# Retrospective

> Analyse completed pipeline runs and surface DOD pass rates, loop-backs, and failure patterns.

- Skill: `wp-media/retrospective` (Agent Skill)
- Install (CLI): `npx skillmds@latest add wp-media/retrospective`
- Raw SKILL.md: https://api.skillmd.com/api/skills/wp-media/retrospective/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra
- Author: wp-media (https://skillmd.com/u/wp-media)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/wp-media/retrospective

---


# Retrospective

Closes the pipeline feedback loop. Scans completed issue runs, surfaces patterns the
team should act on, and proposes ready-to-paste Section 13 learnings for `AGENTS.md`.

## Project identity

Project identity is auto-detected (see AGENTS.md §3) — no config file.
This skill uses: `{TEMP_ROOT}`, `{REPO}`, `{DISPLAY_NAME}`.

## Steps

1. **Parse arguments** (if any):
   - No argument → analyse all runs found in `{TEMP_ROOT}/issues/`
   - Two ISO dates (e.g. `2026-05-01 2026-05-31`) → filter runs by `tasks.json` creation date

2. **Spawn `retrospective-agent`** with `{TEMP_ROOT}`, `{REPO}`, `{DISPLAY_NAME}`, and the
   date range (or `"all"` if not specified).

3. **Return** the output file path and a one-paragraph summary of the top finding.