improvement-loop
The Improvement Loop
Overview
Improve the .claude/ pipeline after resolving the issue at hand — never during. When a skill, agent, hook, or script produces bad output, work through to the correct solution first, then update the pipeline with what you learned.
Core principle: Fix first, understand fully, improve last. Premature edits encode partial understanding.
When to Use
digraph when_to_use {
"Issue resolved successfully?" [shape=diamond];
"Root cause in pipeline file?" [shape=diamond];
"Worth encoding permanently?" [shape=diamond];
"Run improvement cycle" [shape=box style=filled fillcolor=lightgreen];
"Keep working on the issue" [shape=box];
"Skip - not a pipeline problem" [shape=box];
"Skip - one-off or too specific" [shape=box];
More from aaddrick/claude-desktop-debian
simplify
Manually trigger the cdd-code-simplifier agent to review and simplify code
54lint
Run shellcheck and actionlint on shell scripts and GitHub Actions workflows. Use before pushing or when fixing lint issues.
44setup-build-tools
Install build and extraction tools needed for building Claude Desktop Debian packages
44writing-agents
Use when creating new agents, editing existing agents, or defining specialized subagent roles for the Task tool
22implement-issue
Use when given a GitHub issue number and base branch to implement end-to-end
18writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
17