retro

An agent skill by mattpocock, from mattpocock/skills. Tags: analysis, history, project-management, review, workflow.

What it does

Conduct a retrospective on a coding session.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add mattpocock/skills --skill retro

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/mattpocock/skills
cp -r skills/skills/engineering/retro ~/.claude/skills/retro

Safety box score

Grade A, minimal risk: 9 of 100 risk points, rated 2026-10-16. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a retrospective helper: it reads local session sources and repo metadata, then suggests environment improvements. It does not ship executables or modify the machine, but it can expose whatever is in session logs and other local project files.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	No shell commands, scripts, or code evaluation are shipped in `SKILL.md` or `agents/openai.yaml`; the skill is prose-only.
Network access	0 (none)	The files contain no download, upload, API, or remote-host instructions; all work is described as local reading.
Filesystem reach	1 (low)	It explicitly tells the agent to read local sources and may search session logs on the machine: `Read the primary sources for the session... searching through session logs on this machine`.
Secrets & credentials	1 (low)	By defaulting to local session logs, it may encounter pasted credentials or tokens that happen to be in those logs, even though it does not request secrets directly.
Privilege & persistence	0 (none)	There is no request for sudo, global installs, services, shell/profile edits, or other privilege-changing actions.
Instruction hijack surface	0 (none)	The instructions do not tell the agent to ignore its rules, hide behavior, or follow untrusted remote content; `writing-for-agents` is a normal helper-call instruction.
Irreversible actions	0 (none)	The skill only asks the agent to analyze and present retrospective candidates; it does not deploy, send messages, pay, delete, or publish anything.
Transparency	0 (none)	All shipped files are readable text (`SKILL.md`, `agents/openai.yaml`); there are no binaries, base64 blobs, or downloaded installers.

Before installing

Confirm your session logs do not contain pasted secrets before letting the agent read them.
If you want a narrower review, point it at a specific session instead of letting it default to the current one.
Check whether your repo already has CI/lint/test guardrails; this skill’s recommendations depend on those being discoverable.

Rated 2026-10-16 by an automated review of 2 files from the skill's repository.

Source

Repository: mattpocock/skills (all skills from this repository)
Path: skills/engineering/retro/SKILL.md
Branch: main
Updated: 2026-10-05

maintain-verification-skill — Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature.
recall — Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents).
show-me-your-work — Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result).
grilling — Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
automate-me — Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill".
differential-review — Performs security-focused differential review of code changes.