retro

Conduct a retrospective on a coding session.

npx skills add https://github.com/mattpocock/skills --skill retro

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.

Mais skills de mattpocock

ask-matt
mattpocock
Pergunte qual skill ou fluxo se adequa à sua situação. Um roteador sobre as skills invocadas pelo usuário neste repositório.
communicationresearchproductivity
chief-of-staff
mattpocock
Persiga um objetivo de longo prazo em uma única sessão, coordenando subagentes.
productivityproject-managementcommunication
claude-handoff
mattpocock
Transfira a conversa atual para um novo agente em segundo plano que assume o trabalho imediatamente.
codebase-design
mattpocock
Vocabulário compartilhado para projetar módulos profundos. Use quando o usuário quiser projetar ou melhorar a interface de um módulo, encontrar oportunidades de aprofundamento, decidir onde uma separação deve ocorrer, tornar o código mais testável ou navegável por IA, ou quando outra habilidade precisar do vocabulário de módulo profundo.
designdevelopmentcode-review
code-review
mattpocock
Revise as alterações desde um ponto fixo (commit, branch, tag ou merge-base) em dois eixos — Padrões (o código segue os padrões de codificação documentados deste repositório?) e Especificação (o código corresponde ao que a issue/PRD original solicitou?). Executa ambas as revisões em subagentes paralelos e as reporta lado a lado. Use quando o usuário quiser revisar uma branch, um PR, alterações em andamento, ou pedir para "revisar desde X".
testingdevelopmentcode-review
design-an-interface
mattpocock
Gere múltiplos designs de interface radicalmente diferentes para um módulo usando subagentes paralelos. Use quando o usuário quiser projetar uma API, explorar opções de interface, comparar formatos de módulo ou mencionar "projete duas vezes".
developmentdesignapi
diagnosing-bugs
mattpocock
Loop de diagnóstico para bugs difíceis e regressões de performance. Use quando o usuário disser "diagnostique"/"depure isso", ou relatar algo quebrado/lançando exceção/falhando/lento.
testingdevelopmentcode-review
domain-modeling
mattpocock
Construir e refinar o modelo de domínio de um projeto. Use quando o usuário quiser definir a terminologia do domínio ou uma linguagem ubíqua, registrar uma decisão arquitetural, ou quando outra habilidade precisar manter o modelo de domínio.
designdevelopmentdocument