Running Retro | Agent Skills Atlas

About this skill

Take an in-flight retrospective checkpoint mid-session: spawn a subagent to analyze the session transcript so far (reusing retro's parser), classify each finding by category and suggested resolution route (CLAUDE.md fix / rule fix / skill change / new-skill candidate / tracker issue), and append it to a cumulative running ledger — capture and route only, never auto-applied. The live counterpart to /session-flow:retro, which is the end-of-session full scoring + codification pass. An arm action instead launches a detached observer that watches this session out-of-band and runs the checkpoint autonomously after the session ends (zero context cost; findings land in the same ledger). Use when: 'running retro', 'live retro', 'in-flight retro', 'checkpoint this session', 'how is this session going', 'observe the session so far', 'arm the observer', 'watch this session in the background', 'observe this session after it ends', partway through a long skill loop, or on a /loop interval. Does NOT score the session, codify learnings (that is /session-flow:retro codify), auto-file issues, or /clear the session.

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: a3a20db3f7f40b863dcf5995ad27655ec2042e89a96cad1e0c704a8eea26a124

About scan coverage and limitations

Original listing metadata

Original name

running-retro

Original description

Take an in-flight retrospective checkpoint mid-session: spawn a subagent to analyze the session transcript so far (reusing retro's parser), classify each finding by category and suggested resolution route (CLAUDE.md fix / rule fix / skill change / new-skill candidate / tracker issue), and append it to a cumulative running ledger — capture and route only, never auto-applied. The live counterpart to /session-flow:retro, which is the end-of-session full scoring + codification pass. An `arm` action instead launches a detached observer that watches this session out-of-band and runs the checkpoint autonomously after the session ends (zero context cost; findings land in the same ledger). Use when: 'running retro', 'live retro', 'in-flight retro', 'checkpoint this session', 'how is this session going', 'observe the session so far', 'arm the observer', 'watch this session in the background', 'observe this session after it ends', partway through a long skill loop, or on a /loop interval. Does NOT score the session, codify learnings (that is /session-flow:retro codify), auto-file issues, or /clear the session.

About this listing

Category: Content & writing
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.