Retrospect — Development skill for Claude Code
Analysis for a run and its results, process, suggestions for process improvements, process optimizations, fixes, etc. for the next runs.
How to install Retrospect
Installs to ~/.claude/skills/a5c-ai-babysitter-pi-retrospect/SKILL.md
mkdir -p ~/.claude/skills/a5c-ai-babysitter-pi-retrospect && curl -fsSL https://raw.githubusercontent.com/a5c-ai/babysitter-pi/HEAD/commands/retrospect.md -o ~/.claude/skills/a5c-ai-babysitter-pi-retrospect/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Retrospect does
description: Analysis for a run and its results, process, suggestions for process improvements, process optimizations, fixes, etc. for the next runs. argument-hint: "[run-id...] [--all] Specific run IDs, --all for all runs, or defaults to latest" allowed-tools: Read, Grep, Write, Task, Bash, Edit, Grep, Glob, WebFetch, WebSearch, Search, AskUserQuestion, TodoWrite, TodoRead, Skill, BashOutput, KillShell, MultiEdit, LS
Invoke the babysitter:babysit skill (using the Skill tool) and follow
Alternatives in Development
- Mempalace Status — Show the current state of your memory palace — wings, rooms, drawer counts, and suggestions 58.6k ★
- Resume Work From A Handoff Document — You are tasked with resuming work from a handoff document through an interactive process 10k ★
- Grammar Check — Identify grammar and flow errors with targeted fix suggestions 7.8k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Suggest Changes
Analyze the agent-monitor debug logs and codebase to discover concrete improvements, fixes, and optimizations.
Overnight PRs
Autonomous overnight loop — verify issues against the codebase, close stale ones, ship PRs through /ship (bug
Dream
Overnight autoresearch + maintainer sweep that surfaces a MORNING REPORT — suggested changes, issues raised wi
System Review
Analyze implementation vs plan for process improvements
Pbi Error
Diagnose DAX errors across 7 categories (syntax, type mismatch, circular dependency, missing column, ambiguous
Orbit Prompt
Analyze and improve your prompt before sending — returns ORIGINAL PROMPT, ANALYSIS, IMPROVED PROMPT, KEY IMPRO
Related Agents
Improver
Dispatched by self-improve, self-lint, self-perf, and refactor workflows to apply targeted code improvements (
Experiment Tracker
PROACTIVELY use this agent when experiments are started, modified, or when results need analysis. This agent s
Optimization Engineer
MUST BE USED when implementing performance optimizations based on profiling data. This agent specializes exclu