---
name: Retro
slug: retro
category: Quality
description: Retro audits a completed run’s checkpoints, evidence quality, and open action items after ship or escalation. Use it to close the loop and feed lessons into the next run.
github: "https://github.com/huytieu/COG-second-brain/tree/main/skills/retro"
language: HTML
stars: 930
forks: 110
install: "npx degit https://github.com/huytieu/COG-second-brain/tree/main/skills/retro ~/.claude/skills/retro"
installs_to: ~/.claude/skills/retro
source_path: skills/retro/SKILL.md
collection_size: 25
category_size: 1354
collection_url: "https://dirskills.com/collections/huytieu/COG-second-brain"
added: 2026-08-22T05:20:38.110Z
last_synced: 2026-08-22T05:20:38.110Z
canonical_url: "https://dirskills.com/skills/retro"
---

# Retro

Retro audits a completed run’s checkpoints, evidence quality, and open action items after ship or escalation. Use it to close the loop and feed lessons into the next run.

**Install:**

```bash
npx degit https://github.com/huytieu/COG-second-brain/tree/main/skills/retro ~/.claude/skills/retro
```

## README

# /retro — CP-7 close the V

Every non-`tiny` shipped or escalated run gets a retro. Retro is **advisory** but strongly expected: it is how the harness improves.

## When to run

- After CP-6 ship (approved publish, merged PR, vault deliverable done)
- After escalate (capture why verifier failed)
- End of an `/ultragoal` phase (one retro per phase)
- Manual: `/retro <run-dir or spec path>`

## Phase 1 — Gather evidence bundle

Read:

1. Spec or card description + acceptance criteria
2. `04-projects/harness/runs/<id>/evidence/` (ledger, checkpoints.tsv, CP-* files)
3. `.claude/logs/loop-ledger.tsv` (last rows for this run)
4. `04-projects/<goal>/STATUS.md` if an ultragoal phase

## Phase 2 — Checkpoint audit

For each CP the lane required, mark Expected vs Actual vs Gap:

| CP | `tiny` | `normal` | `full` |
|---|---|---|---|
| CP-1 spec | skip | required | required |
| CP-3v component | skip | required | required |
| CP-4 integration | skip | skip | required if multi-task |
| CP-5 acceptance | if mutate | required | required |
| CP-6 ship | if external | if external | required |

## Phase 3 — Evidence quality pass

Ask:

- Any AC-n shipped without a PASS evidence row? (traceability violation)
- Any PASS row where observation is tool-return not artifact? (confident-but-unchecked)
- Any criterion that wasn't falsifiable? (fix in next spec)

## Phase 4 — Write retro

Copy `04-projects/harness/templates/retro.md` to:

`04-projects/harness/retro/YYYY-MM-DD-<slug>.md`

Fill all sections. Action items get IDs (`AI-01`…).

## Phase 5 — Feed forward

1. **Harvest**: append action items + lessons to today's harvest staging
2. **Backlog**: add `AI-n` rows to `04-projects/harness/BACKLOG.md` if harness work
3. **STATUS.md**: if an ultragoal phase, advance the phase state + log open `AC-n`
4. **Spec checkpoint log**: update spec `## Checkpoint log` CP-7 row
5. Record: `bash .claude/lib/checkpoint.sh record <run-dir> CP-7 PASS "retro: <path>"`

## Output to the user

TL;DR: outcome, top lesson, top action item, retro path.