About retro
retro is an agent skill for quickly recording a single useful observation in `.agents/learnings/`. It suits insights too small for a full retrospective, and each entry remains a candidate learning subject to later promotion.
Key features
- 01Capture a single learning quickly
- 02Create a slug from the insight
- 03Record date and provenance fields
- 04Save entries in the designated directory
Use cases
- 01Record a small lesson from ongoing work
- 02Keep useful insights from being left only in handoffs
Install
Copy the command and run it in a terminal.
npx skills add https:/ / github.com/ boshu2/ agentops --skill retroAfter installing, type/retroin Claude Code to confirm it loaded.
Bundled filesreferences/retro.featurescripts/validate.sh
Details
From the project READMERetro Skill
YOU MUST EXECUTE THIS WORKFLOW. Do not just describe it.
Quick-capture a learning to the knowledge flywheel. For comprehensive retrospectives with backlog processing, activation, and retirement, use /post-mortem.
Loop position
Lightest capture surface for move 7 of the operating loop. Single-observation quick-capture into .agents/learnings/. Use when an insight is too small to warrant a full /post-mortem and too potentially-useful to leave in the handoff. The promotion ratchet still applies after capture — a retro entry is a candidate learning, not yet a pattern or rule.
Quick Mode
Given /retro --quick "insight text" or /retro "insight text":
- Generate a slug from the content: first meaningful words, lowercase, hyphens, max 50 chars.
- Resolve the active bead with
timeout_run 1 bd current 2>/dev/null || echo "". - Write directly to
.agents/learnings/YYYY-MM-DD-quick-<slug>.md:
---
type: learning
source: retro-quick
source_bead: <active bead id when available>
source_phase: validate
date: YYYY-MM-DD
maturity: provisional
utility: 0.5
---
# Learning: <Short Title>
**Category**: <auto-classify: debugging|architecture|process|testing|security>
**Confidence**: medium
## What We Learned
<user's insight text>
## Source
Quick capture via `/retro --quick`
If no bead is active, omit source_bead intentionally and still set source_phase: validate.
- Confirm:
Learned: <one-line summary>
Saved to: .agents/learnings/YYYY-MM-DD-quick-<slug>.md
For comprehensive knowledge extraction, use `/post-mortem`.
Done. Return immediately after confirmation.
Examples
User says: /retro --quick "macOS cp alias prompts on overwrite — use /bin/cp to bypass"
What happens:
- Agent generates slug:
macos-cp-alias-overwrite - Agent resolves the active bead with
timeout_run 1 bd current 2>/dev/null || echo "" - Agent writes learning to
.agents/learnings/2026-03-03-quick-macos-cp-alias-overwrite.mdwith provenance fields like:
---
type: learning
source: retro-quick
source_bead: bd-123
source_phase: validate
date: 2026-03-03
maturity: provisional
utility: 0.5
---
- Agent confirms:
Learned: macOS cp alias prompts — use /bin/cp
Troubleshooting
| Problem | Cause | Solution |
|---|---|---|
| Learning too generic | Surface-level capture | Be specific: "auth tokens expire after 1h" not "learned about auth" |
| Duplicate learnings | Same insight captured twice | Check existing learnings with grep before writing |
| Need full retrospective | Quick capture isn't enough | Use /post-mortem for comprehensive extraction + processing |
Reference Documents
- references/retro.feature — Executable spec: single-observation capture to .agents/learnings/, candidate-under-ratchet, lightest move-7 surface (soc-qk4b)