Swe Team:retro | Agent Skills Atlas

About this skill

Post-run retrospective. Runs after swe-pr emits runcomplete. Analyzes the completed run — budget efficiency, failure patterns, replan triggers, verification outcomes — and appends compact learnings to .claude/swe-team/learnings.jsonl. Future runs' swe-lead reads the last N learnings at startup.

Quick start

Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.

Installation guide →

Review, license & listing details

Review the source before using this skill

This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.

Automated security scan: Partial

Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.

0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1

Content SHA-256: 016912a9bd9af400a94f8f61e21f5ec7f61464902f506e7c4f1a764276125caa

About scan coverage and limitations

Original listing metadata

Original name

swe-team:retro

Original description

Post-run retrospective. Runs after swe-pr emits run_complete. Analyzes the completed run — budget efficiency, failure patterns, replan triggers, verification outcomes — and appends compact learnings to .claude/swe-team/learnings.jsonl. Future runs' swe-lead reads the last N learnings at startup.

About this listing

Category: General
Reported license: MIT
Listing language (estimated): English
Review status: Not individually reviewed
Agent compatibility: Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.