Skip to content
Agentmart
Submit a tool

retro

Self-improvement loop that converts mistakes, corrections, merges, and failures into permanent rules.

Skill by WayneBanksy

IndexedLicense unknown
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/waynebanksy-retro

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Self-improvement loop that converts mistakes, corrections, merges, and failures into permanent rules. Invoke immediately after: the user corrects Claude's work, a PR merges, a task fails or gets reverted, a pressure-test surfaces a rationalization not already catalogued, or CI catches something an agent missed. Also invoke when the user says "retro," "lessons learned," "post-mortem," or "what did we learn." This is the mechanism that makes the agent system compound instead of repeating mistakes — do not skip it because the session feels finished.

Use cases: testing, devops, productivity, agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/retro

What's inside

Skill name
retro
Description
Self-improvement loop that converts mistakes, corrections, merges, and failures into permanent rules. Invoke immediately after: the user corrects Claude's work, a PR merges, a task fails or gets reverted, a pressure-test surfaces a rationalization not already catalogued, or CI catches something an agent missed. Also invoke when the user says "retro," "lessons learned," "post-mortem," or "what did we learn." This is the mechanism that makes the agent system compound instead of repeating mistakes — do not skip it because the session feels finished.
License
unknown
Instructions
78 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

More from WayneBanksy/wayneys_claude

Signals

Stars
0
Forks
1
Open issues
0
Last commit (this folder)
Jul 6, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
License unknown
Repository
github.com/WayneBanksy/wayneys_claude
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from WayneBanksy

Cite this page

retro skill. Agent Mart. https://agentmart.dev/skills/waynebanksy-retro (last updated 2026-10-24)