Coding session retrospective

Reviews a finished coding session from its logs and proposes changes to the agent's environment: navigation pointers, lint rules, pre-commit and CI checks, reviewer standards, tool use. Use when an agent session went slowly or made avoidable mistakes.

Vibe codingPack: Matt Pocock's skills44 linesretro
Author
Source
mattpocock/skills/skills/engineering/retro @ abeeaf9
License
MIT · Copyright (c) 2026 Matt Pocock

About this skill

What it does

Retro looks back at a coding session and asks what in the agent's environment should change so the next run goes better. The agent loads the author's writing-for-agents style guide, then reads the session you name, searching your machine's session logs if needed, or the current one by default.

It checks seven areas: navigation (would a pointer in CLAUDE.md or AGENTS.md have saved a long search), automated checks, rules for the reviewer agent, an oversized global AGENTS.md, expensive tool calls, instructions that change nothing, and missing information such as dev server logs. It reads the repo's lint scripts and CI first, so an existing check that is unwired or broken is the finding; a repo with no pre-commit hook and no CI job for lint, typecheck or tests is a finding too. A mechanical rule becomes a linter rule, hook or CI job; CODING_STANDARDS.md is kept for judgement calls. You get a list ordered by severity; nothing is applied.

When to use it, and when not

Use it after a session where the agent hunted for a file, made a mistake a linter could catch, or burned tokens on a heavy tool call.

Skip it for reviewing the change itself or for a team retrospective about people: it looks only at what the agent reads and runs.

How to run it

The install command below puts the folder in place: SKILL.md, the licence and the Codex manifest agents/openai.yaml. With disable-model-invocation: true the agent never starts it by itself; call it:

  • Claude Code: only the /retro command — naming the skill in a message will not start it.
  • Codex: $retro.
  • Cursor: type / in the Agent chat and pick retro.

Example: /retro Look at yesterday's session where the agent spent an hour finding the payment config. What should change in the repo?

Install Writing for agents too: the first step calls it. The standards advice assumes a reviewer that reads CODING_STANDARDS.md, as the author's Code review against standards and spec does.

How it differs from similar skills

Context engineering for agents sets up rules files and context in advance. Retro works afterwards, from one session's evidence, and prefers an automated check to another line in AGENTS.md. Writing skills tests one skill document on subagents; retro looks at the whole environment. For a JavaScript or TypeScript guardrail, Pre-commit hooks setup adds Husky and lint-staged. No other catalog skill reviews a finished session.

Install

Run one command — it saves SKILL.md and the files it uses into your agent's skills folder. Claude Code and Codex pick up a new skill without a restart; if it does not show up, restart the agent.

Claude Code — macOS, Linux
curl -fsSL --create-dirs -o ~/.claude/skills/retro/SKILL.md https://anymodel.org/en/skills/matt-pocock/retro/SKILL.md -o ~/.claude/skills/retro/LICENSE https://anymodel.org/en/skills/matt-pocock/retro/LICENSE -o ~/.claude/skills/retro/agents/openai.yaml https://anymodel.org/en/skills/matt-pocock/retro/agents/openai.yaml
Codex, Cursor — macOS, Linux
curl -fsSL --create-dirs -o ~/.agents/skills/retro/SKILL.md https://anymodel.org/en/skills/matt-pocock/retro/SKILL.md -o ~/.agents/skills/retro/LICENSE https://anymodel.org/en/skills/matt-pocock/retro/LICENSE -o ~/.agents/skills/retro/agents/openai.yaml https://anymodel.org/en/skills/matt-pocock/retro/agents/openai.yaml
Claude Code — Windows PowerShell
foreach ($f in 'SKILL.md','LICENSE','agents/openai.yaml') { $p = Join-Path "$HOME\.claude\skills\retro" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/matt-pocock/retro/$f" -UseBasicParsing -OutFile $p }
Codex, Cursor — Windows PowerShell
foreach ($f in 'SKILL.md','LICENSE','agents/openai.yaml') { $p = Join-Path "$HOME\.agents\skills\retro" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/matt-pocock/retro/$f" -UseBasicParsing -OutFile $p }

Any other agent: save the file into its skills folder, or give it the link to the file: https://anymodel.org/en/skills/matt-pocock/retro/SKILL.md

SKILL.md

Raw

The user has asked for a retrospective. You are suggesting improvements to the coding agent's environment to improve future runs.

Steps

  1. Call the Skill tool with writing-for-agents for the writing style guide.

  2. Read the primary sources for the session the user specifies. This may mean searching through session logs on this machine. If the user doesn't specify a session, default to the current one.

  3. Look for candidates for improvement in these categories.

  • Navigation: how easy was it for the agent to find the right files? Are there hidden dependencies between files? Would a navigation pointer make it easier? Use when the session took a long time to find a piece of information.
  • Automated checks: are there automated checks that could catch errors the agent made? Linting, typing, tests, filesystem linters? Read the repo's own check command first (its package.json/build-tool lint/check scripts, its CI workflow), so a check that already exists but sits unwired or silently broken is the finding, not a reinvention. A repo with no guardrail (no pre-commit hook and no CI job running its lint/typecheck/test command) is itself a finding: an un-linted repo is a standing missed opportunity, not a neutral default. Use when the agent made a mistake an automated check could have caught, or the repo has no guardrail at all.
  • Coding standards: should the reviewer agent be given a new rule to enforce? Should an existing rule be removed or clarified? Classify the violation first: a mechanical one (a fixed syntactic pattern, a banned API, an import shape, a file-location rule) gets a deterministic check, full stop: a custom rule in the repo's own linter, a new pre-commit hook, or a new CI job, whichever the repo's language and existing guardrail make cheapest. Default to building the check over writing the rule. Reserve CODING_STANDARDS.md for genuine judgement calls (cross-file consistency, "matches the surrounding style," anything no guardrail could ever substitute for). Use when the reviewer agent failed to catch a mistake.
  • Global AGENTS.md: are there any steering instructions that should be moved to coding standards (or automated checks) instead? Use when the AGENTS.md file is particularly large - in the repo OR the user's global scope.
  • Tool economy: did the agent make expensive tool calls that could be streamlined? Is there any custom tooling (CLI's, MCP's) that is particularly token-inefficient? Use when the agent made an expensive tool call.
  • No-ops: look for instructions in steering files that don't modify the agent's behavior. Use when the steering files are large and unwieldy.
  • Information access: look for opportunities to increase the agent's access to information. Teeing dev server logs, readonly access to third-party services. Use when a crucial piece of information was not available to the agent.
  1. Present these candidates to the user, in order of severity.

Reference

Implementation vs Review

Remember that all work goes through two stages: implementation and review. The implementation agent has the most context pressure. They are responsible for exploration, writing code, and debugging failures.

The review agent has the least context pressure - it receives a diff, so no exploration needed. It often does not need to write code or debug.

This means that the review agent should be responsible for imposing coding standards, not the implementation agent.

Files

You have access to several files in the repo:

  • CLAUDE.md/AGENTS.md: these files are pushed to the context window of any agent working in this repo. They should be used incredibly sparingly, usually only for navigation pointers to other files.
  • CODING_STANDARDS.md: this file is read during review, not implementation. Add navigation pointers to docs folders if the standards file gets more than 1,000 lines long.
  • Docs: use docs as references files, pointed to by other files. Look for existing docs before writing new ones.
  • Skills: use skills for docs (since their description goes into the agent's context window), or for user-invoked commands. Follow the advice in the writing-for-agents skill.

Connect through AnyModel API

This skill runs on whatever model your agent uses. Point Claude Code, Codex or Cursor at AnyModel to run it on Claude, GPT, Gemini and more with one key — pay per token, no subscription.

More from the pack Matt Pocock's skills

Code review against standards and spec

Reviews the diff since a commit, branch or tag on two axes in parallel subagents: the repo's written standards plus a baseline of Fowler code smells, and the originating spec or issue. Use when a branch or PR needs checking against its spec.

Deep module design

Fixes a shared vocabulary for deep modules (interface, seam, adapter, depth, leverage), with the deletion test, dependency categories and a design-it-twice pattern on parallel subagents. Use when designing a module's interface or deciding where a seam goes.

Diagnosing hard bugs

Diagnoses hard bugs and slowdowns by first building a fast, deterministic command that reproduces the exact symptom, then minimising it, ranking falsifiable hypotheses and adding a regression test at a real seam. Use when something fails, throws or got slow.

Domain modeling

Sharpens a project's domain language during design: challenges fuzzy or conflicting terms, writes resolved ones to GLOSSARY.md at once and offers a short ADR only for hard-to-reverse trade-offs. Use when discussing terminology or recording an ADR.

Implement a spec

Implements a spec and its tickets on one integration branch: a fresh implementer subagent per ticket in its own worktree, run in parallel along the blocking graph, then a code review and one fix pass. Use when the tickets from to-tickets are ready.

Improve codebase architecture

Finds shallow modules worth deepening, starting from the code that changes most, shows the candidates in an HTML report with before/after diagrams and grills the chosen one with you. Use when a codebase has grown hard to test or navigate.

Throwaway prototype

Builds throwaway code to answer one design question: a single-file clickable HTML demo for a state model, or several structurally different UI variants on one route switched by a URL param. Use when checking whether logic holds or how a page should look.

TDD with integration tests

Drives test-first work through public interfaces: agrees the seams to test with the user, runs one red-green cycle per test, mocks only at system boundaries and leaves refactoring to review. Use when building a feature or fixing a bug test-first.

Conversation to spec

Turns the current conversation and codebase into a spec with user stories, implementation and testing decisions, and publishes it to the issue tracker as ready-for-agent, without interviewing the user. Use when a discussed feature needs writing up.

Spec to tickets

Splits a spec, plan or conversation into tracer-bullet tickets, vertical slices that each fit one agent session, with blocking edges, and publishes them as local files or tracker issues. Use when work is too big for one session and needs a task graph.

Issue and PR triage

Triages issues and external PRs on the tracker: gives each a category and a state, checks for existing code and past rejections, reproduces bugs and writes agent briefs for ready work. Use when a maintainer works through incoming issues and PRs.

Wayfinder for huge work

Charts work too big for one agent session as a map issue with child decision tickets on the tracker, then resolves one ticket per session until the route to the goal is clear. Use when a large effort has open questions that block a spec or plan.

Bash wizard for manual steps

Generates an interactive bash script that walks a person through manual steps such as dashboard setup, API keys and CI secrets, opening each URL and saving values to .env and GitHub secrets. Use when setup or a migration needs steps only a human can take.

Git guardrails for Claude Code

Installs a Claude Code PreToolUse hook that stops the usual forms of git push, reset --hard, clean -f, branch -D and checkout or restore of the whole tree, for one project or all, then tests it. Use when you want a safety net against an agent pushing or discarding work on its own.

Migrate tests to shoehorn

Replaces as and as unknown as casts in TypeScript tests with fromPartial and fromAny from @total-typescript/shoehorn, adds the imports and runs the type check. Use when tests fake whole objects or cast partial test data to satisfy the compiler.

Pre-commit hooks setup

Sets up Husky and lint-staged in a Node repo so each commit runs Prettier on staged files, then the typecheck and test scripts, matched to the lockfile, and makes the first commit through the hook. Use when a repo has no commit-time checks.

Grilling a plan

Questions the user about a plan or decision in rounds of numbered questions with recommended answers, looks facts up itself through subagents and stops only when no decision is left assumed. Use when a plan needs stress-testing before work starts.

Teach me a topic

Runs a multi-session course in the current folder: a mission, trusted sources, short HTML lessons with quizzes, reference sheets and learning records that set the next lesson. Use when the user wants to learn a topic over time, not get one answer.

Decision questionnaire

Writes a Markdown questionnaire for someone who holds knowledge the user lacks, after asking only who it goes to and what answers are needed, with the most important questions first. Use when a decision depends on facts from another person.

Writing for agents

Gives the rules for writing text agents read: skill descriptions as context pointers, what to keep inline and what to move to a separate file, completion criteria, leading words and pruning. Use when creating or editing a skill, AGENTS.md or CLAUDE.md.