditable workflow.

Quick Start

Initiate an improvement cycle by analyzing traces, generating a failure-proposal, and starting the challenger pre-check.

Frequently Asked Questions about improvement-agent

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

FAQPage Schema

How do I automate improvement cycles for delivery governance?▼

To automate delivery governance improvement cycles, you can use an agent that reads delivery traces, detects failure and staleness signals, and orchestrates proposal lifecycles. It generates proposals, manages challenger pre-checks, records results, and updates state.

How do I analyze delivery traces to detect failure and staleness signals?▼

Analyzing delivery traces to detect failure and staleness signals is handled by querying traces through a dedicated trace interface. The agent filters trace data to identify where failure signals appear and where stale activity arises within the workflow.

Can I manage proposal generation and challenger pre-check workflows programmatically?▼

Yes, you can manage proposal generation and challenger pre-check workflows programmatically. The agent supports both programmatic and CLI usage, allowing you to initiate cycles, generate proposals, and record challenger results automatically.

What is the best way to apply approved changes to a SKILL.md file safely?▼

The best way to apply approved changes to a SKILL.md file safely is through a controlled, auditable workflow. The agent enforces a no-self-modify constraint, writes proposals to the workspace, and updates state only after challenger review.

Are there limitations on self-modification when generating improvement proposals?▼

Yes, there are limitations on self-modification when generating improvement proposals. The agent enforces a no-self-modify constraint, meaning it cannot directly alter its own codebase; it only writes proposals and updates workspace state files.