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.
retro- Author
- Matt Pocock
- 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
/retrocommand — naming the skill in a message will not start it. - Codex:
$retro. - Cursor: type
/in the Agent chat and pickretro.
Example: /retro Look at yesterday's session where the agent spent an hour finding the payment config. What should change in the repo?
Install Writing for agents too: the first step calls it. The standards advice assumes a reviewer that reads CODING_STANDARDS.md, as the author's Code review against standards and spec does.
How it differs from similar skills
Context engineering for agents sets up rules files and context in advance. Retro works afterwards, from one session's evidence, and prefers an automated check to another line in AGENTS.md. Writing skills tests one skill document on subagents; retro looks at the whole environment. For a JavaScript or TypeScript guardrail, Pre-commit hooks setup adds Husky and lint-staged. No other catalog skill reviews a finished session.
Install
Run one command — it saves SKILL.md and the files it uses into your agent's skills folder. Claude Code and Codex pick up a new skill without a restart; if it does not show up, restart the agent.
curl -fsSL --create-dirs -o ~/.claude/skills/retro/SKILL.md https://anymodel.org/en/skills/matt-pocock/retro/SKILL.md -o ~/.claude/skills/retro/LICENSE https://anymodel.org/en/skills/matt-pocock/retro/LICENSE -o ~/.claude/skills/retro/agents/openai.yaml https://anymodel.org/en/skills/matt-pocock/retro/agents/openai.yaml
curl -fsSL --create-dirs -o ~/.agents/skills/retro/SKILL.md https://anymodel.org/en/skills/matt-pocock/retro/SKILL.md -o ~/.agents/skills/retro/LICENSE https://anymodel.org/en/skills/matt-pocock/retro/LICENSE -o ~/.agents/skills/retro/agents/openai.yaml https://anymodel.org/en/skills/matt-pocock/retro/agents/openai.yaml
foreach ($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 $p }foreach ($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
The user has asked for a retrospective. You are suggesting improvements to the coding agent's environment to improve future runs.
Steps
Call the Skill tool with
writing-for-agentsfor the writing style guide.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.
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-toollint/checkscripts, 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.mdfor 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.
- 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-agentsskill.
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.
AnyModel