retro
Review a coding session and recommend evidence-based improvements to the agent environment.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- retro
- metadata
- { "source": "https://github.com/mattpocock/skills/blob/49dd158/skills/engineering/retro/SKILL.md" }
- description
- Review a coding session and recommend evidence-based improvements to the agent environment.
- disable-model-invocation
- true
02 资源文件 1
- 参考文档agents/openai.yaml146 B
03 SKILL.md 正文
Retrospective
The user has asked for a retrospective. You are suggesting improvements to the coding agent's environment to improve future runs.
Steps
-
Use writing-for-agents for the writing style guide when the productivity plugin is available. If unavailable, keep recommendations concise, actionable, and focused on one source of truth.
-
Read the primary sources for the session the user specifies. Default to the current conversation and its artifacts when no session is named. For another session, use the specified logs or available read-only session tools; if access is missing, report that limit. Redact sensitive information before quoting evidence.
-
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 candidates in order of severity. For each, cite a concrete session failure or repository gap, the smallest proposed improvement, and the validation that would show it works. Distinguish observed failures from inferences; state when no justified improvement was found.
A retrospective produces recommendations. Apply changes only when the user has authorized that scope; do not treat the retrospective request as permission to edit global guidance, install tooling, commit, or publish tracker updates. For a broader repository-guidance assessment, the optional improve-repo-harness provides a separate workflow.
Reference
Implementation vs Review
Implementation and review have different context needs. Implementation must explore, write code, and debug; a reviewer can focus on the selected change and its governing guidance. Prefer deterministic checks for mechanical rules and focused reviewer guidance for judgement calls. Keep task-critical constraints available during implementation too.
Files
Look for the repository's existing guidance before proposing new documents:
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: keep judgement-based review rules here when this is the repository's established convention. 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.
04 同仓库更多 Skills
ui-ux-pro-max
UI/UX design intelligence for web and mobile. Local database with 79 searchable styles (88 catalog entries), 192 color palettes, 74 font pairings, 192 product types, 119 UX guidelines, 105 curated icon entries, 17 GSAP motion presets, and 25 chart types across 22 stacks (React, Next.js, Vue, Nuxt, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Jetpack Compose, Angular, Laravel, JavaFX, WPF, WinUI, Avalonia, Uno Platform, UWP, Three.js, and HTML/CSS). Use when designing, building, or reviewing UI: pages, components, color schemes, typography, layout, accessibility, animation, or data visualization.
figma-mcp
Implement or compare UI against Figma designs using an available Figma MCP integration. Use for Figma-backed implementation, design-token extraction, or visual-parity gap analysis; Figma MCP access is optional and must already be configured by the user.
improve-codebase-architecture
Find evidence-based, active-change architecture improvements using shared design and domain-modeling guidance. Use when a user wants to reduce architectural friction, deepen a module, or make a current change safer, more testable, and easier to navigate.
domain-modeling
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing GLOSSARY.md or CONTEXT.md, or recording or editing an ADR.
codebase-design
Provide the shared vocabulary and discipline for designing deep modules with clear interfaces and seams. Use when a user wants to design or improve a module, find deepening opportunities, choose a seam, or make code more testable and AI-navigable.
test-coverage-review
MUST invoke to review whether added or updated tests cover code changes in a diff. Checks new logic, branches, error paths, and regression risk, producing a change-to-test matrix. Use requirements-to-tests-traceability for acceptance-criteria mapping and orchestrated-review for bundled reviews.